flet ui (experimental)

.gitattributes

@@ -1,15 +0,0 @@
-*.py text eol=lf
-*.md text eol=lf
-*.yml text eol=lf
-*.yaml text eol=lf
-*.toml text eol=lf
-*.json text eol=lf
-*.txt text eol=lf
-*.html text eol=lf
-*.css text eol=lf
-*.js text eol=lf
-*.sh text eol=lf
-*.cfg text eol=lf
-*.ini text eol=lf
-*.svg text eol=lf
-*.j2 text eol=lf

.github/FUNDING.yml

@@ -1,6 +1,6 @@
 # These are supported funding model platforms
 
-github: [jborza, jeremiahsb, mohangk, k0sm0naft]
+github: [jborza, jeremiahsb, mohangk]
 patreon: # Replace with a single Patreon username
 open_collective: # Replace with a single Open Collective username
 ko_fi: # Replace with a single Ko-fi username

.github/workflows/test_pip.yml

@@ -1,9 +1,7 @@
-name: CI
-run-name: CI
-
-on:
+name: pip install
+run-name: pip install
+on: 
   push:
-    branches: [main]
     paths:
       - '**.py'
       - 'pyproject.toml'
@@ -13,41 +11,23 @@ on:
       - 'pyproject.toml'
       - '.github/workflows/**'
   workflow_dispatch:
-
 jobs:
-  test:
+  install-and-run:
     strategy:
       matrix:
-        os: [ubuntu-latest, macos-14, windows-latest]
+        os: [ubuntu-latest, macos-latest, windows-latest]
         python-version: ['3.12']
       fail-fast: false
+    continue-on-error: true
     runs-on: ${{ matrix.os }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v7
-
+        uses: actions/checkout@v4
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-
-      - name: Install uv
-        uses: astral-sh/setup-uv@v8.3.1
-        with:
-          enable-cache: true
-          prune-cache: false
-          cache-dependency-glob: pyproject.toml
-
-      - name: Install system dependencies (Ubuntu)
-        if: runner.os == 'Linux'
-        run: sudo apt-get update && sudo apt-get install -y libegl1
-
-      - name: Install dependencies
-        run: uv pip install --system .[dev]
-        env:
-          UV_LINK_MODE: copy
-
-      - name: Run tests
-        env:
-          QT_QPA_PLATFORM: offscreen
-        run: pytest tests/ -v --tb=short
+      - name: Install from repository
+        run: python -m pip install .
+      #- name: Run abogen
+      #  run: abogen

.github/workflows/test_publish.yml

@@ -18,7 +18,7 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v7
+    - uses: actions/checkout@v4
 
     - name: Login to Github Container Registry
       # Only if we need to push an image

.gitignore

@@ -39,4 +39,3 @@ dist/
 test_assets/
 dev_notes/
 .claude/
-.coverage

abogen/application/__init__.py

@@ -1,8 +0,0 @@
-"""Application layer for conversion flow unification.
-
-This package contains the application-level orchestration logic
-that bridges UI adapters (PyQt, WebUI) with domain functions.
-
-The main entry point is ConversionService.run() which coordinates
-planning, execution, and finalization of a conversion job.
-"""

abogen/application/conversion_executor.py

@@ -1,434 +0,0 @@
-"""Unified conversion executor.
-
-Takes a ConversionPlan and ports, executes the TTS conversion,
-and returns a ConversionResult. No UI imports allowed.
-
-This is Stage 6 of the conversion flow unification plan.
-"""
-
-from __future__ import annotations
-
-import time
-from contextlib import ExitStack
-from typing import Any, Callable, Dict, List, Optional, Tuple
-
-from abogen.application.conversion_models import (
-    ChapterPlan,
-    ConversionPlan,
-    IntroOutroSpec,
-    SegmentPlan,
-)
-from abogen.application.conversion_ports import (
-    AudioSink,
-    ConversionEvents,
-    PipelineProvider,
-    SubtitleWriter,
-    VoiceResolver,
-)
-from abogen.application.conversion_result import ConversionResult
-from abogen.domain.audio_sink import open_audio_sink
-from abogen.domain.conversion_engine import (
-    SegmentStats,
-    SynthParams,
-    process_and_write_subtitles,
-    synthesize_text,
-)
-from abogen.domain.enums import OutputFormat, SubtitleMode
-from abogen.domain.normalization import TTSContext
-from abogen.domain.output_paths import sanitize_filename_for_chapter
-from abogen.infrastructure.subtitle_writer import make_subtitle_writer
-
-
-def execute_conversion(
-    plan: ConversionPlan,
-    events: ConversionEvents,
-    pipeline_provider: PipelineProvider,
-    voice_resolver: VoiceResolver,
-    tts_context: TTSContext,
-    *,
-    check_cancelled: Optional[Callable[[], None]] = None,
-) -> ConversionResult:
-    """Execute a conversion plan and return the result.
-
-    Args:
-        plan: The conversion plan from build_conversion_plan()
-        events: UI-specific callbacks (log, progress, check_cancelled)
-        pipeline_provider: Provides TTS backends
-        voice_resolver: Resolves voice specs into loaded voices
-        tts_context: Normalization context for text processing
-        check_cancelled: Optional cancellation checker (overrides events.check_cancelled)
-
-    Returns:
-        ConversionResult with paths and markers
-
-    Raises:
-        ConversionCancelled: If conversion is cancelled
-    """
-    request = plan.request
-    result = ConversionResult(metadata=plan.metadata)
-
-    # Determine cancellation checker
-    if check_cancelled is None:
-        check_cancelled = lambda: events.check_cancelled()
-
-    # Stats for progress tracking
-    total_characters = sum(
-        len(ch.body_text) for ch in plan.chapters
-    )
-    if plan.intro and plan.intro.enabled:
-        total_characters += len(plan.intro.text)
-    if plan.outro and plan.outro.enabled:
-        total_characters += len(plan.outro.text)
-
-    stats = SegmentStats(
-        processed_chars=0,
-        current_time=0.0,
-        etr_start_time=time.time(),
-        total_characters=total_characters,
-    )
-
-    # Compute subtitle flag once (used in every synthesize_text call)
-    use_spacy = request.subtitle_mode not in (SubtitleMode.DISABLED, SubtitleMode.LINE)
-
-    # Output paths
-    output_layout = plan.output_layout
-    if not output_layout:
-        raise ValueError("ConversionPlan must have an output_layout")
-
-    # Determine if merged output is needed
-    merge_chapters = request.merge_chapters_at_end or not request.save_chapters_separately
-    if request.output_format == OutputFormat.M4B:
-        merge_chapters = True
-
-    # Resolve voices
-    base_voice_spec = request.voice or "M1"
-    base_provider, base_voice_choice, base_speed, base_steps = _resolve_voice(
-        voice_resolver, base_voice_spec, request
-    )
-
-    # Use ExitStack for resource management
-    with ExitStack() as stack:
-        # Open merged audio sink
-        audio_sink: Optional[AudioSink] = None
-        audio_path = None
-        if merge_chapters:
-            audio_path = output_layout.audio_dir / f"{_base_name(request)}.{request.output_format}"
-            meta = plan.metadata if plan.metadata else None
-            audio_sink = stack.enter_context(
-                open_audio_sink(
-                    audio_path,
-                    request.output_format,
-                    metadata=meta,
-                    cancel_check=check_cancelled,
-                )
-            )
-            result.audio_path = audio_path
-
-        # Open subtitle writer if needed
-        subtitle_writer: Optional[SubtitleWriter] = None
-        if request.subtitle_mode != SubtitleMode.DISABLED and audio_sink:
-            subtitle_writer = make_subtitle_writer(
-                audio_path,
-                request.subtitle_format,
-                request.subtitle_mode,
-                max_words=request.max_subtitle_words,
-            )
-            if subtitle_writer:
-                subtitle_writer.open()
-                stack.callback(subtitle_writer.close)
-                result.subtitle_paths.append(subtitle_writer.path)
-
-        effective_subtitle_mode = request.subtitle_mode if subtitle_writer else SubtitleMode.DISABLED
-
-        synth = SynthParams(
-            tts_context=tts_context,
-            stats=stats,
-            check_cancel=check_cancelled,
-            on_progress=lambda pct, etr: events.progress(pct, etr),
-            audio_sink=audio_sink,
-            subtitle_mode=effective_subtitle_mode,
-            max_subtitle_words=request.max_subtitle_words,
-            lang_code=request.language,
-            use_spacy_segmentation=use_spacy,
-        )
-
-        # Chapter directory
-        chapter_dir = None
-        if request.save_chapters_separately and len(plan.chapters) > 1:
-            chapter_dir = output_layout.audio_dir / "chapters"
-            chapter_dir.mkdir(parents=True, exist_ok=True)
-
-        # Process intro
-        intro_emitted = False
-        if plan.intro and plan.intro.enabled and merge_chapters:
-            events.log(f"Title intro: {plan.intro.text[:80]}")
-            intro_provider, intro_voice, intro_speed, intro_steps = _resolve_voice(
-                voice_resolver, plan.intro.voice_spec, request
-            )
-            intro_backend = pipeline_provider.get(intro_provider, request.language, request.use_gpu)
-            synthesize_text(
-                text=plan.intro.text,
-                params=synth,
-                backend=intro_backend,
-                voice=intro_voice,
-                speed=intro_speed or request.speed,
-                chapter_sink=None,
-                preview_callback=lambda text: events.log(f"  {text[:80]}"),
-            )
-            intro_emitted = True
-            events.log("Intro synthesized.")
-
-        # Chapter loop
-        for chapter_idx, chapter in enumerate(plan.chapters, 1):
-            check_cancelled()
-
-            chapter_display = f"Chapter {chapter_idx}/{len(plan.chapters)}: {chapter.title}"
-            events.log(f"Processing {chapter_display}")
-
-            # Resolve chapter voice
-            chapter_provider, chapter_voice, chapter_speed, chapter_steps = _resolve_voice(
-                voice_resolver, chapter.voice_spec, request
-            )
-            chapter_backend = pipeline_provider.get(chapter_provider, request.language, request.use_gpu)
-
-            # Per-chapter sink
-            chapter_sink: Optional[AudioSink] = None
-            chapter_path = None
-            if chapter_dir:
-                chapter_filename = sanitize_filename_for_chapter(chapter.title, chapter_idx)
-                chapter_path = chapter_dir / f"{chapter_filename}.{request.separate_chapters_format}"
-                chapter_sink = stack.enter_context(
-                    open_audio_sink(
-                        chapter_path,
-                        request.separate_chapters_format,
-                        cancel_check=check_cancelled,
-                    )
-                )
-                result.chapter_paths.append(chapter_path)
-
-            # Intro delay before first chapter
-            if not intro_emitted and plan.intro and plan.intro.enabled:
-                # Intro will be emitted with first chapter
-                intro_provider, intro_voice, intro_speed, intro_steps = _resolve_voice(
-                    voice_resolver, plan.intro.voice_spec, request
-                )
-                intro_backend = pipeline_provider.get(intro_provider, request.language, request.use_gpu)
-                synthesize_text(
-                    text=plan.intro.text,
-                    params=synth,
-                    backend=intro_backend,
-                    voice=intro_voice,
-                    speed=intro_speed or request.speed,
-                    chapter_sink=chapter_sink,
-                    preview_callback=lambda text: events.log(f"  Intro: {text[:80]}"),
-                )
-                intro_emitted = True
-                if request.chapter_intro_delay > 0:
-                    _append_silence(
-                        request.chapter_intro_delay,
-                        chapter_sink=chapter_sink,
-                        audio_sink=audio_sink,
-                        stats=stats,
-                    )
-
-            # Process heading
-            if chapter.title:
-                heading_text = _format_heading(chapter.title, chapter_idx, request)
-                if heading_text:
-                    synthesize_text(
-                        text=heading_text,
-                        params=synth,
-                        backend=chapter_backend,
-                        voice=chapter_voice,
-                        speed=chapter_speed or request.speed,
-                        chapter_sink=chapter_sink,
-                        preview_callback=lambda text: events.log(f"  Title: {text[:80]}"),
-                    )
-                    if request.chapter_intro_delay > 0:
-                        _append_silence(
-                            request.chapter_intro_delay,
-                            chapter_sink=chapter_sink,
-                            audio_sink=audio_sink,
-                            stats=stats,
-                        )
-
-            # Process body segments
-            chapter_chunk_markers: List[Dict[str, Any]] = []
-            for seg_idx, segment in enumerate(chapter.segments):
-                check_cancelled()
-
-                # Resolve segment voice (may differ from chapter voice)
-                if segment.voice_spec != chapter.voice_spec:
-                    seg_provider, seg_voice, seg_speed, seg_steps = _resolve_voice(
-                        voice_resolver, segment.voice_spec, request
-                    )
-                    seg_backend = pipeline_provider.get(seg_provider, request.language, request.use_gpu)
-                else:
-                    seg_provider = chapter_provider
-                    seg_voice = chapter_voice
-                    seg_speed = chapter_speed
-                    seg_backend = chapter_backend
-
-                seg_start_time = stats.current_time
-                local_segments, accumulated_tokens = synthesize_text(
-                    text=segment.text,
-                    params=synth,
-                    backend=seg_backend,
-                    voice=seg_voice,
-                    speed=seg_speed or request.speed,
-                    chapter_sink=chapter_sink,
-                    preview_callback=lambda text: events.log(f"  {text[:80]}"),
-                )
-
-                # Process subtitles
-                if subtitle_writer and audio_sink and accumulated_tokens:
-                    process_and_write_subtitles(
-                        accumulated_tokens,
-                        subtitle_writer,
-                        subtitle_mode=request.subtitle_mode,
-                        max_subtitle_words=request.max_subtitle_words,
-                        lang_code=request.language,
-                        use_spacy_segmentation=use_spacy,
-                        fallback_end_time=stats.current_time,
-                    )
-
-                # Record chunk marker
-                if segment.source in ("chunk", "voice_marker"):
-                    chapter_chunk_markers.append({
-                        "id": segment.chunk_id,
-                        "chapter_index": chapter_idx - 1,
-                        "chunk_index": segment.chunk_index or seg_idx,
-                        "start": seg_start_time,
-                        "end": stats.current_time,
-                        "speaker_id": segment.speaker_id,
-                        "voice": segment.voice_spec,
-                        "level": segment.level or request.chunk_level,
-                        "characters": len(segment.text),
-                    })
-
-            # Silence between chapters
-            if chapter_idx < len(plan.chapters) and request.silence_between_chapters > 0:
-                _append_silence(
-                    request.silence_between_chapters,
-                    chapter_sink=chapter_sink,
-                    audio_sink=audio_sink,
-                    stats=stats,
-                )
-
-            # Close chapter sink
-            if chapter_sink:
-                chapter_sink.close()
-
-            # Add chapter marker
-            result.chapter_markers.append({
-                "chapter_index": chapter_idx - 1,
-                "title": chapter.title,
-                "start": stats.current_time - (stats.current_time - seg_start_time) if chapter.segments else stats.current_time,
-                "end": stats.current_time,
-            })
-
-            result.chunk_markers.extend(chapter_chunk_markers)
-
-        # Process outro
-        if plan.outro and plan.outro.enabled and merge_chapters:
-            events.log(f"Closing outro: {plan.outro.text[:80]}")
-            outro_provider, outro_voice, outro_speed, outro_steps = _resolve_voice(
-                voice_resolver, plan.outro.voice_spec, request
-            )
-            outro_backend = pipeline_provider.get(outro_provider, request.language, request.use_gpu)
-
-            # Silence before outro
-            if request.silence_between_chapters > 0:
-                _append_silence(
-                    request.silence_between_chapters,
-                    chapter_sink=None,
-                    audio_sink=audio_sink,
-                    stats=stats,
-                )
-
-            synthesize_text(
-                text=plan.outro.text,
-                params=synth,
-                backend=outro_backend,
-                voice=outro_voice,
-                speed=outro_speed or request.speed,
-                chapter_sink=None,
-                preview_callback=lambda text: events.log(f"  {text[:80]}"),
-            )
-            events.log("Outro synthesized.")
-
-    # Set result metadata
-    result.total_chapters = len(plan.chapters)
-    result.total_segments = sum(len(ch.segments) for ch in plan.chapters)
-    result.total_characters = total_characters
-
-    if output_layout.project_root:
-        result.project_root = output_layout.project_root
-
-    return result
-
-
-# ─── Helpers ────────────────────────────────────────────────────────
-
-
-def _resolve_voice(
-    resolver: VoiceResolver,
-    voice_spec: str,
-    request: Any,
-) -> Tuple[str, Any, Optional[float], Optional[int]]:
-    """Resolve a voice spec and return (provider, voice, speed, steps)."""
-    try:
-        resolved = resolver.resolve(voice_spec)
-        return (
-            resolved.provider,
-            resolved.voice,
-            resolved.speed,
-            resolved.supertonic_steps,
-        )
-    except Exception:
-        # Fallback to base voice
-        resolved = resolver.resolve(request.voice or "M1")
-        return (
-            resolved.provider,
-            resolved.voice,
-            resolved.speed,
-            resolved.supertonic_steps,
-        )
-
-
-def _base_name(request: Any) -> str:
-    """Get base name for output file."""
-    from abogen.domain.output_paths import sanitize_output_stem
-
-    if request.original_filename:
-        return sanitize_output_stem(request.original_filename)
-    return "output"
-
-
-def _format_heading(title: str, index: int, request: Any) -> str:
-    """Format chapter heading for TTS."""
-    from abogen.domain.chapter_titles import format_spoken_chapter_title
-
-    if request.auto_prefix_chapter_titles:
-        return format_spoken_chapter_title(title, index, apply_prefix=True)
-    return title
-
-
-def _append_silence(
-    duration: float,
-    *,
-    chapter_sink: Optional[AudioSink],
-    audio_sink: Optional[AudioSink],
-    stats: SegmentStats,
-) -> None:
-    """Append silence to sinks."""
-    from abogen.domain.audio_buffer import create_silence
-
-    silence = create_silence(duration)
-    if silence.size == 0:
-        return
-    if chapter_sink:
-        chapter_sink.write(silence)
-    if audio_sink:
-        audio_sink.write(silence)
-        stats.current_time += duration

abogen/application/conversion_models.py

@@ -1,95 +0,0 @@
-"""Core models for conversion planning.
-
-These dataclasses represent the structured plan for a conversion job.
-They are UI-agnostic and describe WHAT to convert, not HOW to do it.
-
-The planning flow:
-    ConversionRequest -> ConversionPlan -> ConversionResult
-
-    ConversionPlan contains:
-    - ChapterPlan[]: chapters with their segments
-    - SegmentPlan[]: individual text segments with voice specs
-    - OutputLayout: where to write outputs
-    - IntroOutroSpec: optional intro/outro
-"""
-
-from __future__ import annotations
-
-from dataclasses import dataclass, field
-from pathlib import Path
-from typing import TYPE_CHECKING, Any, Dict, List, Optional
-
-if TYPE_CHECKING:
-    from abogen.application.conversion_request import ConversionRequest
-
-
-@dataclass
-class SegmentPlan:
-    """A single text segment with its voice specification.
-
-    This is the unified model for:
-    - Regular chapter body text
-    - PyQt voice markers (<<VOICE:F1>>)
-    - WebUI chunks with per-chunk voice/speaker
-    - Intro/outro text
-    - Chapter headings
-    """
-
-    text: str
-    voice_spec: str
-    kind: str = "body"  # intro, heading, body, outro
-    speaker_id: str = "narrator"
-    chunk_id: Optional[str] = None
-    chunk_index: Optional[int] = None
-    level: Optional[str] = None  # chunk level (paragraph, sentence, etc.)
-    source: str = "chapter"  # chapter, voice_marker, chunk
-
-
-@dataclass
-class ChapterPlan:
-    """A chapter with its metadata and segments."""
-
-    index: int
-    title: str
-    original_title: str
-    body_text: str
-    segments: List[SegmentPlan]
-    voice_spec: str  # default voice for this chapter
-
-
-@dataclass
-class OutputLayout:
-    """Resolved output paths for a conversion job."""
-
-    parent_dir: Path
-    merged_path: Optional[Path] = None
-    chapter_dir: Optional[Path] = None
-    project_root: Optional[Path] = None
-    audio_dir: Optional[Path] = None
-    subtitle_dir: Optional[Path] = None
-    metadata_dir: Optional[Path] = None
-
-
-@dataclass
-class IntroOutroSpec:
-    """Intro/outro specification with resolved text and voice."""
-
-    enabled: bool = False
-    text: str = ""
-    voice_spec: str = ""
-    kind: str = "intro"  # intro or outro
-
-
-@dataclass
-class ConversionPlan:
-    """Complete plan for a conversion job.
-
-    This is the output of the planning phase and input to the executor.
-    """
-
-    request: ConversionRequest
-    metadata: Dict[str, Any]
-    chapters: List[ChapterPlan]
-    intro: Optional[IntroOutroSpec] = None
-    outro: Optional[IntroOutroSpec] = None
-    output_layout: Optional[OutputLayout] = None

abogen/application/conversion_planner.py

@@ -1,348 +0,0 @@
-"""Unified conversion planner.
-
-Pure functions that take a ConversionRequest and produce a ConversionPlan.
-No side effects, no I/O — all complexity from both UIs in one place.
-
-This is Stage 2 of the conversion flow unification plan.
-"""
-
-from __future__ import annotations
-
-from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple
-
-from abogen.application.conversion_models import (
-    ChapterPlan,
-    ConversionPlan,
-    IntroOutroSpec,
-    OutputLayout,
-    SegmentPlan,
-)
-from abogen.application.conversion_request import ConversionRequest
-from abogen.application.output_layout_service import resolve_output_layout
-from abogen.domain.chapter_overrides import apply_chapter_overrides
-from abogen.domain.file_type import auto_select_relevant_chapters
-from abogen.domain.intro_outro import resolve_intro, resolve_outro
-from abogen.domain.metadata_extraction import extract_metadata_for_file
-from abogen.domain.metadata_merge import merge_metadata
-from abogen.subtitle_utils import split_text_by_voice_markers
-
-
-def build_conversion_plan(request: ConversionRequest) -> ConversionPlan:
-    """Build a complete conversion plan from a request.
-
-    This is the single entry point that both UIs will call.
-    It handles all the planning logic that was previously duplicated
-    in both PyQt and WebUI conversion runners.
-
-    Args:
-        request: Normalized conversion request
-
-    Returns:
-        ConversionPlan with all chapters, segments, and output layout
-
-    Raises:
-        ValueError: If request is invalid (no source, no chapters, etc.)
-    """
-    # 1. Extract and validate source
-    source_text = _extract_source_text(request)
-    if not source_text or not source_text.strip():
-        raise ValueError("No text content to convert")
-
-    # 2. Extract metadata
-    metadata = _extract_metadata(request)
-
-    # 3. Parse chapters
-    raw_chapters = _parse_chapters(source_text, request)
-
-    # 4. Apply chapter selection/overrides
-    selected_chapters = _apply_selection(raw_chapters, request)
-
-    # 5. Build segments for each chapter
-    chapters = _build_chapters(selected_chapters, request)
-
-    # 6. Build intro/outro
-    intro, outro = _build_intro_outro(metadata, request)
-
-    # 7. Resolve output layout
-    output_layout = resolve_output_layout(request)
-
-    return ConversionPlan(
-        request=request,
-        metadata=metadata,
-        chapters=chapters,
-        intro=intro,
-        outro=outro,
-        output_layout=output_layout,
-    )
-
-
-def _extract_source_text(request: ConversionRequest) -> Optional[str]:
-    """Extract text from request source."""
-    from abogen.subtitle_utils import clean_text
-
-    if request.direct_text:
-        return clean_text(request.direct_text)
-    if request.source_path and request.source_path.exists():
-        encoding = "utf-8"
-        try:
-            with open(request.source_path, "r", encoding=encoding, errors="replace") as f:
-                text = f.read()
-        except Exception:
-            return None
-        return clean_text(text)
-    return None
-
-
-def _extract_metadata(request: ConversionRequest) -> Dict[str, Any]:
-    """Extract metadata from source file."""
-    if request.direct_text:
-        return dict(request.metadata_tags)
-
-    if request.source_path and request.source_path.exists():
-        try:
-            extraction = extract_metadata_for_file(
-                str(request.source_path), is_direct_text=False
-            )
-            metadata = dict(extraction.metadata) if extraction.metadata else {}
-        except Exception:
-            metadata = {}
-        metadata = merge_metadata(metadata, request.metadata_tags)
-        return metadata
-
-    return dict(request.metadata_tags)
-
-
-def _parse_chapters(
-    source_text: str, request: ConversionRequest
-) -> List[Tuple[str, str, str]]:
-    """Parse source text into raw chapters.
-
-    Returns list of (title, body_text, default_voice) tuples.
-    """
-    from abogen.domain.text_chapters import parse_chapters_from_text
-
-    # Text is already cleaned in _extract_source_text, so clean=False here
-    chapters = parse_chapters_from_text(source_text, default_title="text", clean=False)
-
-    # Default voice from request
-    default_voice = request.voice or "M1"
-
-    return [(title, text, default_voice) for title, text in chapters]
-
-
-def _apply_selection(
-    raw_chapters: List[Tuple[str, str, str]], request: ConversionRequest
-) -> List[Tuple[str, str, str]]:
-    """Apply chapter selection and overrides."""
-    from abogen.text_extractor import ExtractedChapter
-
-    # Convert to ExtractedChapter objects for auto_select_relevant_chapters
-    extracted = [
-        ExtractedChapter(title=title, text=text)
-        for title, text, _ in raw_chapters
-    ]
-
-    # If user specified chapters, apply overrides
-    if request.chapter_overrides:
-        selected, _, diagnostics = apply_chapter_overrides(extracted, request.chapter_overrides)
-        if selected:
-            # Map back to (title, text, voice) tuples
-            result = []
-            for ch in selected:
-                # Find matching original chapter to get voice
-                voice = request.voice or "M1"
-                for orig_title, orig_text, orig_voice in raw_chapters:
-                    if orig_title == ch.title:
-                        voice = orig_voice
-                        break
-                result.append((ch.title, ch.text or "", voice))
-            return result
-        # If no chapters selected, fall through to auto-selection
-
-    # Auto-select relevant chapters
-    from abogen.domain.file_type import infer_file_type
-
-    file_type = infer_file_type(request.source_path) if request.source_path else "text"
-    result = auto_select_relevant_chapters(extracted, file_type)
-    filtered = result.kept
-
-    if filtered:
-        # Map back to (title, text, voice) tuples
-        result = []
-        for ch in filtered:
-            voice = request.voice or "M1"
-            for orig_title, orig_text, orig_voice in raw_chapters:
-                if orig_title == ch.title:
-                    voice = orig_voice
-                    break
-            result.append((ch.title, ch.text or "", voice))
-        return result
-
-    # Fall back to all chapters
-    return raw_chapters
-
-
-def _build_chapters(
-    selected_chapters: List[Tuple[str, str, str]], request: ConversionRequest
-) -> List[ChapterPlan]:
-    """Build ChapterPlan with SegmentPlan for each chapter."""
-    chapters = []
-
-    for idx, (title, body_text, default_voice) in enumerate(selected_chapters, 1):
-        # Build segments for this chapter
-        segments = _build_segments(body_text, default_voice, request)
-
-        chapter = ChapterPlan(
-            index=idx,
-            title=title,
-            original_title=title,
-            body_text=body_text,
-            segments=segments,
-            voice_spec=default_voice,
-        )
-        chapters.append(chapter)
-
-    return chapters
-
-
-def _build_segments(
-    body_text: str, default_voice: str, request: ConversionRequest
-) -> List[SegmentPlan]:
-    """Build SegmentPlan list for a chapter's body text.
-
-    Handles voice markers (PyQt) and chunks (WebUI).
-    """
-    segments = []
-
-    # Check for chunks (WebUI style)
-    if request.chunks:
-        # Group chunks by chapter (simplified — assume chunks are for current chapter)
-        for chunk_idx, chunk in enumerate(request.chunks):
-            chunk_text = chunk.get("normalized_text") or chunk.get("text", "")
-            if not chunk_text or not chunk_text.strip():
-                continue
-
-            chunk_voice = _resolve_chunk_voice(chunk, default_voice, request)
-            speaker_id = chunk.get("speaker_id", "narrator")
-
-            segments.append(
-                SegmentPlan(
-                    text=chunk_text.strip(),
-                    voice_spec=chunk_voice,
-                    kind="body",
-                    speaker_id=speaker_id,
-                    chunk_id=chunk.get("id"),
-                    chunk_index=chunk.get("chunk_index", chunk_idx),
-                    level=chunk.get("level", request.chunk_level),
-                    source="chunk",
-                )
-            )
-        return segments
-
-    # Check for voice markers (PyQt style)
-    # Detect markers even if validation fails (voice names may not be loaded yet)
-    from abogen.subtitle_utils import _VOICE_MARKER_SEARCH_PATTERN
-
-    has_voice_markers = bool(_VOICE_MARKER_SEARCH_PATTERN.search(body_text))
-    voice_segments, last_voice, valid_count, invalid_count = split_text_by_voice_markers(
-        body_text, default_voice
-    )
-
-    if has_voice_markers or (len(voice_segments) > 1):
-        # Voice markers were used
-        for voice_name, segment_text in voice_segments:
-            if not segment_text or not segment_text.strip():
-                continue
-            segments.append(
-                SegmentPlan(
-                    text=segment_text.strip(),
-                    voice_spec=voice_name,
-                    kind="body",
-                    source="voice_marker",
-                )
-            )
-        return segments
-
-    # No voice markers — single segment for entire body
-    if body_text and body_text.strip():
-        segments.append(
-            SegmentPlan(
-                text=body_text.strip(),
-                voice_spec=default_voice,
-                kind="body",
-                source="chapter",
-            )
-        )
-
-    return segments
-
-
-def _resolve_chunk_voice(
-    chunk: Dict[str, Any], default_voice: str, request: ConversionRequest
-) -> str:
-    """Resolve voice for a chunk."""
-    # Check for speaker-based voice
-    speaker_id = chunk.get("speaker_id", "narrator")
-    if speaker_id and speaker_id != "narrator" and request.speakers:
-        speaker_config = request.speakers.get(speaker_id, {})
-        if isinstance(speaker_config, dict):
-            voice = speaker_config.get("voice")
-            if voice:
-                return voice
-
-    # Check for direct voice field
-    voice = chunk.get("voice")
-    if voice:
-        return voice
-
-    return default_voice
-
-
-def _build_intro_outro(
-    metadata: Dict[str, Any], request: ConversionRequest
-) -> Tuple[Optional[IntroOutroSpec], Optional[IntroOutroSpec]]:
-    """Build intro and outro specs."""
-    intro_spec = None
-    outro_spec = None
-
-    # Intro
-    if request.read_title_intro:
-        resolved = resolve_intro(
-            metadata,
-            request.original_filename,
-            True,
-            request.voice or "M1",
-            request.voice or "M1",
-            [],
-        )
-        if resolved.enabled:
-            intro_spec = IntroOutroSpec(
-                enabled=True,
-                text=resolved.text,
-                voice_spec=resolved.voice_spec,
-                kind="intro",
-            )
-
-    # Outro
-    if request.read_closing_outro:
-        resolved = resolve_outro(
-            metadata,
-            request.original_filename,
-            True,
-            request.voice or "M1",
-            request.voice or "M1",
-            [],
-        )
-        if resolved.enabled:
-            outro_spec = IntroOutroSpec(
-                enabled=True,
-                text=resolved.text,
-                voice_spec=resolved.voice_spec,
-                kind="outro",
-            )
-
-    return intro_spec, outro_spec
-
-
-# Output layout resolution is now in application/output_layout_service.py

abogen/application/conversion_ports.py

@@ -1,112 +0,0 @@
-"""Ports / interfaces for the conversion service.
-
-These protocols define how the conversion service communicates with
-the outside world (UI, TTS backends, voice resolvers).
-
-The service ONLY depends on these interfaces, never on concrete
-implementations (PyQt signals, Flask Job, etc.).
-"""
-
-from __future__ import annotations
-
-from dataclasses import dataclass
-from typing import Any, List, Optional, Protocol, runtime_checkable
-
-
-class ConversionCancelled(Exception):
-    """Raised when conversion is cancelled by user."""
-    pass
-
-
-class ConversionEvents(Protocol):
-    """UI-specific actions the conversion service delegates back to the caller.
-
-    Implementations:
-    - PyQt: emits signals (log_updated, progress_updated, etc.)
-    - WebUI: updates Job attributes (job.add_log, job.progress, etc.)
-    """
-
-    def log(self, message: str, level: str = "info") -> None:
-        """Log a message to the UI."""
-        ...
-
-    def progress(self, processed: int, total: int, etr: str) -> None:
-        """Update progress display."""
-        ...
-
-    def check_cancelled(self) -> None:
-        """Check if conversion was cancelled.
-
-        Should raise ConversionCancelled (or UI-specific exception)
-        if cancellation is requested. Normal return means "continue".
-        """
-        ...
-
-
-class PipelineProvider(Protocol):
-    """Provides access to TTS backends (Kokoro, SuperTonic, etc.).
-
-    Implementations:
-    - PyQt: wraps self.backend (single pipeline)
-    - WebUI: wraps PipelinePool (multi-provider)
-    """
-
-    def get(self, provider: str, language: str, use_gpu: bool) -> Any:
-        """Get a TTS backend instance."""
-        ...
-
-    def dispose_all(self) -> None:
-        """Dispose all backend resources."""
-        ...
-
-
-@dataclass
-class ResolvedVoice:
-    """A resolved voice ready for TTS synthesis."""
-
-    provider: str
-    resolved_spec: str
-    voice: Any  # loaded voice tensor or name
-    speed: float
-    supertonic_steps: int
-
-
-class VoiceResolver(Protocol):
-    """Resolves voice specs into loaded voice objects.
-
-    Implementations:
-    - PyQt: wraps load_voice_cached + VoiceCache
-    - WebUI: wraps resolve_voice_choice + PipelinePool + VoiceCache
-    """
-
-    def resolve(self, voice_spec: str) -> ResolvedVoice:
-        """Resolve a voice spec into a loaded voice."""
-        ...
-
-
-class SubtitleWriter(Protocol):
-    """Writes subtitle entries to a file."""
-
-    def open(self) -> None:
-        """Open the subtitle file for writing."""
-        ...
-
-    def write_entry(self, start: float, end: float, text: str) -> None:
-        """Write a single subtitle entry."""
-        ...
-
-    def close(self) -> None:
-        """Close the subtitle file."""
-        ...
-
-
-class AudioSink(Protocol):
-    """Writes audio data to a file."""
-
-    def write(self, audio: Any) -> None:
-        """Write audio samples to the sink."""
-        ...
-
-    def close(self) -> None:
-        """Close the audio file."""
-        ...

abogen/application/conversion_request.py

@@ -1,156 +0,0 @@
-"""ConversionRequest — normalized input for a conversion job.
-
-This is NOT a WebUI Job and NOT a PyQt ConversionThread state.
-It describes the TASK, not the UI.
-
-UI adapters are responsible for converting their respective state
-into a ConversionRequest before calling ConversionService.run().
-"""
-
-from __future__ import annotations
-
-import dataclasses
-from dataclasses import dataclass, field
-from pathlib import Path
-from typing import Any, Dict, List, Optional
-
-from abogen.domain.enums import Language, OutputFormat, SaveMode, SubtitleFormat, SubtitleMode
-
-
-class ConversionRequestError(ValueError):
-    """Raised when ConversionRequest has invalid field values."""
-
-
-# Numeric field constraints: attr -> (min, max)
-_NUMERIC_CONSTRAINTS: dict[str, tuple[float, float | None]] = {
-    "max_subtitle_words": (1, 500),
-    "speed": (0.5, 3.0),
-    "supertonic_total_steps": (2, 15),
-    "silence_between_chapters": (0.0, None),
-    "chapter_intro_delay": (0.0, None),
-}
-
-# Enum-like fields that must be in allowed set
-_ENUM_CONSTRAINTS: dict[str, tuple[str, ...]] = {
-    "chunk_level": ("paragraph", "sentence"),
-    "speaker_mode": ("single", "multi"),
-}
-
-
-@dataclass
-class ConversionRequest:
-    """Normalized request for a conversion job.
-
-    Only contains fields that describe the conversion task itself.
-    UI-only fields (display, logging, user prompts) stay in adapters.
-
-    Validation runs on creation via __post_init__:
-    - None values → replaced with field default (from declaration)
-    - Numeric fields → clamped to valid range
-    - String enums → validated against allowed set
-    """
-
-    # --- Source ---
-    source_path: Optional[Path] = None
-    direct_text: Optional[str] = None
-    original_filename: str = ""
-
-    # --- TTS Settings ---
-    language: Language = Language.EN_US
-    tts_provider: str = "kokoro"
-    voice: str = "M1"
-    voice_profile: Optional[str] = None
-    speed: float = 1.0
-    use_gpu: bool = True
-    supertonic_total_steps: int = 5
-
-    # --- Output Format ---
-    output_format: OutputFormat = OutputFormat.WAV
-    subtitle_mode: SubtitleMode = SubtitleMode.DISABLED
-    subtitle_format: SubtitleFormat = SubtitleFormat.SRT
-    max_subtitle_words: int = 50
-
-    # --- Save Options ---
-    save_mode: SaveMode = SaveMode.SAVE_NEXT_TO_INPUT
-    output_folder: Optional[Path] = None
-    save_chapters_separately: bool = False
-    merge_chapters_at_end: bool = True
-    separate_chapters_format: OutputFormat = OutputFormat.WAV
-    save_as_project: bool = False
-
-    # --- Timing ---
-    silence_between_chapters: float = 2.0
-    chapter_intro_delay: float = 0.0
-
-    # --- Content Processing ---
-    replace_single_newlines: bool = False
-    read_title_intro: bool = False
-    read_closing_outro: bool = True
-    auto_prefix_chapter_titles: bool = True
-    normalize_chapter_opening_caps: bool = False
-
-    # --- Pronunciation / Normalization ---
-    pronunciation_overrides: List[Dict[str, Any]] = field(default_factory=list)
-    manual_overrides: List[Dict[str, Any]] = field(default_factory=list)
-    heteronym_overrides: List[Dict[str, Any]] = field(default_factory=list)
-    normalization_overrides: Optional[Dict[str, Any]] = None
-
-    # --- Chapter/Chunk Configuration ---
-    chapter_overrides: List[Dict[str, Any]] = field(default_factory=list)
-    chunks: List[Dict[str, Any]] = field(default_factory=list)
-    chunk_level: str = "paragraph"
-    speaker_mode: str = "single"
-    speakers: Dict[str, Any] = field(default_factory=dict)
-
-    # --- Metadata ---
-    metadata_tags: Dict[str, Any] = field(default_factory=dict)
-
-    # --- Artifacts ---
-    cover_image_path: Optional[Path] = None
-    cover_image_mime: Optional[str] = None
-    generate_epub3: bool = False
-
-    def __post_init__(self) -> None:
-        """Resolve None → default, then validate and clamp."""
-        _apply_none_defaults(self)
-        if not self.tts_provider:
-            self.tts_provider = "kokoro"
-        _clamp_numerics(self)
-        _validate_enums(self)
-
-
-def _apply_none_defaults(obj: ConversionRequest) -> None:
-    """Replace None values with field defaults from dataclass declaration."""
-    for f in dataclasses.fields(obj):
-        if getattr(obj, f.name) is not None:
-            continue
-        if f.default is not dataclasses.MISSING:
-            setattr(obj, f.name, f.default)
-        elif f.default_factory is not dataclasses.MISSING:
-            setattr(obj, f.name, f.default_factory())
-
-
-def _clamp_numerics(obj: ConversionRequest) -> None:
-    """Clamp numeric fields to valid ranges."""
-    for attr, (min_v, max_v) in _NUMERIC_CONSTRAINTS.items():
-        val = getattr(obj, attr)
-        if val is None:
-            continue
-        if not isinstance(val, (int, float)):
-            raise ConversionRequestError(
-                f"{attr} must be a number, got {type(val).__name__}"
-            )
-        clamped = max(min_v, float(val))
-        if max_v is not None:
-            clamped = min(max_v, clamped)
-        setattr(obj, attr, clamped)
-
-
-def _validate_enums(obj: ConversionRequest) -> None:
-    """Validate string enum fields against allowed values."""
-    for attr, allowed in _ENUM_CONSTRAINTS.items():
-        val = getattr(obj, attr)
-        if val not in allowed:
-            raise ConversionRequestError(
-                f"{attr} must be one of {allowed}, got {val!r}"
-            )

abogen/application/conversion_result.py

@@ -1,47 +0,0 @@
-"""ConversionResult — output of a successful conversion.
-
-Returned by ConversionService.run() after all synthesis and finalization.
-UI adapters consume this to update their respective state (Job, signals, etc.).
-"""
-
-from __future__ import annotations
-
-from dataclasses import dataclass, field
-from pathlib import Path
-from typing import Any, Dict, List, Optional
-
-
-@dataclass
-class ConversionResult:
-    """Output of a successful conversion job."""
-
-    # --- Primary outputs ---
-    audio_path: Optional[Path] = None
-    subtitle_paths: List[Path] = field(default_factory=list)
-    chapter_paths: List[Path] = field(default_factory=list)
-
-    # --- Markers (for metadata/audiobookshelf) ---
-    chapter_markers: List[Dict[str, Any]] = field(default_factory=list)
-    chunk_markers: List[Dict[str, Any]] = field(default_factory=list)
-
-    # --- Metadata ---
-    metadata: Dict[str, Any] = field(default_factory=dict)
-
-    # --- Artifacts ---
-    artifacts: Dict[str, Path] = field(default_factory=dict)
-    project_root: Optional[Path] = None
-    epub_path: Optional[Path] = None
-
-    # --- Stats ---
-    total_chapters: int = 0
-    total_segments: int = 0
-    total_characters: int = 0
-
-
-@dataclass
-class ConversionError:
-    """Error information when conversion fails."""
-
-    message: str
-    details: Optional[str] = None
-    is_cancelled: bool = False

abogen/application/conversion_service.py

@@ -1,172 +0,0 @@
-"""ConversionService — main orchestrator for the conversion flow.
-
-Ties together planner, executor, and finalizers into a single entry point.
-Both UIs (PyQt, WebUI) call ConversionService.run() to execute a conversion.
-
-Responsibilities:
-- Prepare TTSContext (normalization settings, pronunciation rules)
-- Build ConversionPlan via planner
-- Execute conversion via executor
-- Handle lifecycle (cleanup, error handling)
-- Return ConversionResult
-
-The service NEVER imports from PyQt or WebUI.
-"""
-
-from __future__ import annotations
-
-from typing import Any, Callable, Dict, Optional
-
-from abogen.application.conversion_executor import execute_conversion
-from abogen.application.conversion_models import ConversionPlan
-from abogen.application.conversion_planner import build_conversion_plan
-from abogen.application.conversion_ports import (
-    ConversionEvents,
-    PipelineProvider,
-    VoiceResolver,
-)
-from abogen.application.conversion_request import ConversionRequest
-from abogen.application.conversion_result import ConversionResult
-from abogen.domain.enums import SubtitleMode
-from abogen.domain.normalization import TTSContext
-from abogen.domain.split_pattern import get_split_pattern
-
-
-def run_conversion(
-    request: ConversionRequest,
-    events: ConversionEvents,
-    pipeline_provider: PipelineProvider,
-    voice_resolver: VoiceResolver,
-) -> ConversionResult:
-    """Execute a conversion request and return the result.
-
-    This is the single entry point for both UIs. It orchestrates:
-    1. TTS context preparation
-    2. Conversion planning
-    3. Conversion execution
-    4. Resource cleanup
-
-    Args:
-        request: Normalized conversion request
-        events: UI-specific callbacks (log, progress, check_cancelled)
-        pipeline_provider: Provides TTS backends
-        voice_resolver: Resolves voice specs into loaded voices
-
-    Returns:
-        ConversionResult with paths and markers
-
-    Raises:
-        ConversionCancelled: If conversion was cancelled
-        ValueError: If request is invalid
-        Exception: On TTS or I/O errors
-    """
-    try:
-        # Stage 1: Prepare TTS context
-        events.log("Preparing conversion pipeline")
-        tts_context = _prepare_tts_context(request, events)
-
-        # Stage 2: Build conversion plan
-        events.log("Building conversion plan")
-        plan = build_conversion_plan(request)
-
-        # Stage 3: Execute conversion
-        events.log("Starting conversion")
-        result = execute_conversion(
-            plan=plan,
-            events=events,
-            pipeline_provider=pipeline_provider,
-            voice_resolver=voice_resolver,
-            tts_context=tts_context,
-        )
-
-        # Stage 4: Finalize
-        events.log("Conversion complete")
-        return result
-
-    except Exception as e:
-        events.log(f"Conversion failed: {e}", level="error")
-        raise
-
-
-def _prepare_tts_context(
-    request: ConversionRequest,
-    events: ConversionEvents,
-) -> TTSContext:
-    """Prepare TTSContext with normalization settings.
-
-    This compiles pronunciation/heteronym rules and creates the
-    normalization context used during conversion.
-
-    Args:
-        request: Conversion request with override settings
-        events: For logging warnings about missing features
-
-    Returns:
-        TTSContext ready for text normalization
-    """
-    from abogen.domain.normalization import (
-        build_apostrophe_config,
-        get_runtime_settings,
-    )
-    from abogen.domain.pronunciation import (
-        compile_heteronym_sentence_rules,
-        compile_pronunciation_rules,
-        merge_pronunciation_overrides,
-    )
-
-    # Get runtime normalization settings
-    normalization_settings = get_runtime_settings()
-
-    # Build apostrophe config
-    apostrophe_config = build_apostrophe_config(
-        settings=normalization_settings,
-    )
-
-    # Check for num2words availability
-    if apostrophe_config.convert_numbers:
-        try:
-            import num2words  # noqa: F401
-        except ImportError:
-            events.log(
-                "Number normalization is enabled but 'num2words' library is not available. "
-                "Numbers will NOT be converted to words.",
-                level="warning",
-            )
-
-    # Compute split pattern
-    split_pattern = get_split_pattern(
-        request.language or Language.EN_US,
-        request.subtitle_mode or SubtitleMode.DISABLED,
-    )
-
-    # Merge pronunciation overrides (manual + pronunciation)
-    # Create a mock job-like object for merge_pronunciation_overrides
-    class _MockJob:
-        def __init__(self, req):
-            self.pronunciation_overrides = req.pronunciation_overrides
-            self.manual_overrides = req.manual_overrides
-            self.heteronym_overrides = req.heteronym_overrides
-
-    merged_overrides = merge_pronunciation_overrides(_MockJob(request))
-
-    # Compile rules
-    pronunciation_rules = compile_pronunciation_rules(merged_overrides)
-    heteronym_rules = compile_heteronym_sentence_rules(request.heteronym_overrides)
-
-    if heteronym_rules:
-        events.log(
-            f"Applying {len(heteronym_rules)} heteronym override(s) during conversion.",
-            level="debug",
-        )
-    if pronunciation_rules:
-        events.log(
-            f"Applying {len(pronunciation_rules)} pronunciation override(s) during conversion.",
-            level="debug",
-        )
-
-    return TTSContext(
-        split_pattern=split_pattern,
-        pronunciation_rules=pronunciation_rules,
-        heteronym_rules=heteronym_rules,
-        normalization_overrides=request.normalization_overrides,
-    )

abogen/application/output_layout_service.py

@@ -1,150 +0,0 @@
-"""Output layout resolution service.
-
-Determines where conversion outputs (audio, subtitles, metadata) should be written.
-Extracted from conversion_planner.py as a standalone service per plan Stage 5.
-
-Responsibilities:
-- Resolve base output directory from save_mode and source_path
-- Determine base filename from original_filename
-- Find unique output path to avoid overwrites
-- Resolve project layout (audio_dir, subtitle_dir, metadata_dir)
-- Force merged output for m4b format
-- Return OutputLayout dataclass
-"""
-
-from __future__ import annotations
-
-from pathlib import Path
-from typing import Optional
-
-from abogen.application.conversion_models import OutputLayout
-from abogen.application.conversion_request import ConversionRequest
-from abogen.domain.enums import OutputFormat, SaveMode, SubtitleFormat
-from abogen.domain.output_paths import (
-    resolve_project_layout,
-    resolve_unique_path,
-    sanitize_output_stem,
-)
-
-
-def resolve_output_layout(request: ConversionRequest) -> OutputLayout:
-    """Resolve output paths for a conversion request.
-
-    This is the single entry point for output path resolution,
-    used by both UIs and the conversion service.
-
-    Args:
-        request: Normalized conversion request
-
-    Returns:
-        OutputLayout with resolved paths
-    """
-    # Determine base output directory
-    if request.save_mode == SaveMode.CUSTOM_FOLDER and request.output_folder:
-        parent_dir = Path(request.output_folder)
-    elif request.source_path:
-        parent_dir = request.source_path.parent
-    else:
-        parent_dir = Path.cwd()
-
-    # Determine base name
-    if request.original_filename:
-        base_name = sanitize_output_stem(request.original_filename)
-    elif request.source_path:
-        base_name = sanitize_output_stem(request.source_path.stem)
-    else:
-        base_name = "output"
-
-    # Find unique output path
-    allowed_exts = {request.output_format, SubtitleFormat.SRT, SubtitleFormat.ASS, "vtt", "mp4", OutputFormat.M4B}
-    unique_base = resolve_unique_path(
-        parent_dir, base_name, "", allowed_extensions=allowed_exts
-    )
-
-    # Resolve project layout
-    project_root = None
-    audio_dir = parent_dir
-    subtitle_dir = None
-    metadata_dir = None
-
-    if request.save_as_project:
-        project_root, audio_dir, subtitle_dir, metadata_dir = resolve_project_layout(
-            original_filename=request.original_filename,
-            save_as_project=True,
-            base_dir=parent_dir,
-        )
-
-    return OutputLayout(
-        parent_dir=parent_dir,
-        project_root=project_root,
-        audio_dir=audio_dir,
-        subtitle_dir=subtitle_dir,
-        metadata_dir=metadata_dir,
-    )
-
-
-def resolve_merged_path(
-    layout: OutputLayout,
-    request: ConversionRequest,
-) -> Path:
-    """Resolve the merged output audio file path.
-
-    Args:
-        layout: Resolved output layout
-        request: Conversion request
-
-    Returns:
-        Path to the merged output file
-    """
-    base_name = sanitize_output_stem(
-        request.original_filename or "output"
-    )
-    return layout.audio_dir / f"{base_name}.{request.output_format}"
-
-
-def resolve_chapter_path(
-    layout: OutputLayout,
-    request: ConversionRequest,
-    chapter_title: str,
-    chapter_index: int,
-) -> Path:
-    """Resolve the output path for a separate chapter file.
-
-    Args:
-        layout: Resolved output layout
-        request: Conversion request
-        chapter_title: Chapter title for filename
-        chapter_index: Chapter number (1-based)
-
-    Returns:
-        Path to the chapter output file
-    """
-    import re
-
-    slug = re.sub(r'[^\w\s-]', '', chapter_title.lower())
-    slug = re.sub(r'[\s_]+', '_', slug).strip('_')
-    if not slug:
-        slug = f"chapter_{chapter_index}"
-    filename = f"{chapter_index:02d}_{slug}.{request.separate_chapters_format}"
-    return layout.audio_dir / "chapters" / filename
-
-
-def should_merge_output(request: ConversionRequest) -> bool:
-    """Determine if merged output is required.
-
-    Rules:
-    - m4b format always forces merged output
-    - If save_chapters_separately is False, merged is required
-    - Otherwise, use merge_chapters_at_end setting
-
-    Args:
-        request: Conversion request
-
-    Returns:
-        True if merged output should be created
-    """
-    if request.output_format == OutputFormat.M4B:
-        return True
-    if not request.save_chapters_separately:
-        return True
-    return request.merge_chapters_at_end

abogen/assets/settings.svg

@@ -1,31 +1,31 @@
-<?xml version="1.0" encoding="utf-8"?>
-
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<!-- Uploaded to: SVG Repo, www.svgrepo.com, Generator: SVG Repo Mixer Tools -->
-<svg height="800px" width="800px" version="1.1" id="_x32_" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" 
-	 viewBox="0 0 512 512"  xml:space="preserve">
-<style type="text/css">
-	.st0{fill:#808080;}
-</style>
-<g>
-	<path class="st0" d="M502.325,307.303l-39.006-30.805c-6.215-4.908-9.665-12.429-9.668-20.348c0-0.084,0-0.168,0-0.252
-		c-0.014-7.936,3.44-15.478,9.667-20.396l39.007-30.806c8.933-7.055,12.093-19.185,7.737-29.701l-17.134-41.366
-		c-4.356-10.516-15.167-16.86-26.472-15.532l-49.366,5.8c-7.881,0.926-15.656-1.966-21.258-7.586
-		c-0.059-0.06-0.118-0.119-0.177-0.178c-5.597-5.602-8.476-13.36-7.552-21.225l5.799-49.363
-		c1.328-11.305-5.015-22.116-15.531-26.472L337.004,1.939c-10.516-4.356-22.646-1.196-29.701,7.736l-30.805,39.005
-		c-4.908,6.215-12.43,9.665-20.349,9.668c-0.084,0-0.168,0-0.252,0c-7.935,0.014-15.477-3.44-20.395-9.667L204.697,9.675
-		c-7.055-8.933-19.185-12.092-29.702-7.736L133.63,19.072c-10.516,4.356-16.86,15.167-15.532,26.473l5.799,49.366
-		c0.926,7.881-1.964,15.656-7.585,21.257c-0.059,0.059-0.118,0.118-0.178,0.178c-5.602,5.598-13.36,8.477-21.226,7.552
-		l-49.363-5.799c-11.305-1.328-22.116,5.015-26.472,15.531L1.939,174.996c-4.356,10.516-1.196,22.646,7.736,29.701l39.006,30.805
-		c6.215,4.908,9.665,12.429,9.668,20.348c0,0.084,0,0.167,0,0.251c0.014,7.935-3.44,15.477-9.667,20.395L9.675,307.303
-		c-8.933,7.055-12.092,19.185-7.736,29.701l17.134,41.365c4.356,10.516,15.168,16.86,26.472,15.532l49.366-5.799
-		c7.882-0.926,15.656,1.965,21.258,7.586c0.059,0.059,0.118,0.119,0.178,0.178c5.597,5.603,8.476,13.36,7.552,21.226l-5.799,49.364
-		c-1.328,11.305,5.015,22.116,15.532,26.472l41.366,17.134c10.516,4.356,22.646,1.196,29.701-7.736l30.804-39.005
-		c4.908-6.215,12.43-9.665,20.348-9.669c0.084,0,0.168,0,0.251,0c7.936-0.014,15.478,3.44,20.396,9.667l30.806,39.007
-		c7.055,8.933,19.185,12.093,29.701,7.736l41.366-17.134c10.516-4.356,16.86-15.168,15.532-26.472l-5.8-49.366
-		c-0.926-7.881,1.965-15.656,7.586-21.257c0.059-0.059,0.119-0.119,0.178-0.178c5.602-5.597,13.36-8.476,21.225-7.552l49.364,5.799
-		c11.305,1.328,22.117-5.015,26.472-15.531l17.134-41.365C514.418,326.488,511.258,314.358,502.325,307.303z M281.292,329.698
-		c-39.68,16.436-85.172-2.407-101.607-42.087c-16.436-39.68,2.407-85.171,42.087-101.608c39.68-16.436,85.172,2.407,101.608,42.088
-		C339.815,267.771,320.972,313.262,281.292,329.698z"/>
-</g>
+<?xml version="1.0" encoding="utf-8"?>
+
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<!-- Uploaded to: SVG Repo, www.svgrepo.com, Generator: SVG Repo Mixer Tools -->
+<svg height="800px" width="800px" version="1.1" id="_x32_" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" 
+	 viewBox="0 0 512 512"  xml:space="preserve">
+<style type="text/css">
+	.st0{fill:#808080;}
+</style>
+<g>
+	<path class="st0" d="M502.325,307.303l-39.006-30.805c-6.215-4.908-9.665-12.429-9.668-20.348c0-0.084,0-0.168,0-0.252
+		c-0.014-7.936,3.44-15.478,9.667-20.396l39.007-30.806c8.933-7.055,12.093-19.185,7.737-29.701l-17.134-41.366
+		c-4.356-10.516-15.167-16.86-26.472-15.532l-49.366,5.8c-7.881,0.926-15.656-1.966-21.258-7.586
+		c-0.059-0.06-0.118-0.119-0.177-0.178c-5.597-5.602-8.476-13.36-7.552-21.225l5.799-49.363
+		c1.328-11.305-5.015-22.116-15.531-26.472L337.004,1.939c-10.516-4.356-22.646-1.196-29.701,7.736l-30.805,39.005
+		c-4.908,6.215-12.43,9.665-20.349,9.668c-0.084,0-0.168,0-0.252,0c-7.935,0.014-15.477-3.44-20.395-9.667L204.697,9.675
+		c-7.055-8.933-19.185-12.092-29.702-7.736L133.63,19.072c-10.516,4.356-16.86,15.167-15.532,26.473l5.799,49.366
+		c0.926,7.881-1.964,15.656-7.585,21.257c-0.059,0.059-0.118,0.118-0.178,0.178c-5.602,5.598-13.36,8.477-21.226,7.552
+		l-49.363-5.799c-11.305-1.328-22.116,5.015-26.472,15.531L1.939,174.996c-4.356,10.516-1.196,22.646,7.736,29.701l39.006,30.805
+		c6.215,4.908,9.665,12.429,9.668,20.348c0,0.084,0,0.167,0,0.251c0.014,7.935-3.44,15.477-9.667,20.395L9.675,307.303
+		c-8.933,7.055-12.092,19.185-7.736,29.701l17.134,41.365c4.356,10.516,15.168,16.86,26.472,15.532l49.366-5.799
+		c7.882-0.926,15.656,1.965,21.258,7.586c0.059,0.059,0.118,0.119,0.178,0.178c5.597,5.603,8.476,13.36,7.552,21.226l-5.799,49.364
+		c-1.328,11.305,5.015,22.116,15.532,26.472l41.366,17.134c10.516,4.356,22.646,1.196,29.701-7.736l30.804-39.005
+		c4.908-6.215,12.43-9.665,20.348-9.669c0.084,0,0.168,0,0.251,0c7.936-0.014,15.478,3.44,20.396,9.667l30.806,39.007
+		c7.055,8.933,19.185,12.093,29.701,7.736l41.366-17.134c10.516-4.356,16.86-15.168,15.532-26.472l-5.8-49.366
+		c-0.926-7.881,1.965-15.656,7.586-21.257c0.059-0.059,0.119-0.119,0.178-0.178c5.602-5.597,13.36-8.476,21.225-7.552l49.364,5.799
+		c11.305,1.328,22.117-5.015,26.472-15.531l17.134-41.365C514.418,326.488,511.258,314.358,502.325,307.303z M281.292,329.698
+		c-39.68,16.436-85.172-2.407-101.607-42.087c-16.436-39.68,2.407-85.171,42.087-101.608c39.68-16.436,85.172,2.407,101.608,42.088
+		C339.815,267.771,320.972,313.262,281.292,329.698z"/>
+</g>
 </svg>

abogen/constants.py

@@ -63,6 +63,64 @@ SUPPORTED_INPUT_FORMATS = [
 # 384 if self.lang_code in 'ab':
 SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION = list(LANGUAGE_DESCRIPTIONS.keys())
 
+# Voice and sample text constants
+VOICES_INTERNAL = [
+    "af_alloy",
+    "af_aoede",
+    "af_bella",
+    "af_heart",
+    "af_jessica",
+    "af_kore",
+    "af_nicole",
+    "af_nova",
+    "af_river",
+    "af_sarah",
+    "af_sky",
+    "am_adam",
+    "am_echo",
+    "am_eric",
+    "am_fenrir",
+    "am_liam",
+    "am_michael",
+    "am_onyx",
+    "am_puck",
+    "am_santa",
+    "bf_alice",
+    "bf_emma",
+    "bf_isabella",
+    "bf_lily",
+    "bm_daniel",
+    "bm_fable",
+    "bm_george",
+    "bm_lewis",
+    "ef_dora",
+    "em_alex",
+    "em_santa",
+    "ff_siwis",
+    "hf_alpha",
+    "hf_beta",
+    "hm_omega",
+    "hm_psi",
+    "if_sara",
+    "im_nicola",
+    "jf_alpha",
+    "jf_gongitsune",
+    "jf_nezumi",
+    "jf_tebukuro",
+    "jm_kumo",
+    "pf_dora",
+    "pm_alex",
+    "pm_santa",
+    "zf_xiaobei",
+    "zf_xiaoni",
+    "zf_xiaoxiao",
+    "zf_xiaoyi",
+    "zm_yunjian",
+    "zm_yunxi",
+    "zm_yunxia",
+    "zm_yunyang",
+]
+
 # Voice and sample text mapping
 SAMPLE_VOICE_TEXTS = {
     "a": "This is a sample of the selected voice.",

abogen/domain/audio_buffer.py

@@ -1,239 +0,0 @@
-"""Audio buffer operations for audiobook generation.
-
-This module provides core audio buffer manipulation functions including:
-- Silence generation
-- Audio mixing
-- Audio normalization
-- Audio buffer resizing
-"""
-
-from __future__ import annotations
-
-from typing import Optional
-
-import numpy as np
-
-# Standard sample rate used throughout the application
-SAMPLE_RATE = 24000
-
-
-def create_silence(duration_seconds: float) -> np.ndarray:
-    """Create a silence audio buffer.
-    
-    Args:
-        duration_seconds: Duration of silence in seconds.
-        
-    Returns:
-        Numpy array of float32 zeros with length = duration_seconds * SAMPLE_RATE.
-        Returns empty array if duration is <= 0.
-    """
-    if duration_seconds <= 0:
-        return np.array([], dtype="float32")
-    
-    samples = int(round(duration_seconds * SAMPLE_RATE))
-    if samples <= 0:
-        return np.array([], dtype="float32")
-    
-    return np.zeros(samples, dtype="float32")
-
-
-def mix_audio(
-    target: np.ndarray,
-    source: np.ndarray,
-    start_sample: int,
-    end_sample: Optional[int] = None,
-) -> np.ndarray:
-    """Mix source audio into target buffer at specified position.
-    
-    This performs additive mixing (target += source). The target buffer
-    is extended if necessary to accommodate the source audio.
-    
-    Args:
-        target: The target audio buffer to mix into.
-        source: The source audio buffer to mix.
-        start_sample: Starting sample index in target buffer.
-        end_sample: Optional end sample index. If None, calculated from source length.
-        
-    Returns:
-        The target buffer (possibly extended). If target was extended, returns new array.
-    """
-    if source.size == 0:
-        return target
-    
-    if end_sample is None:
-        end_sample = start_sample + len(source)
-    
-    # Extend target buffer if needed
-    if end_sample > len(target):
-        new_length = end_sample
-        new_target = np.concatenate([
-            target,
-            np.zeros(new_length - len(target), dtype="float32")
-        ])
-        target = new_target
-    
-    # Perform the mix (additive)
-    target[start_sample:end_sample] += source
-    return target
-
-
-def normalize_audio(
-    audio: np.ndarray,
-    target_peak: float = 1.0,
-) -> np.ndarray:
-    """Normalize audio buffer to prevent clipping.
-    
-    If the audio exceeds the target peak (default 1.0), it is scaled down
-    proportionally to prevent distortion.
-    
-    Args:
-        audio: Input audio buffer.
-        target_peak: Target maximum amplitude (default 1.0).
-        
-    Returns:
-        Normalized audio buffer (new array, original is not modified).
-    """
-    if audio.size == 0:
-        return audio.copy()
-    
-    max_amplitude = float(np.abs(audio).max())
-    
-    if max_amplitude <= target_peak:
-        return audio.copy()
-    
-    # Scale down to prevent clipping
-    scale_factor = target_peak / max_amplitude
-    return (audio * scale_factor).astype("float32")
-
-
-def ensure_buffer_size(
-    buffer: np.ndarray,
-    min_samples: int,
-) -> np.ndarray:
-    """Ensure audio buffer is at least min_samples long.
-    
-    If buffer is shorter, it is extended with zeros.
-    
-    Args:
-        buffer: Input audio buffer.
-        min_samples: Minimum required length in samples.
-        
-    Returns:
-        Buffer of at least min_samples length (new array if extended).
-    """
-    if len(buffer) >= min_samples:
-        return buffer
-    
-    new_buffer = np.zeros(min_samples, dtype="float32")
-    new_buffer[:len(buffer)] = buffer
-    return new_buffer
-
-
-def concatenate_audio(*buffers: np.ndarray) -> np.ndarray:
-    """Concatenate multiple audio buffers.
-    
-    Args:
-        *buffers: Audio buffers to concatenate.
-        
-    Returns:
-        Single concatenated audio buffer.
-    """
-    non_empty = [b for b in buffers if b.size > 0]
-    if not non_empty:
-        return np.array([], dtype="float32")
-    return np.concatenate(non_empty)
-
-
-def audio_duration(audio: np.ndarray, sample_rate: int = SAMPLE_RATE) -> float:
-    """Calculate duration of audio buffer in seconds.
-    
-    Args:
-        audio: Audio buffer.
-        sample_rate: Sample rate in Hz (default SAMPLE_RATE).
-        
-    Returns:
-        Duration in seconds.
-    """
-    return len(audio) / sample_rate
-
-
-def samples_for_duration(duration_seconds: float, sample_rate: int = SAMPLE_RATE) -> int:
-    """Calculate number of samples for a given duration.
-    
-    Args:
-        duration_seconds: Duration in seconds.
-        sample_rate: Sample rate in Hz (default SAMPLE_RATE).
-        
-    Returns:
-        Number of samples (rounded to nearest integer), or 0 if duration is <= 0.
-    """
-    if duration_seconds <= 0:
-        return 0
-    return int(round(duration_seconds * sample_rate))
-
-
-def fit_audio_to_duration(
-    audio: np.ndarray,
-    target_duration: float,
-    sample_rate: int = SAMPLE_RATE,
-) -> np.ndarray:
-    """Pad or trim audio to match target duration.
-
-    Args:
-        audio: Input audio buffer.
-        target_duration: Desired duration in seconds.
-        sample_rate: Sample rate in Hz.
-
-    Returns:
-        Audio buffer of exact length target_duration * sample_rate.
-    """
-    target_samples = int(target_duration * sample_rate)
-    if len(audio) < target_samples:
-        padding = np.zeros(target_samples - len(audio), dtype="float32")
-        return np.concatenate([audio, padding])
-    return audio[:target_samples]
-
-
-def ffmpeg_time_stretch(
-    audio: np.ndarray,
-    speed_factor: float,
-    sample_rate: int = SAMPLE_RATE,
-) -> np.ndarray:
-    """Time-stretch audio using FFmpeg's atempo filter.
-
-    Args:
-        audio: Input audio buffer (float32).
-        speed_factor: Speed multiplier (>1.0 = faster).
-        sample_rate: Sample rate in Hz.
-
-    Returns:
-        Time-stretched audio buffer.
-    """
-    import math
-    import subprocess
-
-    import static_ffmpeg
-
-    if speed_factor <= 1.0 or audio.size == 0:
-        return audio
-
-    static_ffmpeg.add_paths()
-    num_stages = max(1, int(math.ceil(math.log(speed_factor) / math.log(2.0))))
-    tempo = speed_factor ** (1.0 / num_stages)
-    filter_str = ",".join([f"atempo={tempo:.6f}"] * num_stages)
-
-    proc = subprocess.Popen(
-        [
-            "ffmpeg", "-y",
-            "-f", "f32le", "-ar", str(sample_rate), "-ac", "1",
-            "-i", "pipe:0",
-            "-filter:a", filter_str,
-            "-f", "f32le", "-ar", str(sample_rate), "-ac", "1",
-            "pipe:1",
-        ],
-        stdin=subprocess.PIPE,
-        stdout=subprocess.PIPE,
-        stderr=subprocess.PIPE,
-    )
-    out, _ = proc.communicate(input=audio.tobytes())
-    return np.frombuffer(out, dtype="float32")

abogen/domain/audio_helpers.py

@@ -1,118 +0,0 @@
-"""Audio helper utilities.
-
-Functions for building ffmpeg commands, converting audio formats,
-and applying chapter metadata to MP4 files.
-"""
-
-from __future__ import annotations
-
-from pathlib import Path
-from typing import Any, Dict, List, Optional
-
-import numpy as np
-
-
-SAMPLE_RATE = 24000
-
-
-def build_ffmpeg_command(path: Path, fmt: str, metadata: Optional[Dict[str, str]] = None) -> list[str]:
-    from abogen.infrastructure.exporters import ExportService
-
-    base = [
-        "ffmpeg",
-        "-y",
-        "-f",
-        "f32le",
-        "-ar",
-        str(SAMPLE_RATE),
-        "-ac",
-        "1",
-        "-i",
-        "pipe:0",
-    ]
-    if fmt == "mp3":
-        base += ["-c:a", "libmp3lame", "-qscale:a", "2"]
-    elif fmt == "opus":
-        base += ["-c:a", "libopus", "-b:a", "24000"]
-    elif fmt == "m4b":
-        base += ["-c:a", "aac", "-q:a", "2", "-movflags", "+faststart+use_metadata_tags"]
-    else:
-        base += ["-c:a", "copy"]
-
-    if metadata:
-        svc = ExportService()
-        base.extend(svc._metadata_to_ffmpeg_args(metadata))
-    base.append(str(path))
-    return base
-
-
-def to_float32(audio_segment) -> np.ndarray:
-    if audio_segment is None:
-        return np.zeros(0, dtype="float32")
-
-    tensor = audio_segment
-    if hasattr(tensor, "detach"):
-        tensor = tensor.detach()
-    if hasattr(tensor, "cpu"):
-        try:
-            tensor = tensor.cpu()
-        except Exception:
-            pass
-    if hasattr(tensor, "numpy"):
-        return np.asarray(tensor.numpy(), dtype="float32").reshape(-1)
-    return np.asarray(tensor, dtype="float32").reshape(-1)
-
-
-def apply_m4b_chapters_with_mutagen(
-    audio_path: Path,
-    chapters: List[Dict[str, Any]],
-) -> bool:
-    """Apply chapter atoms to an MP4/M4B file using mutagen.
-
-    Returns True if chapters were written, False otherwise.
-    Raises ImportError if mutagen is not installed.
-    """
-    if not chapters:
-        return False
-
-    from fractions import Fraction
-    from mutagen.mp4 import MP4, MP4Chapter  # type: ignore[import]
-
-    mp4 = MP4(str(audio_path))
-
-    chapter_objects: List[MP4Chapter] = []
-    for index, entry in enumerate(sorted(chapters, key=lambda item: float(item.get("start") or 0.0))):
-        start_raw = entry.get("start")
-        if start_raw is None:
-            continue
-        try:
-            start_seconds = max(0.0, float(start_raw))
-        except (TypeError, ValueError):
-            continue
-
-        title_value = entry.get("title")
-        title_text = str(title_value) if title_value else f"Chapter {index + 1}"
-
-        start_fraction = Fraction(int(round(start_seconds * 1000)), 1000)
-        chapter_atom = MP4Chapter(start_fraction, title_text)
-
-        end_raw = entry.get("end")
-        if end_raw is not None:
-            try:
-                end_seconds = float(end_raw)
-            except (TypeError, ValueError):
-                end_seconds = None
-            if end_seconds is not None and end_seconds > start_seconds:
-                chapter_atom.end = Fraction(int(round(end_seconds * 1000)), 1000)
-
-        chapter_objects.append(chapter_atom)
-
-    if not chapter_objects:
-        return False
-
-    from typing import cast
-
-    mp4.chapters = cast(Any, chapter_objects)
-    mp4.save()
-
-    return True

abogen/domain/audio_sink.py

@@ -1,131 +0,0 @@
-"""Audio sink abstraction for unified audio output.
-
-Provides a context-manager-based abstraction for writing audio data
-to various output formats (WAV, FLAC via soundfile; compressed via ffmpeg).
-
-Usage:
-    with open_audio_sink(path, "wav") as sink:
-        sink.write(audio_data)
-"""
-
-from __future__ import annotations
-
-import os
-import subprocess
-import sys
-from dataclasses import dataclass
-from pathlib import Path
-from typing import Callable, Optional
-
-import numpy as np
-
-from abogen.domain.audio_buffer import SAMPLE_RATE
-from abogen.domain.audio_helpers import build_ffmpeg_command
-
-
-@dataclass(frozen=True)
-class AudioSink:
-    """Represents an open audio output target."""
-
-    write: Callable[[np.ndarray], None]
-    close: Callable[[], None]
-
-    def __enter__(self) -> AudioSink:
-        return self
-
-    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
-        self.close()
-
-
-def _ensure_ffmpeg() -> None:
-    """Ensure static ffmpeg binaries are on PATH."""
-    import static_ffmpeg  # type: ignore
-
-    ffmpeg_cache_root = _get_ffmpeg_cache_root()
-    platform_cache = os.path.join(ffmpeg_cache_root, sys.platform)
-    os.makedirs(platform_cache, exist_ok=True)
-    try:
-        import static_ffmpeg.run as static_ffmpeg_run  # type: ignore
-
-        static_ffmpeg_run.LOCK_FILE = os.path.join(ffmpeg_cache_root, "lock.file")
-    except Exception:
-        pass
-    static_ffmpeg.add_paths(weak=True, download_dir=platform_cache)
-
-
-def _get_ffmpeg_cache_root() -> str:
-    from abogen.utils import get_internal_cache_path
-
-    return get_internal_cache_path("ffmpeg")
-
-
-def open_audio_sink(
-    path: Path,
-    fmt: str,
-    *,
-    metadata: Optional[dict[str, str]] = None,
-    cancel_check: Optional[Callable[[], bool]] = None,
-    extra_ffmpeg_args: Optional[list[str]] = None,
-    ffmpeg_cmd: Optional[list[str]] = None,
-) -> AudioSink:
-    """Open an audio output sink for writing raw float32 PCM samples.
-
-    Args:
-        path: Output file path.
-        fmt: Output format ("wav", "flac", "mp3", "opus", "m4b").
-        metadata: Optional metadata dict (ignored when ffmpeg_cmd is provided).
-        cancel_check: Optional callable; if it returns True, writes are silently skipped.
-        extra_ffmpeg_args: Optional extra args inserted after ffmpeg header (ignored when ffmpeg_cmd is provided).
-        ffmpeg_cmd: Optional pre-built ffmpeg command list (for m4b with cover art etc.).
-
-    Returns:
-        AudioSink with write() and close() methods.
-    """
-    fmt = fmt.lower()
-
-    if fmt in {"wav", "flac"}:
-        import soundfile as sf
-
-        soundfile_obj = sf.SoundFile(
-            path,
-            mode="w",
-            samplerate=SAMPLE_RATE,
-            channels=1,
-            format=fmt.upper(),
-        )
-
-        def _write_wav(data: np.ndarray) -> None:
-            if cancel_check and cancel_check():
-                return
-            soundfile_obj.write(data)
-
-        def _close_wav() -> None:
-            soundfile_obj.close()
-
-        return AudioSink(write=_write_wav, close=_close_wav)
-
-    # Compressed formats: pipe through ffmpeg
-    _ensure_ffmpeg()
-
-    if ffmpeg_cmd is not None:
-        cmd = list(ffmpeg_cmd)
-    else:
-        cmd = build_ffmpeg_command(path, fmt, metadata=metadata)
-        if extra_ffmpeg_args:
-            cmd[2:2] = extra_ffmpeg_args
-
-    process = subprocess.Popen(
-        cmd, stdin=subprocess.PIPE, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL
-    )
-
-    def _write_compressed(data: np.ndarray) -> None:
-        if (cancel_check and cancel_check()) or process.stdin is None or process.stdin.closed:
-            return
-        process.stdin.write(data.tobytes())
-
-    def _close_compressed() -> None:
-        if process.stdin and not process.stdin.closed:
-            process.stdin.close()
-        process.wait()
-
-    return AudioSink(write=_write_compressed, close=_close_compressed)

abogen/domain/chapter_classification.py

@@ -1,131 +0,0 @@
-"""Heuristics for classifying chapters as content vs. supplements.
-
-A 'supplement' is any non-story material that a listener would typically
-skip: title page, copyright, table of contents, acknowledgements, etc.
-The scoring functions return a float; higher ⇒ more likely to be a
-supplement.  ``should_preselect_chapter`` turns that score into a
-boolean suitable for a web form default.
-"""
-
-from __future__ import annotations
-
-import re
-from typing import Any, Dict, List, Tuple
-
-# Compiled once at module load – these are immutable.
-
-_SUPPLEMENT_TITLE_PATTERNS: List[Tuple[re.Pattern[str], float]] = [
-    (re.compile(r"\btitle\s+page\b"), 3.0),
-    (re.compile(r"\bcopyright\b"), 2.4),
-    (re.compile(r"\btable\s+of\s+contents\b"), 2.8),
-    (re.compile(r"\bcontents\b"), 2.0),
-    (re.compile(r"\backnowledg(e)?ments?\b"), 2.0),
-    (re.compile(r"\bdedication\b"), 2.0),
-    (re.compile(r"\babout\s+the\s+author(s)?\b"), 2.4),
-    (re.compile(r"\balso\s+by\b"), 2.0),
-    (re.compile(r"\bpraise\s+for\b"), 2.0),
-    (re.compile(r"\bcolophon\b"), 2.2),
-    (re.compile(r"\bpublication\s+data\b"), 2.2),
-    (re.compile(r"\btranscriber'?s?\s+note\b"), 2.2),
-    (re.compile(r"\bglossary\b"), 2.2),
-    (re.compile(r"\bindex\b"), 2.0),
-    (re.compile(r"\bbibliograph(y|ies)\b"), 2.0),
-    (re.compile(r"\breferences\b"), 1.8),
-    (re.compile(r"\bappendix\b"), 1.9),
-]
-
-_CONTENT_TITLE_PATTERNS: List[re.Pattern[str]] = [
-    re.compile(r"\bchapter\b"),
-    re.compile(r"\bbook\b"),
-    re.compile(r"\bpart\b"),
-    re.compile(r"\bsection\b"),
-    re.compile(r"\bscene\b"),
-    re.compile(r"\bprologue\b"),
-    re.compile(r"\bepilogue\b"),
-    re.compile(r"\bintroduction\b"),
-    re.compile(r"\bstory\b"),
-]
-
-_SUPPLEMENT_TEXT_KEYWORDS: List[Tuple[str, float]] = [
-    ("copyright", 1.2),
-    ("all rights reserved", 1.1),
-    ("isbn", 0.9),
-    ("library of congress", 1.0),
-    ("table of contents", 1.0),
-    ("dedicated to", 0.8),
-    ("acknowledg", 0.8),
-    ("printed in", 0.6),
-    ("permission", 0.6),
-    ("publisher", 0.5),
-    ("praise for", 0.9),
-    ("also by", 0.9),
-    ("glossary", 0.8),
-    ("index", 0.8),
-    ("newsletter", 3.2),
-    ("mailing list", 2.6),
-    ("sign-up", 2.2),
-]
-
-
-def supplement_score(title: str, text: str, index: int) -> float:
-    """Return a score indicating how likely *title*/*text* is a supplement.
-
-    Higher values ⇒ more likely to be non-story material (title page,
-    copyright, acknowledgements, etc.).
-    """
-    normalized_title = (title or "").lower()
-    score = 0.0
-
-    for pattern, weight in _SUPPLEMENT_TITLE_PATTERNS:
-        if pattern.search(normalized_title):
-            score += weight
-
-    for pattern in _CONTENT_TITLE_PATTERNS:
-        if pattern.search(normalized_title):
-            score -= 2.0
-
-    stripped_text = (text or "").strip()
-    length = len(stripped_text)
-    if length <= 150:
-        score += 0.9
-    elif length <= 400:
-        score += 0.6
-    elif length <= 800:
-        score += 0.35
-
-    lowercase_text = stripped_text.lower()
-    for keyword, weight in _SUPPLEMENT_TEXT_KEYWORDS:
-        if keyword in lowercase_text:
-            score += weight
-
-    if index == 0 and score > 0:
-        score += 0.25
-
-    return score
-
-
-def should_preselect_chapter(
-    title: str,
-    text: str,
-    index: int,
-    total_count: int,
-) -> bool:
-    """Return True if the chapter should be *enabled* by default in the form.
-
-    A single chapter is always preselected.  For multi-chapter books, the
-    chapter is preselected when its supplement score is below 1.9.
-    """
-    if total_count <= 1:
-        return True
-    score = supplement_score(title, text, index)
-    return score < 1.9
-
-
-def ensure_at_least_one_chapter_enabled(chapters: List[Dict[str, Any]]) -> None:
-    """Mutate *chapters* in-place so that at least one has ``enabled=True``."""
-    if not chapters:
-        return
-    if any(chapter.get("enabled") for chapter in chapters):
-        return
-    best_index = max(range(len(chapters)), key=lambda idx: chapters[idx].get("characters", 0))
-    chapters[best_index]["enabled"] = True

abogen/domain/chapter_overrides.py

@@ -1,92 +0,0 @@
-from __future__ import annotations
-
-from typing import Any, Dict, List, Optional, Tuple
-
-from abogen.text_extractor import ExtractedChapter
-from abogen.domain.voice_utils import coerce_truthy
-
-
-def apply_chapter_overrides(
-    extracted: List[ExtractedChapter],
-    overrides: List[Dict[str, Any]],
-) -> Tuple[List[ExtractedChapter], Dict[str, str], List[str]]:
-    if not overrides:
-        return [], {}, []
-
-    selected: List[ExtractedChapter] = []
-    metadata_updates: Dict[str, str] = {}
-    diagnostics: List[str] = []
-
-    for position, payload in enumerate(overrides):
-        if not isinstance(payload, dict):
-            diagnostics.append(
-                f"Skipped chapter override at position {position + 1}: unsupported payload type {type(payload).__name__}."
-            )
-            continue
-
-        enabled = coerce_truthy(payload.get("enabled", True))
-        payload["enabled"] = enabled
-        if not enabled:
-            continue
-
-        metadata_payload = payload.get("metadata") or {}
-        if isinstance(metadata_payload, dict):
-            for key, value in metadata_payload.items():
-                if value is None:
-                    continue
-                metadata_updates[str(key)] = str(value)
-
-        base: Optional[ExtractedChapter] = None
-        idx_candidate = payload.get("index")
-        idx_normalized: Optional[int] = None
-        if isinstance(idx_candidate, int):
-            idx_normalized = idx_candidate
-        elif isinstance(idx_candidate, str):
-            try:
-                idx_normalized = int(idx_candidate)
-            except ValueError:
-                idx_normalized = None
-        if idx_normalized is not None and 0 <= idx_normalized < len(extracted):
-            base = extracted[idx_normalized]
-            payload["index"] = idx_normalized
-
-        if base is None:
-            source_title = payload.get("source_title")
-            if isinstance(source_title, str):
-                base = next((chapter for chapter in extracted if chapter.title == source_title), None)
-
-        if base is None:
-            candidate_title = payload.get("title")
-            if isinstance(candidate_title, str):
-                base = next((chapter for chapter in extracted if chapter.title == candidate_title), None)
-
-        text_override = payload.get("text")
-        if text_override is not None:
-            text_value = str(text_override)
-        elif base is not None:
-            text_value = base.text
-        else:
-            diagnostics.append(
-                f"Skipped chapter override at position {position + 1}: no text provided and no matching source chapter found."
-            )
-            continue
-
-        title_override = payload.get("title")
-        if title_override is not None:
-            title_value = str(title_override)
-        elif base is not None:
-            title_value = base.title
-        else:
-            title_value = f"Chapter {position + 1}"
-
-        if base and not payload.get("source_title"):
-            payload["source_title"] = base.title
-
-        payload["title"] = title_value
-        payload["text"] = text_value
-        payload["characters"] = len(text_value)
-        payload.setdefault("order", payload.get("order", position))
-
-        selected.append(ExtractedChapter(title=title_value, text=text_value))
-
-    return selected, metadata_updates, diagnostics

abogen/domain/chapter_titles.py

@@ -1,204 +0,0 @@
-from __future__ import annotations
-
-import re
-from typing import List, Tuple
-
-
-_HEADING_SANITIZE_RE = re.compile(r"[^a-z0-9]+")
-_HEADING_NUMBER_PREFIX_RE = re.compile(
-    r"^\s*(?P<number>(?:\d+|[ivxlcdm]+))(?P<suffix>(?:[\s.:;-].*)?)$",
-    re.IGNORECASE,
-)
-_ACRONYM_ALLOWLIST = {
-    "AI", "API", "CPU", "DIY", "GPU", "HTML", "HTTP", "HTTPS", "ID",
-    "JSON", "MP3", "MP4", "M4B", "NASA", "OCR", "PDF", "SQL", "TV",
-    "TTS", "UK", "UN", "UFO", "OK", "URL", "USA", "US", "VR",
-}
-_ROMAN_NUMERAL_CHARS = frozenset("IVXLCDM")
-_CAPS_WORD_RE = re.compile(r"[A-Z][A-Z0-9'\u2019-]*")
-
-
-def simplify_heading_text(text: str) -> str:
-    raw = str(text or "").strip().lower()
-    if not raw:
-        return ""
-    simplified = _HEADING_SANITIZE_RE.sub("", raw)
-    if simplified.startswith("chapter"):
-        simplified = simplified[7:]
-    return simplified
-
-
-def headings_equivalent(left: str, right: str) -> bool:
-    simple_left = simplify_heading_text(left)
-    simple_right = simplify_heading_text(right)
-    if not simple_left or not simple_right:
-        return False
-    if simple_left == simple_right:
-        return True
-    if simple_right.startswith(simple_left):
-        return True
-    if simple_left.startswith(simple_right):
-        return True
-    if len(simple_left) > 5 and simple_left in simple_right:
-        return True
-    return False
-
-
-def strip_duplicate_heading_line(text: str, heading: str) -> Tuple[str, bool]:
-    source_text = str(text or "")
-    if not source_text:
-        return source_text, False
-    normalized_heading = simplify_heading_text(heading)
-    if not normalized_heading:
-        return source_text, False
-    lines = source_text.splitlines()
-    new_lines: List[str] = []
-    removed = False
-    for line in lines:
-        stripped = line.strip()
-        if not removed and stripped:
-            if headings_equivalent(stripped, heading):
-                removed = True
-                continue
-        new_lines.append(line)
-    if not removed:
-        return source_text, False
-    while new_lines and not new_lines[0].strip():
-        new_lines.pop(0)
-    return "\n".join(new_lines), True
-
-
-def normalize_caps_word(word: str) -> str:
-    upper = word.upper()
-    letters = [char for char in upper if char.isalpha()]
-    if not letters:
-        return word
-    if upper in _ACRONYM_ALLOWLIST:
-        return word
-    if len(letters) <= 1:
-        return word
-    if all(char in _ROMAN_NUMERAL_CHARS for char in letters) and len(letters) <= 7:
-        return word
-
-    parts = re.split(r"(['\-\u2019])", word)
-    normalized_parts: List[str] = []
-    for part in parts:
-        if part in {"'", "-", "\u2019"}:
-            normalized_parts.append(part)
-            continue
-        if not part:
-            continue
-        normalized_parts.append(part[0].upper() + part[1:].lower())
-    return "".join(normalized_parts) or word
-
-
-def normalize_chapter_opening_caps(text: str) -> Tuple[str, bool]:
-    if not text:
-        return text, False
-
-    leading_len = len(text) - len(text.lstrip())
-    leading = text[:leading_len]
-    working = text[leading_len:]
-    if not working:
-        return text, False
-
-    builder: List[str] = []
-    pos = 0
-    changed = False
-
-    while pos < len(working):
-        char = working[pos]
-        if char in "\r\n":
-            builder.append(working[pos:])
-            pos = len(working)
-            break
-        if char.isspace():
-            builder.append(char)
-            pos += 1
-            continue
-        if char.islower():
-            builder.append(working[pos:])
-            pos = len(working)
-            break
-        if not char.isalpha():
-            builder.append(char)
-            pos += 1
-            continue
-
-        match = _CAPS_WORD_RE.match(working, pos)
-        if not match:
-            builder.append(char)
-            pos += 1
-            continue
-
-        word = match.group(0)
-        if any(ch.islower() for ch in word):
-            builder.append(working[pos:])
-            pos = len(working)
-            break
-
-        normalized = normalize_caps_word(word)
-        if normalized != word:
-            changed = True
-        builder.append(normalized)
-        pos = match.end()
-
-    if pos < len(working):
-        builder.append(working[pos:])
-
-    if not changed:
-        return text, False
-
-    return leading + "".join(builder), True
-
-
-def format_spoken_chapter_title(title: str, index: int, apply_prefix: bool) -> str:
-    base = str(title or "").strip()
-    if not base:
-        return f"Chapter {index}" if apply_prefix else ""
-    if not apply_prefix:
-        return base
-    lowered = base.lower()
-    if lowered.startswith("chapter") and (len(lowered) == 7 or not lowered[7].isalpha()):
-        return base
-    match = _HEADING_NUMBER_PREFIX_RE.match(base)
-    if match:
-        number = match.group("number") or ""
-        suffix = match.group("suffix") or ""
-        cleaned_suffix = suffix.lstrip(" .,:;-_ \t\u2013\u2014\u00b7\u2022")
-        if cleaned_suffix:
-            return f"Chapter {number}. {cleaned_suffix}"
-        return f"Chapter {number}"
-    return base
-
-
-def apply_chapter_text_transforms(
-    text: str,
-    *,
-    heading_text: str,
-    raw_title: str,
-    strip_heading: bool,
-    normalize_caps: bool,
-) -> Tuple[str, bool, bool]:
-    """Strip duplicate heading and normalize opening caps.
-
-    Returns ``(text, heading_removed, caps_changed)``.
-    The caller is responsible for state updates (pending flags, logging,
-    dict mutation, ``continue``).
-    """
-    heading_removed = False
-    caps_changed = False
-
-    if strip_heading and heading_text:
-        text, heading_removed = strip_duplicate_heading_line(text, heading_text)
-        if not heading_removed and raw_title:
-            match = _HEADING_NUMBER_PREFIX_RE.match(raw_title)
-            if match:
-                number = match.group("number")
-                if number:
-                    text, heading_removed = strip_duplicate_heading_line(text, number)
-
-    if normalize_caps and text:
-        text, caps_changed = normalize_chapter_opening_caps(text)
-
-    return text, heading_removed, caps_changed

abogen/domain/chunk_utils.py

@@ -1,75 +0,0 @@
-"""Chunk processing utilities.
-
-Functions for grouping chunks, recording override usage, and selecting
-text for TTS synthesis.
-"""
-
-from __future__ import annotations
-
-from collections import defaultdict
-from typing import Any, Dict, Iterable, Mapping, Optional
-
-from abogen.pronunciation_store import increment_usage
-
-
-def safe_int(value: Any, default: int = 0) -> int:
-    try:
-        return int(value)
-    except (TypeError, ValueError):
-        return default
-
-
-def group_chunks_by_chapter(chunks: Iterable[Dict[str, Any]]) -> Dict[int, List[Dict[str, Any]]]:
-    grouped: Dict[int, List[Dict[str, Any]]] = defaultdict(list)
-    for entry in chunks or []:
-        if not isinstance(entry, dict):
-            continue
-        try:
-            chapter_index = int(entry.get("chapter_index", 0))
-        except (TypeError, ValueError):
-            chapter_index = 0
-        grouped[chapter_index].append(dict(entry))
-
-    for chapter_index, items in grouped.items():
-        items.sort(key=lambda payload: safe_int(payload.get("chunk_index")))
-
-    return grouped
-
-
-def record_override_usage(
-    job: Any,
-    usage_counter: Mapping[str, int],
-    token_map: Mapping[str, str],
-) -> None:
-    if not usage_counter:
-        return
-
-    language = getattr(job, "language", "") or "a"
-    for normalized, amount in usage_counter.items():
-        if amount <= 0:
-            continue
-        token_value = token_map.get(normalized, normalized)
-        try:
-            increment_usage(language=language, token=token_value, amount=int(amount))
-        except Exception:  # pragma: no cover - defensive logging
-            job.add_log(f"Failed to record usage for override {token_value}", level="warning")
-
-
-def chunk_text_for_tts(entry: Mapping[str, Any]) -> str:
-    """Choose the best source text for synthesis.
-
-    We must prefer the raw chunk text (``text`` / ``original_text``) so
-    manual/pronunciation overrides can match against the original tokens
-    (e.g. censored words like ``Unfu*k``).  ``normalized_text`` may have
-    already been run through ``normalize_for_pipeline``, which can remove
-    punctuation and prevent overrides from triggering.
-    """
-
-    if not isinstance(entry, Mapping):
-        return ""
-    return str(
-        entry.get("text")
-        or entry.get("original_text")
-        or entry.get("normalized_text")
-        or ""
-    ).strip()

abogen/domain/conversion_engine.py

@@ -1,226 +0,0 @@
-"""Shared TTS iteration loop used by both WebUI and PyQt conversion runners.
-
-The core pattern is identical across both UIs:
-
-    for seg in tts_segments(text, backend, voice, speed, split_pattern, current_time):
-        check_cancel()
-        update_progress(seg)
-        write_audio(seg, sink)
-        accumulate_subtitles(seg)
-
-After the loop, the caller processes accumulated subtitle tokens.
-
-This module provides ``run_tts_segment_loop`` which encapsulates that
-iteration, and ``synthesize_text`` which adds normalization on top —
-the single entry point both UIs should call for text-to-speech.
-"""
-
-from __future__ import annotations
-
-import time
-from dataclasses import dataclass, field
-from typing import Any, Callable, List, Optional, Protocol
-
-from abogen.domain.audio_sink import AudioSink
-from abogen.domain.conversion_pipeline import tts_segments
-from abogen.domain.enums import SubtitleMode
-from abogen.domain.normalization import TTSContext
-from abogen.domain.progress import calc_etr_str
-from abogen.domain.subtitle_generation import process_subtitle_tokens
-
-
-class CancelChecker(Protocol):
-    """Returns True if conversion has been cancelled."""
-    def __call__(self) -> bool: ...
-
-
-@dataclass
-class SegmentStats:
-    """Running statistics updated per TTS segment."""
-    processed_chars: int = 0
-    current_time: float = 0.0
-    etr_start_time: float = field(default_factory=time.time)
-    total_characters: int = 0
-
-
-@dataclass
-class SegmentInfo:
-    """Read-only info about a TTS segment, passed to on_segment callback."""
-    graphemes: str
-    audio: Any
-    tokens: list
-    duration: float
-    chunk_start: float
-
-
-def run_tts_segment_loop(
-    *,
-    text: str,
-    params: SynthParams,
-    backend: Any,
-    voice: Any,
-    speed: float,
-    split_pattern: str,
-    chapter_sink: Optional[AudioSink] = None,
-    preview_callback: Optional[Callable[[str], None]] = None,
-    on_segment: Optional[Callable[[SegmentInfo], None]] = None,
-) -> tuple[int, list]:
-    """Run the core TTS segment iteration loop.
-
-    Args:
-        text: Normalized text to synthesize.
-        params: Common synthesis parameters (stats, callbacks, sinks, etc.).
-        backend: TTS pipeline instance (Kokoro or Supertonic).
-        voice: Voice name/id for the backend.
-        speed: Speech speed multiplier.
-        split_pattern: Regex pattern used by the TTS engine for sentence splitting.
-        preview_callback: Called with a short preview string per segment.
-        on_segment: Called with a SegmentInfo for each segment *before*
-            audio is written.  Useful for callers that need per-segment
-            subtitle processing (e.g. PyQt dual-writer pattern).
-            When provided, the default subtitle accumulation is skipped.
-
-    Returns:
-        Tuple of (segment_count, accumulated_subtitle_tokens).
-        The caller is responsible for processing subtitle tokens via
-        ``process_subtitle_tokens`` and writing entries to subtitle writers.
-    """
-    local_segments = 0
-    accumulated_tokens: list[dict] = []
-
-    for seg in tts_segments(
-        text,
-        backend=backend,
-        voice=voice,
-        speed=speed,
-        split_pattern=split_pattern,
-        current_time=params.stats.current_time,
-    ):
-        if params.check_cancel():
-            break
-
-        local_segments += 1
-        params.stats.processed_chars += len(seg.graphemes)
-
-        # Progress
-        if params.stats.total_characters:
-            percent = min(int(params.stats.processed_chars / params.stats.total_characters * 100), 99)
-        else:
-            percent = 0 if params.stats.processed_chars == 0 else 99
-
-        etr_str = calc_etr_str(
-            time.time() - params.stats.etr_start_time,
-            params.stats.processed_chars,
-            params.stats.total_characters,
-        )
-        params.on_progress(percent, etr_str)
-
-        # Preview / log
-        if preview_callback:
-            preview_callback(seg.graphemes or "[silence]")
-
-        # Per-segment callback (for callers needing segment-level access)
-        if on_segment:
-            info = SegmentInfo(
-                graphemes=seg.graphemes,
-                audio=seg.audio,
-                tokens=list(seg.tokens) if seg.tokens else [],
-                duration=seg.duration,
-                chunk_start=getattr(seg, "chunk_start", params.stats.current_time),
-            )
-            on_segment(info)
-
-        # Write audio
-        if chapter_sink:
-            chapter_sink.write(seg.audio)
-        if params.audio_sink:
-            params.audio_sink.write(seg.audio)
-
-        # Accumulate subtitle tokens (default path; skipped if on_segment handles it)
-        if not on_segment and params.subtitle_mode != SubtitleMode.DISABLED and seg.tokens:
-            accumulated_tokens.extend(seg.tokens)
-
-        # Update timing
-        if params.audio_sink:
-            params.stats.current_time += seg.duration
-
-    return local_segments, accumulated_tokens
-
-
-def process_and_write_subtitles(
-    accumulated_tokens: list[dict],
-    subtitle_writer: Any,
-    *,
-    subtitle_mode: str,
-    max_subtitle_words: int,
-    lang_code: str,
-    use_spacy_segmentation: bool,
-    fallback_end_time: float,
-) -> None:
-    """Process accumulated subtitle tokens and write entries to a subtitle writer.
-
-    This is the standard subtitle post-processing step shared by both UIs.
-    """
-    if not accumulated_tokens or not subtitle_writer:
-        return
-    new_entries: list[tuple] = []
-    process_subtitle_tokens(
-        accumulated_tokens,
-        new_entries,
-        max_subtitle_words,
-        subtitle_mode,
-        lang_code,
-        use_spacy_segmentation=use_spacy_segmentation,
-        fallback_end_time=fallback_end_time,
-    )
-    for start, end, text in new_entries:
-        subtitle_writer.write_entry(start=start, end=end, text=text)
-
-
-@dataclass(frozen=True)
-class SynthParams:
-    """Common parameters for synthesize_text calls.
-
-    Packed once by the executor to avoid repeating identical kwargs.
-    When adding new common params, change only this dataclass.
-    """
-    tts_context: TTSContext
-    stats: SegmentStats
-    check_cancel: CancelChecker
-    on_progress: Callable[[int, str], None]
-    audio_sink: Optional[AudioSink] = None
-    subtitle_mode: str = "Disabled"
-    max_subtitle_words: int = 50
-    lang_code: str = "a"
-    use_spacy_segmentation: bool = False
-
-
-def synthesize_text(
-    *,
-    text: str,
-    params: SynthParams,
-    backend: Any,
-    voice: Any,
-    speed: float,
-    chapter_sink: Optional[AudioSink] = None,
-    preview_callback: Optional[Callable[[str], None]] = None,
-    on_segment: Optional[Callable[[SegmentInfo], None]] = None,
-    split_pattern_override: Optional[str] = None,
-) -> tuple[int, list]:
-    """Normalize text and run TTS — the single entry point for both UIs.
-
-    Combines TTSContext.normalize() + run_tts_segment_loop() into one call.
-    UI-specific concerns (provider resolution, progress display) stay in the UI.
-    """
-    normalized = params.tts_context.normalize(text)
-    return run_tts_segment_loop(
-        text=normalized,
-        params=params,
-        backend=backend,
-        voice=voice,
-        speed=speed,
-        split_pattern=split_pattern_override or params.tts_context.split_pattern,
-        chapter_sink=chapter_sink,
-        preview_callback=preview_callback,
-        on_segment=on_segment,
-    )

abogen/domain/conversion_pipeline.py

@@ -1,244 +0,0 @@
-"""Shared TTS emission pipeline.
-
-Provides the core TTS emission loop used by both WebUI and PyQt conversion runners.
-The caller handles audio I/O, progress reporting, and subtitle writing.
-"""
-
-from __future__ import annotations
-
-import logging
-from dataclasses import dataclass, field
-
-from abogen.domain.enums import SubtitleMode
-from typing import Any, Callable, Dict, Iterator, List, Optional
-
-import numpy as np
-
-from abogen.domain.audio_helpers import to_float32
-from abogen.domain.normalization import prepare_text_for_tts
-from abogen.domain.tokens import FakeToken
-from abogen.domain.audio_buffer import SAMPLE_RATE
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class SegmentResult:
-    """One TTS segment emitted by the pipeline."""
-    graphemes: str
-    audio: np.ndarray
-    duration: float
-    chunk_start: float
-    tokens: List[Dict[str, Any]] = field(default_factory=list)
-
-
-def tts_segments(
-    text: str,
-    *,
-    backend: Any,
-    voice: Any,
-    speed: float,
-    split_pattern: str,
-    current_time: float = 0.0,
-) -> Iterator[SegmentResult]:
-    """Invoke TTS backend on (already normalized) text and yield SegmentResults.
-
-    Use this when you've already normalized the text yourself (e.g. after
-    spaCy sentence segmentation). For raw text, use emit_text_segments() instead.
-
-    Args:
-        text: Already-normalized text to synthesize.
-        backend: TTS pipeline callable.
-        voice: Resolved voice.
-        speed: TTS speed multiplier.
-        split_pattern: Regex pattern for sentence splitting.
-        current_time: Current position in the audio timeline (seconds).
-
-    Yields:
-        SegmentResult for each non-empty TTS segment.
-    """
-    segment_iter = backend(
-        text,
-        voice=voice,
-        speed=speed,
-        split_pattern=split_pattern,
-    )
-
-    chunk_start = current_time
-
-    for segment in segment_iter:
-        graphemes_raw = getattr(segment, "graphemes", "") or ""
-        graphemes = graphemes_raw.strip()
-
-        audio = to_float32(getattr(segment, "audio", None))
-        if audio.size == 0:
-            continue
-
-        duration = len(audio) / SAMPLE_RATE
-
-        tokens_list = getattr(segment, "tokens", [])
-        if not tokens_list and graphemes:
-            tokens_list = [FakeToken(graphemes, 0, duration)]
-
-        tokens = [
-            {
-                "start": chunk_start + (tok.start_ts or 0),
-                "end": chunk_start + (tok.end_ts or 0),
-                "text": tok.text,
-                "whitespace": tok.whitespace,
-            }
-            for tok in tokens_list
-        ]
-
-        yield SegmentResult(
-            graphemes=graphemes,
-            audio=audio,
-            duration=duration,
-            chunk_start=chunk_start,
-            tokens=tokens,
-        )
-
-        chunk_start += duration
-
-
-def emit_text_segments(
-    text: str,
-    *,
-    backend: Any,
-    voice: Any,
-    speed: float,
-    split_pattern: str,
-    current_time: float = 0.0,
-    # normalization
-    heteronym_rules: Any = None,
-    pronunciation_rules: Any = None,
-    normalization_overrides: Any = None,
-    usage_counter: Optional[Dict[str, int]] = None,
-) -> Iterator[SegmentResult]:
-    """Normalize text and yield SegmentResults from the TTS backend.
-
-    This is the innermost TTS emission loop shared by both UIs. It handles:
-    1. Text normalization (heteronym + pronunciation rules)
-    2. TTS backend invocation
-    3. Segment iteration with token extraction
-
-    The caller is responsible for:
-    - Writing audio to sinks
-    - Accumulating tokens for subtitle processing
-    - Progress tracking and cancellation
-    - Error handling
-
-    Args:
-        text: Raw text to synthesize.
-        backend: TTS pipeline callable (kokoro or supertonic).
-        voice: Resolved voice for TTS.
-        speed: TTS speed multiplier.
-        split_pattern: Regex pattern for sentence splitting.
-        current_time: Current position in the audio timeline (seconds).
-        heteronym_rules: Compiled heteronym rules.
-        pronunciation_rules: Compiled pronunciation rules.
-        normalization_overrides: User normalization overrides.
-        usage_counter: Counter for normalization statistics.
-
-    Yields:
-        SegmentResult for each non-empty TTS segment.
-    """
-    source_text = str(text or "")
-    normalized = prepare_text_for_tts(
-        source_text,
-        heteronym_rules=heteronym_rules,
-        pronunciation_rules=pronunciation_rules,
-        normalization_overrides=normalization_overrides,
-        usage_counter=usage_counter,
-    )
-
-    yield from tts_segments(
-        normalized,
-        backend=backend,
-        voice=voice,
-        speed=speed,
-        split_pattern=split_pattern,
-        current_time=current_time,
-    )
-
-
-def emit_text_to_sinks(
-    text: str,
-    *,
-    backend: Any,
-    voice: Any,
-    speed: float,
-    split_pattern: str,
-    current_time: float = 0.0,
-    # sinks
-    audio_sink: Any = None,
-    chapter_sink: Any = None,
-    # subtitle
-    subtitle_writer: Any = None,
-    subtitle_mode: str = "Disabled",
-    subtitle_lang: str = "a",
-    max_subtitle_words: int = 50,
-    use_spacy_segmentation: bool = True,
-    # normalization
-    heteronym_rules: Any = None,
-    pronunciation_rules: Any = None,
-    normalization_overrides: Any = None,
-    usage_counter: Optional[Dict[str, int]] = None,
-) -> tuple[int, float, List[Dict[str, Any]]]:
-    """Emit TTS audio for text, writing to sinks and collecting subtitle tokens.
-
-    Convenience wrapper around emit_text_segments() that handles audio writing
-    and token accumulation. Returns stats for the caller to update progress.
-
-    Returns:
-        Tuple of (segments_emitted, new_current_time, accumulated_tokens).
-    """
-    from abogen.domain.subtitle_generation import process_subtitle_tokens
-
-    segments_emitted = 0
-    accumulated_tokens: List[Dict[str, Any]] = []
-
-    for seg in emit_text_segments(
-        text,
-        backend=backend,
-        voice=voice,
-        speed=speed,
-        split_pattern=split_pattern,
-        current_time=current_time,
-        heteronym_rules=heteronym_rules,
-        pronunciation_rules=pronunciation_rules,
-        normalization_overrides=normalization_overrides,
-        usage_counter=usage_counter,
-    ):
-        segments_emitted += 1
-
-        # Write audio
-        if chapter_sink:
-            chapter_sink.write(seg.audio)
-        if audio_sink:
-            audio_sink.write(seg.audio)
-
-        # Collect tokens
-        accumulated_tokens.extend(seg.tokens)
-
-    # Flush subtitle tokens
-    if subtitle_writer and accumulated_tokens:
-        _use_spacy = subtitle_mode not in (SubtitleMode.DISABLED, SubtitleMode.LINE)
-        new_entries: List[tuple] = []
-        process_subtitle_tokens(
-            accumulated_tokens,
-            new_entries,
-            max_subtitle_words,
-            subtitle_mode,
-            subtitle_lang,
-            use_spacy_segmentation=_use_spacy,
-            fallback_end_time=current_time + sum(t["end"] - t["start"] for t in accumulated_tokens if accumulated_tokens),
-        )
-        for start, end, text_entry in new_entries:
-            subtitle_writer.write_entry(start=start, end=end, text=text_entry)
-
-    new_time = current_time
-    if accumulated_tokens:
-        new_time = max(t["end"] for t in accumulated_tokens)
-
-    return segments_emitted, new_time, accumulated_tokens

abogen/domain/device.py

@@ -1,31 +0,0 @@
-from __future__ import annotations
-
-import platform as _platform
-
-
-def select_device() -> str:
-    """Return the best available compute device (``"mps"``, ``"cuda"``, or ``"cpu"``).
-
-    Checks ``torch`` availability at runtime so this can be called from
-    any context without requiring torch at import time.
-    """
-    try:
-        import torch  # type: ignore[import-not-found]
-    except Exception:
-        return "cpu"
-
-    system = _platform.system()
-    if system == "Darwin" and _platform.processor() == "arm":
-        try:
-            if torch.backends.mps.is_available():  # type: ignore[union-attr]
-                return "mps"
-        except Exception:
-            pass
-        return "cpu"
-
-    try:
-        if torch.cuda.is_available():  # type: ignore[union-attr]
-            return "cuda"
-    except Exception:
-        pass
-    return "cpu"

abogen/domain/enums.py

@@ -1,179 +0,0 @@
-"""Domain enums — typed constants for values tied to business logic.
-
-Using Enum instead of bare strings ensures:
-- Invalid values are caught at construction time
-- IDE autocomplete and type checking work
-- Adding new values is explicit (must update Enum)
-"""
-
-from __future__ import annotations
-
-from enum import Enum
-from pathlib import Path
-
-
-class SubtitleMode(str, Enum):
-    """Subtitle generation mode."""
-    DISABLED = "Disabled"
-    LINE = "Line"
-    SENTENCE = "Sentence"
-    SENTENCE_COMMA = "Sentence + Comma"
-    SENTENCE_HIGHLIGHT = "Sentence + Highlighting"
-
-    @classmethod
-    def from_str(cls, value: str) -> SubtitleMode:
-        """Parse from user input: case-insensitive, strips whitespace."""
-        normalized = value.strip()
-        for member in cls:
-            if member.value.lower() == normalized.lower():
-                return member
-        raise ValueError(f"Invalid SubtitleMode: {value!r}. Valid: {[m.value for m in cls]}")
-
-
-class OutputFormat(str, Enum):
-    """Audio output format."""
-    WAV = "wav"
-    MP3 = "mp3"
-    FLAC = "flac"
-    OPUS = "opus"
-    M4B = "m4b"
-
-    @property
-    def dot_ext(self) -> str:
-        """File extension with dot: '.wav', '.mp3', etc."""
-        return f".{self.value}"
-
-    @property
-    def is_lossless(self) -> bool:
-        """True for lossless formats."""
-        return self in (self.WAV, self.FLAC)
-
-    @classmethod
-    def from_str(cls, value: str) -> OutputFormat:
-        """Parse from user input: strips dot prefix, case-insensitive."""
-        normalized = value.strip().lstrip(".").lower()
-        for member in cls:
-            if member.value == normalized:
-                return member
-        raise ValueError(f"Invalid OutputFormat: {value!r}. Valid: {[m.value for m in cls]}")
-
-
-class SaveMode(str, Enum):
-    """Where to save the output file."""
-    SAVE_NEXT_TO_INPUT = "save_next_to_input"
-    SAVE_TO_DESKTOP = "save_to_desktop"
-    CHOOSE_OUTPUT_FOLDER = "choose_output_folder"
-    DEFAULT_OUTPUT = "default_output"
-    CUSTOM_FOLDER = "custom_folder"
-
-
-class SubtitleFormat(str, Enum):
-    """Subtitle file format."""
-    SRT = "srt"
-    ASS = "ass"
-    VTT = "vtt"
-
-    @property
-    def dot_ext(self) -> str:
-        """File extension with dot: '.srt', '.ass'."""
-        return f".{self.value}"
-
-    @classmethod
-    def from_str(cls, value: str) -> SubtitleFormat:
-        """Parse from user input: strips dot prefix, case-insensitive."""
-        normalized = value.strip().lstrip(".").lower()
-        for member in cls:
-            if member.value == normalized:
-                return member
-        raise ValueError(f"Invalid SubtitleFormat: {value!r}. Valid: {[m.value for m in cls]}")
-
-
-class InputFormat(str, Enum):
-    """Input file format."""
-    EPUB = "epub"
-    PDF = "pdf"
-    TXT = "txt"
-    MD = "md"
-    SRT = "srt"
-    ASS = "ass"
-    VTT = "vtt"
-
-    @property
-    def is_book(self) -> bool:
-        """True for book/document formats (epub, pdf, txt, md)."""
-        return self in (self.EPUB, self.PDF, self.TXT, self.MD)
-
-    @property
-    def is_subtitle(self) -> bool:
-        """True for subtitle formats (srt, ass, vtt)."""
-        return self in (self.SRT, self.ASS, self.VTT)
-
-    @property
-    def dot_ext(self) -> str:
-        """File extension with dot: '.epub', '.srt', etc."""
-        return f".{self.value}"
-
-    @classmethod
-    def from_path(cls, path: Path) -> InputFormat:
-        """Detect format from file path extension."""
-        suffix = path.suffix.lower().lstrip(".")
-        if suffix == "markdown":
-            return cls.MD
-        try:
-            return cls(suffix)
-        except ValueError:
-            raise ValueError(f"Unsupported input format: {path.suffix!r}. Supported: {[m.value for m in cls]}")
-
-
-class Language(str, Enum):
-    """TTS language code (ISO 639-1 with region where needed).
-
-    Each engine (Kokoro, Supertonic) maps these to its own
-    internal language identifiers.
-    """
-    EN_US = "en-US"
-    EN_GB = "en-GB"
-    ES = "es"
-    FR = "fr"
-    HI = "hi"
-    IT = "it"
-    JA = "ja"
-    PT_BR = "pt-BR"
-    ZH = "zh"
-
-    @property
-    def display_name(self) -> str:
-        """Human-readable language name."""
-        _names = {
-            "en-US": "American English",
-            "en-GB": "British English",
-            "es": "Spanish",
-            "fr": "French",
-            "hi": "Hindi",
-            "it": "Italian",
-            "ja": "Japanese",
-            "pt-BR": "Brazilian Portuguese",
-            "zh": "Mandarin Chinese",
-        }
-        return _names[self.value]
-
-    @property
-    def is_cjk(self) -> bool:
-        """True for CJK languages (Chinese, Japanese)."""
-        return self in (self.ZH, self.JA)
-
-    @property
-    def supports_subtitle_tokens(self) -> bool:
-        """True if this language generates timestamped tokens for subtitles."""
-        return self in (self.EN_US, self.EN_GB)
-
-    @classmethod
-    def from_str(cls, value: str) -> Language:
-        """Parse from user input: ISO code, case-insensitive."""
-        if isinstance(value, Language):
-            return value
-        normalized = value.strip()
-        for member in cls:
-            if member.value.lower() == normalized.lower():
-                return member
-        raise ValueError(f"Invalid Language: {value!r}. Valid: {[m.value for m in cls]}")

abogen/domain/file_type.py

@@ -1,136 +0,0 @@
-from __future__ import annotations
-
-import re
-from dataclasses import dataclass
-from pathlib import Path
-from typing import Any, Dict, List, Tuple
-
-from abogen.text_extractor import ExtractedChapter
-
-
-_SIGNIFICANT_LENGTH_THRESHOLDS: Dict[str, int] = {"epub": 1000, "markdown": 500}
-_MIN_SHORT_CONTENT: Dict[str, int] = {"epub": 240, "markdown": 160}
-_STRUCTURAL_KEYWORDS = (
-    "preface",
-    "prologue",
-    "introduction",
-    "foreword",
-    "epilogue",
-    "afterword",
-    "appendix",
-    "acknowledgment",
-    "acknowledgement",
-)
-_STRUCTURAL_MIN_LENGTH = 120
-_MAX_SHORT_CHAPTERS = 2
-
-
-@dataclass
-class ChapterFilterResult:
-    kept: List[ExtractedChapter]
-    skipped: List[Tuple[str, int]]
-
-
-def infer_file_type(path: Path) -> str:
-    suffix = path.suffix.lower()
-    if suffix == ".epub":
-        return "epub"
-    if suffix in {".md", ".markdown"}:
-        return "markdown"
-    if suffix == ".pdf":
-        return "pdf"
-    if suffix == ".txt":
-        return "text"
-    return suffix.lstrip(".") or "text"
-
-
-def looks_structural(title: str) -> bool:
-    lowered = title.strip().lower()
-    if not lowered:
-        return False
-    return any(keyword in lowered for keyword in _STRUCTURAL_KEYWORDS)
-
-
-def chapter_label(file_type: str) -> str:
-    return "chapters" if file_type.lower() in {"epub", "markdown"} else "pages"
-
-
-def auto_select_relevant_chapters(
-    chapters: List[ExtractedChapter],
-    file_type: str,
-) -> ChapterFilterResult:
-    if not chapters:
-        return ChapterFilterResult(kept=[], skipped=[])
-
-    normalized = file_type.lower()
-    threshold = _SIGNIFICANT_LENGTH_THRESHOLDS.get(normalized, 0)
-    min_short = _MIN_SHORT_CONTENT.get(normalized, 0)
-
-    kept: List[ExtractedChapter] = []
-    skipped: List[Tuple[str, int]] = []
-    short_kept = 0
-
-    for chapter in chapters:
-        stripped = chapter.text.strip()
-        length = len(stripped)
-        if length == 0:
-            skipped.append((chapter.title, length))
-            continue
-
-        keep = False
-        if threshold == 0:
-            keep = True
-        elif length >= threshold:
-            keep = True
-        elif not kept:
-            keep = True
-        elif min_short and length >= min_short and short_kept < _MAX_SHORT_CHAPTERS:
-            keep = True
-            short_kept += 1
-        elif looks_structural(chapter.title) and length >= _STRUCTURAL_MIN_LENGTH:
-            keep = True
-
-        if keep:
-            kept.append(chapter)
-        else:
-            skipped.append((chapter.title, length))
-
-    if kept:
-        return ChapterFilterResult(kept=kept, skipped=skipped)
-
-    longest_idx = None
-    longest_length = 0
-    for idx, chapter in enumerate(chapters):
-        stripped = chapter.text.strip()
-        if stripped and len(stripped) > longest_length:
-            longest_length = len(stripped)
-            longest_idx = idx
-
-    if longest_idx is not None:
-        longest = chapters[longest_idx]
-        fallback_skipped = [
-            (chapter.title, len(chapter.text.strip()))
-            for idx, chapter in enumerate(chapters)
-            if idx != longest_idx and chapter.text.strip()
-        ]
-        return ChapterFilterResult(kept=[longest], skipped=fallback_skipped)
-
-    return ChapterFilterResult(kept=[], skipped=skipped)
-
-
-def update_metadata_for_chapter_count(
-    metadata: Dict[str, Any], count: int, file_type: str
-) -> None:
-    if not metadata or count <= 0:
-        return
-
-    label = "Chapters" if file_type.lower() in {"epub", "markdown"} else "Pages"
-    metadata["chapter_count"] = str(count)
-
-    pattern = re.compile(r"\(\d+\s+(Chapters?|Pages?)\)")
-    replacement = f"({count} {label})"
-    for key in ("album", "ALBUM"):
-        value = metadata.get(key)
-        if not isinstance(value, str):
-            continue
-        metadata[key] = pattern.sub(replacement, value)

abogen/domain/intro_outro.py

@@ -1,83 +0,0 @@
-"""Intro/outro text building and voice resolution for audiobook conversion.
-
-Both UIs (WebUI and Desktop) need to:
-1. Build intro/outro text from book metadata
-2. Resolve which voice to use for intro/outro synthesis
-
-This module provides the shared domain logic. The actual TTS synthesis
-and audio writing remain UI-specific.
-"""
-
-from __future__ import annotations
-
-from dataclasses import dataclass
-from typing import Any, Dict, Optional
-
-from abogen.domain.title_builder import build_title_intro_text, build_outro_text
-from abogen.domain.voice_resolution import resolve_fallback_voice_spec
-
-
-@dataclass
-class IntroOutroSpec:
-    """Resolved intro or outro specification ready for TTS synthesis."""
-    text: str
-    voice_spec: str
-    enabled: bool
-
-
-def resolve_intro(
-    metadata: Optional[Dict[str, Any]],
-    original_filename: str,
-    read_title_intro: bool,
-    base_voice_spec: str,
-    job_voice: str,
-    voice_cache_keys: list[str],
-) -> IntroOutroSpec:
-    """Resolve the intro specification from job settings and metadata.
-
-    Returns an IntroOutroSpec with text and voice_spec populated,
-    or enabled=False if intro is disabled or text cannot be built.
-    """
-    if not read_title_intro:
-        return IntroOutroSpec(text="", voice_spec="", enabled=False)
-
-    text = build_title_intro_text(metadata, original_filename)
-    if not text:
-        return IntroOutroSpec(text="", voice_spec="", enabled=False)
-
-    voice_spec = resolve_fallback_voice_spec(
-        base_voice_spec, job_voice, voice_cache_keys
-    )
-    if not voice_spec:
-        return IntroOutroSpec(text=text, voice_spec="", enabled=False)
-
-    return IntroOutroSpec(text=text, voice_spec=voice_spec, enabled=True)
-
-
-def resolve_outro(
-    metadata: Optional[Dict[str, Any]],
-    original_filename: str,
-    read_closing_outro: bool,
-    base_voice_spec: str,
-    job_voice: str,
-    voice_cache_keys: list[str],
-) -> IntroOutroSpec:
-    """Resolve the outro specification from job settings and metadata.
-
-    Returns an IntroOutroSpec with text and voice_spec populated,
-    or enabled=False if outro is disabled or text cannot be built.
-    """
-    if not read_closing_outro:
-        return IntroOutroSpec(text="", voice_spec="", enabled=False)
-
-    text = build_outro_text(metadata, original_filename)
-    if not text:
-        return IntroOutroSpec(text="", voice_spec="", enabled=False)
-
-    voice_spec = resolve_fallback_voice_spec(
-        base_voice_spec, job_voice, voice_cache_keys
-    )
-    if not voice_spec:
-        return IntroOutroSpec(text=text, voice_spec="", enabled=False)
-
-    return IntroOutroSpec(text=text, voice_spec=voice_spec, enabled=True)

abogen/domain/metadata_extraction.py

@@ -1,504 +0,0 @@
-"""Metadata extraction and processing utilities.
-
-This module provides functions for extracting metadata from text content,
-formatting metadata tags for TTS embedding, and generating ffmpeg metadata arguments.
-"""
-
-from __future__ import annotations
-
-import datetime
-import logging
-import os
-import re
-import uuid
-from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple
-
-logger = logging.getLogger(__name__)
-
-
-def extract_metadata_from_text(text: str) -> Dict[str, Optional[str]]:
-    """Extract metadata tags from text content.
-    
-    Looks for tags in format: <<METADATA_KEY:value>>
-    
-    Supported tags:
-    - TITLE, ARTIST, ALBUM, YEAR
-    - ALBUM_ARTIST, COMPOSER, GENRE
-    - COVER_PATH
-    
-    Args:
-        text: Text content to search for metadata tags.
-        
-    Returns:
-        Dictionary with extracted metadata values (None if not found).
-    """
-    metadata = {}
-    
-    patterns = {
-        "title": r"<<METADATA_TITLE:([^>]*)>>",
-        "artist": r"<<METADATA_ARTIST:([^>]*)>>",
-        "album": r"<<METADATA_ALBUM:([^>]*)>>",
-        "year": r"<<METADATA_YEAR:([^>]*)>>",
-        "album_artist": r"<<METADATA_ALBUM_ARTIST:([^>]*)>>",
-        "composer": r"<<METADATA_COMPOSER:([^>]*)>>",
-        "genre": r"<<METADATA_GENRE:([^>]*)>>",
-        "cover_path": r"<<METADATA_COVER_PATH:([^>]*)>>",
-    }
-    
-    for key, pattern in patterns.items():
-        match = re.search(pattern, text)
-        if match:
-            metadata[key] = match.group(1).strip()
-        else:
-            metadata[key] = None
-    
-    return metadata
-
-
-def get_filename_from_path(
-    file_path: str,
-    display_path: Optional[str] = None,
-    from_queue: bool = False,
-) -> str:
-    """Extract filename (without extension) from path.
-    
-    Args:
-        file_path: The file path to extract from.
-        display_path: Optional display path (used if from_queue is False).
-        from_queue: Whether the file is from queue.
-        
-    Returns:
-        Filename without extension.
-    """
-    if from_queue:
-        base_path = file_path
-    else:
-        base_path = display_path if display_path else file_path
-    
-    filename = os.path.splitext(os.path.basename(base_path))[0]
-    return filename
-
-
-def build_ffmpeg_metadata_args(
-    metadata: Dict[str, Optional[str]],
-    filename: str,
-) -> List[str]:
-    """Build ffmpeg metadata arguments from metadata dictionary.
-    
-    Args:
-        metadata: Dictionary with metadata keys and values.
-        filename: Fallback filename for title/album if not specified.
-        
-    Returns:
-        List of ffmpeg metadata arguments.
-    """
-    args = []
-    
-    # Default values
-    defaults = {
-        "title": filename,
-        "artist": "Unknown",
-        "album": filename,
-        "date": str(datetime.datetime.now().year),
-        "album_artist": "Unknown",
-        "composer": "Narrator",
-        "genre": "Audiobook",
-    }
-    
-    # Map of metadata keys to ffmpeg metadata keys
-    key_mapping = {
-        "title": "title",
-        "artist": "artist",
-        "album": "album",
-        "year": "date",  # year -> date for ffmpeg
-        "album_artist": "album_artist",
-        "composer": "composer",
-        "genre": "genre",
-    }
-    
-    for metadata_key, ffmpeg_key in key_mapping.items():
-        value = metadata.get(metadata_key)
-        if value is None:
-            value = defaults.get(metadata_key, "")
-        if value:
-            args.extend(["-metadata", f"{ffmpeg_key}={value}"])
-    
-    return args
-
-
-def extract_metadata_and_build_args(
-    text: str,
-    filename: str,
-    display_path: Optional[str] = None,
-    from_queue: bool = False,
-) -> Tuple[List[str], Optional[str]]:
-    """Extract metadata from text and build ffmpeg arguments.
-    
-    Convenience function that combines extract_metadata_from_text and
-    build_ffmpeg_metadata_args.
-    
-    Args:
-        text: Text content to search for metadata tags.
-        filename: Fallback filename for title/album.
-        display_path: Optional display path.
-        from_queue: Whether the file is from queue.
-        
-    Returns:
-        Tuple of (ffmpeg_metadata_args, cover_path).
-    """
-    metadata = extract_metadata_from_text(text)
-    cover_path = metadata.get("cover_path")
-    
-    # Get actual filename from path
-    actual_filename = get_filename_from_path(
-        file_path=filename,
-        display_path=display_path,
-        from_queue=from_queue,
-    )
-    
-    args = build_ffmpeg_metadata_args(metadata, actual_filename)
-    return args, cover_path
-
-
-def read_text_for_metadata(
-    file_path: str,
-    is_direct_text: bool,
-    direct_text: Optional[str] = None,
-    encoding: Optional[str] = None,
-) -> str:
-    """Read text content for metadata extraction.
-    
-    Args:
-        file_path: Path to file (or text if is_direct_text).
-        is_direct_text: Whether file_path contains direct text.
-        direct_text: Optional direct text (used if is_direct_text).
-        encoding: File encoding (detected if not provided).
-        
-    Returns:
-        Text content for metadata extraction.
-    """
-    if is_direct_text:
-        return direct_text or file_path
-    
-    # Read from file
-    actual_path = direct_text if direct_text else file_path
-    
-    try:
-        if encoding is None:
-            from abogen.utils import detect_encoding
-            encoding = detect_encoding(actual_path)
-        
-        with open(actual_path, "r", encoding=encoding, errors="replace") as f:
-            return f.read()
-    except Exception:
-        return ""
-
-
-def extract_metadata_for_file(
-    file_path: str,
-    is_direct_text: bool = False,
-) -> Dict[str, Optional[str]]:
-    """Extract metadata dict from a file or direct text.
-
-    Convenience function combining read_text_for_metadata + extract_metadata_from_text.
-    Returns empty dict on any error.
-    """
-    try:
-        text = read_text_for_metadata(
-            file_path=file_path,
-            is_direct_text=is_direct_text,
-            direct_text=file_path if is_direct_text else None,
-        )
-        if text:
-            return extract_metadata_from_text(text) or {}
-    except Exception:
-        pass
-    return {}
-
-
-def format_metadata_tags(
-    metadata: Dict[str, Any],
-    filename: str,
-    chapter_count: int,
-    file_type: str,
-    cover_bytes: Optional[bytes] = None,
-    cache_dir: Optional[str] = None,
-) -> str:
-    """Format metadata tags for insertion into TTS text.
-
-    Builds <<METADATA_KEY:value>> tags that are later parsed by
-    extract_metadata_from_text() and fed to ffmpeg.
-
-    Args:
-        metadata: Dict with keys like 'title', 'authors' (list),
-            'publication_year', 'description', 'cover_image' (bytes).
-        filename: Fallback filename (without extension) for title/album.
-        chapter_count: Number of chapters/pages.
-        file_type: 'epub', 'pdf', or 'markdown'.
-        cover_bytes: Optional cover image bytes to save to cache.
-        cache_dir: Directory for cover cache (uses default if None).
-
-    Returns:
-        Newline-joined string of <<METADATA_KEY:value>> tags.
-    """
-    title = metadata.get("title") or filename
-    authors = metadata.get("authors") or ["Unknown"]
-    authors_text = ", ".join(authors) if isinstance(authors, list) else str(authors)
-    year = metadata.get("publication_year") or str(datetime.datetime.now().year)
-
-    chapter_label = "Chapters" if file_type in ("epub", "markdown") else "Pages"
-    chapter_text = f"{chapter_count} {chapter_label}"
-
-    tags = [
-        f"<<METADATA_TITLE:{title}>>",
-        f"<<METADATA_ARTIST:{authors_text}>>",
-        f"<<METADATA_ALBUM:{title} ({chapter_text})>>",
-        f"<<METADATA_YEAR:{year}>>",
-        f"<<METADATA_ALBUM_ARTIST:{authors_text}>>",
-        f"<<METADATA_COMPOSER:Narrator>>",
-        f"<<METADATA_GENRE:Audiobook>>",
-    ]
-
-    cover_path = _save_cover_to_cache(cover_bytes, cache_dir)
-    if cover_path:
-        tags.append(f"<<METADATA_COVER_PATH:{cover_path}>>")
-
-    return "\n".join(tags)
-
-
-def _save_cover_to_cache(
-    cover_bytes: Optional[bytes],
-    cache_dir: Optional[str] = None,
-) -> Optional[str]:
-    """Save cover image bytes to cache directory.
-
-    Args:
-        cover_bytes: Raw image bytes (e.g. JPEG/PNG).
-        cache_dir: Directory to save to. If None, returns None.
-
-    Returns:
-        Normalized path to saved cover file, or None on failure.
-    """
-    if not cover_bytes:
-        return None
-    if cache_dir is None:
-        return None
-
-    try:
-        cover_path = os.path.join(cache_dir, f"cover_{uuid.uuid4()}.jpg")
-        cover_path = os.path.normpath(cover_path)
-        with open(cover_path, "wb") as f:
-            f.write(cover_bytes)
-        return cover_path
-    except Exception as e:
-        logger.warning("Failed to save cover image: %s", e)
-        return None
-
-
-def extract_book_metadata_epub(book: Any) -> Dict[str, Any]:
-    """Extract metadata from an opened ebooklib EPUB book.
-
-    Args:
-        book: An opened ebooklib EPUB book object.
-
-    Returns:
-        Dict with keys: title, authors, description, publisher,
-        publication_year, cover_image (bytes or None).
-    """
-    import ebooklib
-
-    metadata: Dict[str, Any] = {
-        "title": None,
-        "authors": [],
-        "description": None,
-        "cover_image": None,
-        "publisher": None,
-        "publication_year": None,
-    }
-
-    try:
-        title_items = book.get_metadata("DC", "title")
-        if title_items and len(title_items) > 0:
-            metadata["title"] = title_items[0][0]
-    except Exception as e:
-        logger.warning("Error extracting title metadata: %s", e)
-
-    try:
-        author_items = book.get_metadata("DC", "creator")
-        if author_items:
-            metadata["authors"] = [
-                author[0] for author in author_items if len(author) > 0
-            ]
-    except Exception as e:
-        logger.warning("Error extracting author metadata: %s", e)
-
-    try:
-        desc_items = book.get_metadata("DC", "description")
-        if desc_items and len(desc_items) > 0:
-            metadata["description"] = desc_items[0][0]
-    except Exception as e:
-        logger.warning("Error extracting description metadata: %s", e)
-
-    try:
-        publisher_items = book.get_metadata("DC", "publisher")
-        if publisher_items and len(publisher_items) > 0:
-            metadata["publisher"] = publisher_items[0][0]
-    except Exception as e:
-        logger.warning("Error extracting publisher metadata: %s", e)
-
-    try:
-        date_items = book.get_metadata("DC", "date")
-        if date_items and len(date_items) > 0:
-            date_str = date_items[0][0]
-            year_match = re.search(r"\b(19|20)\d{2}\b", date_str)
-            if year_match:
-                metadata["publication_year"] = year_match.group(0)
-            else:
-                metadata["publication_year"] = date_str
-    except Exception as e:
-        logger.warning("Error extracting publication date metadata: %s", e)
-
-    for item in book.get_items_of_type(ebooklib.ITEM_COVER):
-        metadata["cover_image"] = item.get_content()
-        break
-
-    if not metadata["cover_image"]:
-        for item in book.get_items_of_type(ebooklib.ITEM_IMAGE):
-            if "cover" in item.get_name().lower():
-                metadata["cover_image"] = item.get_content()
-                break
-
-    return metadata
-
-
-def extract_book_metadata_pdf(pdf_doc: Any) -> Dict[str, Any]:
-    """Extract metadata from an opened PyMuPDF document.
-
-    Args:
-        pdf_doc: An opened fitz.Document object.
-
-    Returns:
-        Dict with keys: title, authors, description, publisher,
-        publication_year, cover_image (bytes or None).
-    """
-    metadata: Dict[str, Any] = {
-        "title": None,
-        "authors": [],
-        "description": None,
-        "cover_image": None,
-        "publisher": None,
-        "publication_year": None,
-    }
-
-    pdf_info = pdf_doc.metadata
-    if pdf_info:
-        metadata["title"] = pdf_info.get("title", None)
-        author = pdf_info.get("author", None)
-        if author:
-            metadata["authors"] = [author]
-        metadata["description"] = pdf_info.get("subject", None)
-        keywords = pdf_info.get("keywords", None)
-        if keywords:
-            if metadata["description"]:
-                metadata["description"] += f"\n\nKeywords: {keywords}"
-            else:
-                metadata["description"] = f"Keywords: {keywords}"
-        metadata["publisher"] = pdf_info.get("creator", None)
-
-        if "creationDate" in pdf_info:
-            date_str = pdf_info["creationDate"]
-            year_match = re.search(r"D:(\d{4})", date_str)
-            if year_match:
-                metadata["publication_year"] = year_match.group(1)
-        elif "modDate" in pdf_info:
-            date_str = pdf_info["modDate"]
-            year_match = re.search(r"D:(\d{4})", date_str)
-            if year_match:
-                metadata["publication_year"] = year_match.group(1)
-
-    if len(pdf_doc) > 0:
-        try:
-            import fitz
-            pix = pdf_doc[0].get_pixmap(matrix=fitz.Matrix(2, 2))
-            metadata["cover_image"] = pix.tobytes("png")
-        except Exception:
-            pass
-
-    return metadata
-
-
-def extract_book_metadata_markdown(
-    markdown_text: str,
-    markdown_toc: Optional[List[Dict[str, Any]]] = None,
-) -> Dict[str, Any]:
-    """Extract metadata from markdown frontmatter and first heading.
-
-    Args:
-        markdown_text: Raw markdown text content.
-        markdown_toc: Optional table of contents list (each item has
-            'level' and 'name' keys).
-
-    Returns:
-        Dict with keys: title, authors, description, publication_year.
-        cover_image is always None for markdown.
-    """
-    metadata: Dict[str, Any] = {
-        "title": None,
-        "authors": [],
-        "description": None,
-        "cover_image": None,
-        "publisher": None,
-        "publication_year": None,
-    }
-
-    if not markdown_text:
-        return metadata
-
-    frontmatter_match = re.match(
-        r"^---\s*\n(.*?)\n---\s*\n", markdown_text, re.DOTALL
-    )
-    if frontmatter_match:
-        try:
-            frontmatter = frontmatter_match.group(1)
-            title_match = re.search(
-                r"^title:\s*(.+)$", frontmatter, re.MULTILINE | re.IGNORECASE
-            )
-            if title_match:
-                metadata["title"] = title_match.group(1).strip().strip("\"'")
-
-            author_match = re.search(
-                r"^author:\s*(.+)$", frontmatter, re.MULTILINE | re.IGNORECASE
-            )
-            if author_match:
-                metadata["authors"] = [
-                    author_match.group(1).strip().strip("\"'")
-                ]
-
-            desc_match = re.search(
-                r"^description:\s*(.+)$", frontmatter, re.MULTILINE | re.IGNORECASE
-            )
-            if desc_match:
-                metadata["description"] = (
-                    desc_match.group(1).strip().strip("\"'")
-                )
-
-            date_match = re.search(
-                r"^date:\s*(.+)$", frontmatter, re.MULTILINE | re.IGNORECASE
-            )
-            if date_match:
-                date_str = date_match.group(1).strip().strip("\"'")
-                year_match = re.search(r"\b(19|20)\d{2}\b", date_str)
-                if year_match:
-                    metadata["publication_year"] = year_match.group(0)
-        except Exception as e:
-            logger.warning("Error parsing markdown frontmatter: %s", e)
-
-    if not metadata["title"] and markdown_toc:
-        first_h1 = next(
-            (h for h in markdown_toc if h.get("level") == 1), None
-        )
-        if first_h1:
-            metadata["title"] = first_h1.get("name")
-
-    return metadata

abogen/domain/metadata_helpers.py

@@ -1,405 +0,0 @@
-from __future__ import annotations
-
-import json
-import math
-import re
-from pathlib import Path
-from typing import Any, Dict, List, Mapping, Optional, Tuple
-
-
-_SERIES_NAME_KEYS = (
-    "series",
-    "series_name",
-    "series_title",
-)
-_SERIES_NUMBER_KEYS = (
-    "series_index",
-    "series_position",
-    "series_sequence",
-    "book_number",
-    "series_number",
-)
-_SERIES_NUMBER_RE = re.compile(r"\d+(?:\.\d+)?")
-
-
-def normalize_metadata_map(values: Optional[Mapping[str, Any]]) -> Dict[str, str]:
-    normalized: Dict[str, str] = {}
-    if not values:
-        return normalized
-    for key, value in values.items():
-        if value is None:
-            continue
-        text = str(value).strip()
-        if not text:
-            continue
-        normalized[str(key).casefold()] = text
-    return normalized
-
-
-def format_author_sentence(raw: Optional[str]) -> str:
-    if raw is None:
-        return ""
-    normalized = str(raw).strip()
-    if not normalized:
-        return ""
-    lowered = normalized.casefold()
-    if lowered in {"unknown", "various"}:
-        return ""
-
-    working = normalized.replace("&", " and ")
-    segments = [segment.strip() for segment in working.split(",") if segment.strip()]
-    tokens: List[str] = []
-
-    if segments:
-        for segment in segments:
-            parts = [part.strip() for part in re.split(r"\band\b", segment, flags=re.IGNORECASE) if part.strip()]
-            if parts:
-                tokens.extend(parts)
-            else:
-                tokens.append(segment)
-    else:
-        parts = [part.strip() for part in re.split(r"\band\b", working, flags=re.IGNORECASE) if part.strip()]
-        tokens.extend(parts or [normalized])
-
-    cleaned = [token for token in tokens if token and token.casefold() not in {"unknown", "various"}]
-    if not cleaned:
-        return ""
-    if len(cleaned) == 1:
-        return f"By {cleaned[0]}"
-    if len(cleaned) == 2:
-        return f"By {cleaned[0]} and {cleaned[1]}"
-    return f"By {', '.join(cleaned[:-1])}, and {cleaned[-1]}"
-
-
-def ensure_sentence(text: str) -> str:
-    cleaned = text.strip()
-    if not cleaned:
-        return ""
-    if cleaned[-1] in ".!?":
-        return cleaned
-    return f"{cleaned}."
-
-
-def normalize_series_number(value: Any) -> Optional[str]:
-    text = str(value or "").strip()
-    if not text:
-        return None
-    candidate = text.replace(",", ".")
-    if candidate.replace(".", "", 1).isdigit():
-        if "." in candidate:
-            normalized = candidate.rstrip("0").rstrip(".")
-            return normalized or "0"
-        try:
-            return str(int(candidate))
-        except ValueError:
-            pass
-    match = _SERIES_NUMBER_RE.search(candidate)
-    if not match:
-        return None
-    normalized = match.group(0)
-    if "." in normalized:
-        normalized = normalized.rstrip("0").rstrip(".")
-        return normalized or "0"
-    try:
-        return str(int(normalized))
-    except ValueError:
-        return normalized
-
-
-def extract_series_metadata(values: Mapping[str, str]) -> Tuple[Optional[str], Optional[str]]:
-    series_name: Optional[str] = None
-    for key in _SERIES_NAME_KEYS:
-        raw = values.get(key)
-        if raw:
-            cleaned = str(raw).strip()
-            if cleaned:
-                series_name = cleaned
-                break
-
-    series_number: Optional[str] = None
-    for key in _SERIES_NUMBER_KEYS:
-        raw = values.get(key)
-        if raw is None:
-            continue
-        normalized = normalize_series_number(raw)
-        if normalized:
-            series_number = normalized
-            break
-
-    return series_name, series_number
-
-
-def format_series_sentence(series_name: Optional[str], series_number: Optional[str]) -> str:
-    if not series_name or not series_number:
-        return ""
-    name = series_name.strip()
-    number = series_number.strip()
-    if not name or not number:
-        return ""
-    article = "the " if not name.lower().startswith("the ") else ""
-    phrase = f"Book {number} of {article}{name}"
-    return re.sub(r"\s+", " ", phrase).strip()
-
-
-_PEOPLE_SPLIT_RE = re.compile(r"[;,/&]|\band\b", re.IGNORECASE)
-_LIST_SPLIT_RE = re.compile(r"[;,\n]")
-_SERIES_SEQUENCE_TAG_KEYS: Tuple[str, ...] = (
-    "series_index",
-    "series_position",
-    "series_sequence",
-    "series_number",
-    "seriesnumber",
-    "book_number",
-    "booknumber",
-)
-
-
-def normalize_metadata_casefold(values: Optional[Mapping[str, Any]]) -> Dict[str, Any]:
-    normalized: Dict[str, Any] = {}
-    if not values:
-        return normalized
-    for key, value in values.items():
-        if value is None:
-            continue
-        key_text = str(key).strip().lower()
-        if not key_text:
-            continue
-        if isinstance(value, (list, tuple, set)):
-            normalized[key_text] = value
-        else:
-            text = str(value).strip()
-            if text:
-                normalized[key_text] = text
-    return normalized
-
-
-def split_people_field(raw: Any) -> List[str]:
-    if raw is None:
-        return []
-    if isinstance(raw, (list, tuple, set)):
-        results: List[str] = []
-        for item in raw:
-            results.extend(split_people_field(item))
-        return results
-    text = str(raw or "").strip()
-    if not text:
-        return []
-    tokens = [_token.strip() for _token in _PEOPLE_SPLIT_RE.split(text) if _token.strip()]
-    seen: set[str] = set()
-    ordered: List[str] = []
-    for token in tokens:
-        key = token.casefold()
-        if key in seen:
-            continue
-        seen.add(key)
-        ordered.append(token)
-    return ordered
-
-
-def split_simple_list(raw: Any) -> List[str]:
-    if raw is None:
-        return []
-    if isinstance(raw, (list, tuple, set)):
-        results: List[str] = []
-        for item in raw:
-            results.extend(split_simple_list(item))
-        return results
-    text = str(raw or "").strip()
-    if not text:
-        return []
-    tokens = [_token.strip() for _token in _LIST_SPLIT_RE.split(text) if _token.strip()]
-    seen: set[str] = set()
-    ordered: List[str] = []
-    for token in tokens:
-        key = token.casefold()
-        if key in seen:
-            continue
-        seen.add(key)
-        ordered.append(token)
-    return ordered
-
-
-def first_nonempty(*values: Any) -> Optional[str]:
-    for value in values:
-        if value is None:
-            continue
-        if isinstance(value, (list, tuple, set)):
-            items = list(value)
-            if not items:
-                continue
-            value = items[0]
-        text = str(value).strip()
-        if text:
-            return text
-    return None
-
-
-def extract_year(raw: Optional[str]) -> Optional[int]:
-    if not raw:
-        return None
-    text = str(raw).strip()
-    if not text:
-        return None
-    match = re.search(r"(19|20)\d{2}", text)
-    if match:
-        try:
-            return int(match.group(0))
-        except ValueError:
-            return None
-    try:
-        parsed = int(text)
-    except ValueError:
-        return None
-    if 0 < parsed < 3000:
-        return parsed
-    return None
-
-
-def normalize_series_sequence(raw: Any) -> Optional[str]:
-    if raw is None:
-        return None
-    if isinstance(raw, (int, float)):
-        if isinstance(raw, float) and (math.isnan(raw) or math.isinf(raw)):
-            return None
-        text = str(raw)
-    else:
-        text = str(raw).strip()
-    if not text:
-        return None
-    candidate = text.replace(",", ".")
-    match = _SERIES_NUMBER_RE.search(candidate)
-    if not match:
-        return None
-    normalized = match.group(0)
-    if "." in normalized:
-        normalized = normalized.rstrip("0").rstrip(".")
-        if not normalized:
-            normalized = "0"
-        return normalized
-    try:
-        return str(int(normalized))
-    except ValueError:
-        cleaned = normalized.lstrip("0")
-        return cleaned or "0"
-
-
-def build_audiobookshelf_metadata(
-    tags: Mapping[str, Any],
-    *,
-    language: str = "",
-    filename: str = "",
-) -> Dict[str, Any]:
-    normalized = normalize_metadata_casefold(tags)
-    title = first_nonempty(
-        normalized.get("title"),
-        normalized.get("book_title"),
-        normalized.get("name"),
-        normalized.get("album"),
-        filename,
-    )
-    authors = split_people_field(
-        normalized.get("authors")
-        or normalized.get("author")
-        or normalized.get("album_artist")
-        or normalized.get("artist")
-    )
-    narrators = split_people_field(normalized.get("narrators") or normalized.get("narrator"))
-    description = first_nonempty(
-        normalized.get("description"), normalized.get("summary"), normalized.get("comment")
-    )
-    genres = split_simple_list(normalized.get("genre"))
-    keywords = split_simple_list(normalized.get("tags") or normalized.get("keywords"))
-    lang = first_nonempty(normalized.get("language"), normalized.get("lang")) or language or ""
-    series_name = first_nonempty(
-        normalized.get("series"),
-        normalized.get("series_name"),
-        normalized.get("seriesname"),
-        normalized.get("series_title"),
-        normalized.get("seriestitle"),
-    )
-
-    series_sequence = None
-    for key in _SERIES_SEQUENCE_TAG_KEYS:
-        raw_value = normalized.get(key)
-        seq = normalize_series_sequence(raw_value)
-        if seq:
-            series_sequence = seq
-            break
-    if not series_name:
-        series_sequence = None
-
-    data: Dict[str, Any] = {
-        "title": title,
-        "subtitle": normalized.get("subtitle"),
-        "authors": authors,
-        "narrators": narrators,
-        "description": description,
-        "publisher": normalized.get("publisher"),
-        "genres": genres,
-        "tags": keywords,
-        "language": lang,
-        "publishedYear": extract_year(
-            normalized.get("published")
-            or normalized.get("publication_year")
-            or normalized.get("date")
-            or normalized.get("year")
-        ),
-        "seriesName": series_name,
-        "seriesSequence": series_sequence,
-        "isbn": first_nonempty(normalized.get("isbn"), normalized.get("asin")),
-    }
-    published_date = first_nonempty(
-        normalized.get("published"), normalized.get("publication_date"), normalized.get("date")
-    )
-    if published_date:
-        data["publishedDate"] = published_date
-
-    rating_text = first_nonempty(normalized.get("rating"), normalized.get("my_rating"))
-    if rating_text:
-        try:
-            data["rating"] = float(str(rating_text).strip())
-        except ValueError:
-            pass
-        rating_max_text = first_nonempty(
-            normalized.get("rating_max"), normalized.get("rating_scale")
-        )
-        if rating_max_text:
-            try:
-                data["ratingMax"] = float(str(rating_max_text).strip())
-            except ValueError:
-                pass
-
-    cleaned: Dict[str, Any] = {}
-    for key, value in data.items():
-        if value is None:
-            continue
-        if isinstance(value, str) and not value.strip():
-            continue
-        if isinstance(value, (list, tuple)) and not value:
-            continue
-        cleaned[key] = value
-    return cleaned
-
-
-def load_audiobookshelf_chapters(
-    metadata_path: Path,
-) -> Optional[List[Dict[str, Any]]]:
-    if not metadata_path.exists():
-        return None
-    try:
-        payload = json.loads(metadata_path.read_text(encoding="utf-8"))
-    except (OSError, json.JSONDecodeError):
-        return None
-    chapters = payload.get("chapters")
-    if not isinstance(chapters, list):
-        return None
-    cleaned: List[Dict[str, Any]] = []
-    for entry in chapters:
-        if not isinstance(entry, Mapping):
-            continue
-        title = first_nonempty(entry.get("title"), entry.get("original_title"))
-        start = entry.get("start")
-        end = entry.get("end")
-        if title and start is not None and end is not None:
-            cleaned.append({"title": str(title), "start": start, "end": end})
-    return cleaned or None

abogen/domain/metadata_merge.py

@@ -1,23 +0,0 @@
-from __future__ import annotations
-
-from typing import Any, Dict, Optional
-
-
-def merge_metadata(
-    extracted: Optional[Dict[str, Any]],
-    overrides: Optional[Dict[str, Any]],
-) -> Dict[str, str]:
-    merged: Dict[str, str] = {}
-    if extracted:
-        for key, value in extracted.items():
-            if value is None:
-                continue
-            merged[str(key)] = str(value)
-    if overrides:
-        for key, value in overrides.items():
-            key_str = str(key)
-            if value is None:
-                merged.pop(key_str, None)
-            else:
-                merged[key_str] = str(value)
-    return merged

abogen/domain/metadata_overrides.py

@@ -1,99 +0,0 @@
-"""OPDS metadata normalization.
-
-Normalizes metadata keys from various OPDS/Calibre sources into
-a canonical set of overrides for the audiobook conversion pipeline.
-"""
-
-from __future__ import annotations
-
-from typing import Any, Dict, Mapping
-
-
-def normalize_opds_metadata(metadata_payload: Mapping[str, Any]) -> Dict[str, Any]:
-    """Normalize OPDS/Calibre metadata into canonical override keys.
-
-    Takes a metadata payload with various key aliases (e.g. 'series'/'series_name',
-    'tags'/'keywords', 'authors'/'creator') and returns a dict with canonical
-    keys set.
-
-    Args:
-        metadata_payload: Raw metadata dict from OPDS/Calibre import.
-
-    Returns:
-        Dict with canonical metadata keys (series, series_index, tags,
-        description, subtitle, publisher, authors).
-    """
-    metadata_overrides: Dict[str, Any] = {}
-
-    def _stringify(value: Any) -> str:
-        if value is None:
-            return ""
-        if isinstance(value, (list, tuple, set)):
-            parts = [str(item).strip() for item in value if item is not None]
-            return ", ".join(part for part in parts if part)
-        return str(value).strip()
-
-    raw_series = metadata_payload.get("series") or metadata_payload.get("series_name")
-    series_name = str(raw_series or "").strip()
-    if series_name:
-        metadata_overrides["series"] = series_name
-        metadata_overrides.setdefault("series_name", series_name)
-
-    series_index_value = (
-        metadata_payload.get("series_index")
-        or metadata_payload.get("series_position")
-        or metadata_payload.get("series_sequence")
-        or metadata_payload.get("book_number")
-    )
-    if series_index_value is not None:
-        series_index_text = str(series_index_value).strip()
-        if series_index_text:
-            metadata_overrides.setdefault("series_index", series_index_text)
-            metadata_overrides.setdefault("series_position", series_index_text)
-            metadata_overrides.setdefault("series_sequence", series_index_text)
-            metadata_overrides.setdefault("book_number", series_index_text)
-
-    tags_value = metadata_payload.get("tags") or metadata_payload.get("keywords")
-    if tags_value:
-        tags_text = _stringify(tags_value)
-        if tags_text:
-            metadata_overrides.setdefault("tags", tags_text)
-            metadata_overrides.setdefault("keywords", tags_text)
-            metadata_overrides.setdefault("genre", tags_text)
-
-    description_value = metadata_payload.get("description") or metadata_payload.get("summary")
-    if description_value:
-        description_text = _stringify(description_value)
-        if description_text:
-            metadata_overrides.setdefault("description", description_text)
-            metadata_overrides.setdefault("summary", description_text)
-
-    subtitle_value = (
-        metadata_payload.get("subtitle")
-        or metadata_payload.get("sub_title")
-        or metadata_payload.get("calibre_subtitle")
-    )
-    if subtitle_value:
-        subtitle_text = _stringify(subtitle_value)
-        if subtitle_text:
-            metadata_overrides.setdefault("subtitle", subtitle_text)
-
-    publisher_value = metadata_payload.get("publisher")
-    if publisher_value:
-        publisher_text = _stringify(publisher_value)
-        if publisher_text:
-            metadata_overrides.setdefault("publisher", publisher_text)
-
-    authors_value = (
-        metadata_payload.get("authors")
-        or metadata_payload.get("author")
-        or metadata_payload.get("creator")
-        or metadata_payload.get("dc_creator")
-    )
-    if authors_value:
-        authors_text = _stringify(authors_value)
-        if authors_text:
-            metadata_overrides.setdefault("authors", authors_text)
-            metadata_overrides.setdefault("author", authors_text)
-
-    return metadata_overrides

abogen/domain/normalization.py

@@ -1,125 +0,0 @@
-"""Text normalization convenience helpers.
-
-Provides both the simple ``normalize_text_for_pipeline`` (apostrophe + LLM only)
-and the comprehensive ``prepare_text_for_tts`` that chains all three normalization
-stages used during conversion: heteronym rules → pronunciation rules → pipeline
-normalization.  The latter is the single entry point that both the Web UI and
-PyQt Desktop GUI should use.
-
-Also provides ``TTSContext`` — a dataclass bundling all pre-compiled normalization
-resources so they can be created once and passed as a single object.
-"""
-
-from __future__ import annotations
-
-from dataclasses import dataclass, field
-from typing import Any, Dict, List, Mapping, Optional
-
-from abogen.kokoro_text_normalization import (
-    ApostropheConfig,
-    normalize_for_pipeline as _normalize_for_pipeline,
-)
-from abogen.normalization_settings import (
-    build_apostrophe_config,
-    get_runtime_settings,
-    apply_overrides as _apply_overrides,
-)
-
-_BASE_APOSTROPHE_CONFIG = ApostropheConfig()
-
-
-@dataclass
-class TTSContext:
-    """Bundles pre-compiled normalization resources for TTS processing.
-
-    Created once per conversion job and passed to ``prepare_text_for_tts``
-    instead of threading 5 separate parameters.
-    """
-
-    split_pattern: str = r"(?<=[.!?\-])\s+"
-    pronunciation_rules: Optional[List[Dict[str, Any]]] = None
-    heteronym_rules: Optional[List[Dict[str, Any]]] = None
-    normalization_overrides: Optional[Mapping[str, Any]] = None
-    usage_counter: Dict[str, int] = field(default_factory=dict)
-
-    def normalize(self, text: str) -> str:
-        """Shorthand: normalize text using this context's compiled rules."""
-        return prepare_text_for_tts(
-            text,
-            heteronym_rules=self.heteronym_rules,
-            pronunciation_rules=self.pronunciation_rules,
-            normalization_overrides=self.normalization_overrides,
-            usage_counter=self.usage_counter,
-        )
-
-
-def normalize_text_for_pipeline(
-    text: str,
-    *,
-    normalization_overrides: Optional[Mapping[str, Any]] = None,
-) -> str:
-    """Normalize text using runtime settings with optional overrides."""
-    runtime_settings = get_runtime_settings()
-    if normalization_overrides:
-        runtime_settings = _apply_overrides(runtime_settings, normalization_overrides)
-    apostrophe_config = build_apostrophe_config(settings=runtime_settings, base=_BASE_APOSTROPHE_CONFIG)
-    return _normalize_for_pipeline(text, config=apostrophe_config, settings=runtime_settings)
-
-
-def prepare_text_for_tts(
-    text: str,
-    *,
-    heteronym_rules: Optional[List[Dict[str, Any]]] = None,
-    pronunciation_rules: Optional[List[Dict[str, Any]]] = None,
-    normalization_overrides: Optional[Mapping[str, Any]] = None,
-    usage_counter: Optional[Dict[str, int]] = None,
-) -> str:
-    """Apply the full text normalization pipeline before TTS synthesis.
-
-    Chains three stages in order:
-      1. Heteronym sentence rules (context-dependent pronunciation)
-      2. Pronunciation rules (token-level replacements)
-      3. Pipeline normalization (apostrophe handling, LLM normalization)
-
-    This is the **single entry point** that both the Web UI conversion runner
-    and the PyQt conversion thread should call before passing text to the TTS
-    backend.
-
-    Parameters
-    ----------
-    text:
-        Raw text to normalize.
-    heteronym_rules:
-        Compiled heteronym rules from ``compile_heteronym_sentence_rules``.
-    pronunciation_rules:
-        Compiled pronunciation rules from ``compile_pronunciation_rules``.
-    normalization_overrides:
-        User-level overrides for normalization settings (apostrophe mode, etc.).
-    usage_counter:
-        Mutable dict that tracks how many times each pronunciation override was
-        applied.  Passed through to ``apply_pronunciation_rules``.
-
-    Returns
-    -------
-    str
-        Fully normalized text ready for TTS.
-    """
-    from abogen.domain.pronunciation import (
-        apply_heteronym_sentence_rules,
-        apply_pronunciation_rules,
-    )
-
-    result = str(text or "")
-
-    if heteronym_rules:
-        result = apply_heteronym_sentence_rules(result, heteronym_rules)
-
-    if pronunciation_rules:
-        result = apply_pronunciation_rules(result, pronunciation_rules, usage_counter)
-
-    runtime_settings = get_runtime_settings()
-    if normalization_overrides:
-        runtime_settings = _apply_overrides(runtime_settings, normalization_overrides)
-    apostrophe_config = build_apostrophe_config(settings=runtime_settings, base=_BASE_APOSTROPHE_CONFIG)
-
-    return _normalize_for_pipeline(result, config=apostrophe_config, settings=runtime_settings)

abogen/domain/output_paths.py

@@ -1,183 +0,0 @@
-"""Output path resolution utilities.
-
-Pure functions for resolving output directories, building file paths,
-and computing project folder layouts.
-"""
-
-from __future__ import annotations
-
-import os
-import platform
-import re
-from datetime import datetime
-from pathlib import Path
-from typing import Any, Callable, List, Optional, Tuple
-
-from abogen.subtitle_utils import sanitize_name_for_os
-from abogen.text_extractor import ExtractedChapter
-
-
-_OUTPUT_SANITIZE_RE = re.compile(r"[^\w\-_.]+")
-
-# OS-specific illegal characters for filenames
-_WINDOWS_ILLEGAL_CHARS_RE = re.compile(r'[<>:"/\\|?*\x00-\x1f]')
-_UNIX_CONTROL_CHARS_RE = re.compile(r'[\x00-\x1f]')
-_RESERVED_NAMES = frozenset(
-    {"CON", "PRN", "AUX", "NUL"}
-    | {f"COM{i}" for i in range(1, 10)}
-    | {f"LPT{i}" for i in range(1, 10)}
-)
-
-
-def slugify(title: str, index: int) -> str:
-    sanitized = re.sub(r"[^\w\-]+", "_", title.lower()).strip("_")
-    if not sanitized:
-        sanitized = f"chapter_{index:02d}"
-    return sanitized[:80]
-
-
-def sanitize_filename_for_chapter(title: str, index: int, max_len: int = 80) -> str:
-    """Sanitize a chapter name for use as a filename component.
-
-    Combines character sanitization, OS safety, and smart truncation
-    at word boundaries. Prepends zero-padded index prefix.
-
-    Args:
-        title: Raw chapter title.
-        index: 1-based chapter number for prefix.
-        max_len: Maximum length of the sanitized portion (excluding prefix).
-
-    Returns:
-        Sanitized string like "01_the_beginning".
-    """
-    # Remove non-word/non-space/non-hyphen chars, then collapse spaces/hyphens
-    sanitized = re.sub(r"[^\w\s\-]", "", title)
-    sanitized = re.sub(r"[\s\-]+", "_", sanitized).strip("_")
-
-    if not sanitized:
-        sanitized = f"chapter_{index:02d}"
-
-    # OS-specific sanitization
-    system = platform.system()
-    if system == "Windows":
-        sanitized = _WINDOWS_ILLEGAL_CHARS_RE.sub("_", sanitized)
-        sanitized = sanitized.rstrip(". ")
-        base = sanitized.split(".")[0].upper()
-        if base in _RESERVED_NAMES:
-            sanitized = f"_{sanitized}"
-    # Linux: only NUL is truly illegal, but control chars are problematic
-    sanitized = _UNIX_CONTROL_CHARS_RE.sub("_", sanitized)
-
-    # Smart truncation at word boundary
-    if len(sanitized) > max_len:
-        pos = sanitized[:max_len].rfind("_")
-        sanitized = sanitized[: pos if pos > 0 else max_len].rstrip("_")
-
-    return f"{index:02d}_{sanitized}"
-
-
-def sanitize_output_stem(name: str, index: int = 0) -> str:
-    base = Path(name or "").stem
-    sanitized = _OUTPUT_SANITIZE_RE.sub("_", base).strip("_")
-    return sanitized or "output"
-
-
-def output_timestamp_token() -> str:
-    return datetime.now().strftime("%Y%m%d-%H%M%S")
-
-
-def build_output_path(directory: Path, original_name: str, extension: str) -> Path:
-    sanitized = sanitize_output_stem(original_name)
-    return directory / f"{sanitized}.{extension}"
-
-
-def apply_newline_policy(chapters: List[ExtractedChapter], replace_single_newlines: bool) -> None:
-    if not replace_single_newlines:
-        return
-    newline_regex = re.compile(r"(?<!\n)\n(?!\n)")
-    for chapter in chapters:
-        chapter.text = newline_regex.sub(" ", chapter.text)
-
-
-from abogen.domain.enums import SaveMode
-
-
-def resolve_output_directory(
-    *,
-    save_mode: str,
-    stored_path: Path,
-    output_folder: Optional[str],
-    desktop_dir: Optional[Path],
-    user_output_path: Optional[Path],
-    user_cache_outputs: Optional[Path],
-) -> Path:
-    if save_mode in (SaveMode.SAVE_TO_DESKTOP, "Save to Desktop") and desktop_dir:
-        return desktop_dir
-    if save_mode in (SaveMode.SAVE_NEXT_TO_INPUT, "Save next to input file"):
-        return stored_path.parent
-    if save_mode in (SaveMode.CHOOSE_OUTPUT_FOLDER, "Choose output folder") and output_folder:
-        return Path(output_folder)
-    if save_mode in (SaveMode.DEFAULT_OUTPUT, "Use default save location") and user_output_path:
-        return user_output_path
-    return user_cache_outputs or Path(".")
-
-
-def resolve_project_layout(
-    *,
-    original_filename: str,
-    save_as_project: bool,
-    base_dir: Path,
-    timestamp_fn: Callable[[], str] = output_timestamp_token,
-    sanitize_fn: Callable[[str, int], str] = sanitize_output_stem,
-) -> Tuple[Path, Path, Path, Optional[Path]]:
-    sanitized = sanitize_fn(original_filename, 0)
-    folder_name = f"{timestamp_fn()}_{sanitized}"
-    project_root = base_dir / folder_name
-    project_root.mkdir(parents=True, exist_ok=True)
-
-    if save_as_project:
-        audio_dir = project_root / "audio"
-        subtitle_dir = project_root / "subtitles"
-        metadata_dir = project_root / "metadata"
-        for directory in (audio_dir, subtitle_dir, metadata_dir):
-            directory.mkdir(parents=True, exist_ok=True)
-        return project_root, audio_dir, subtitle_dir, metadata_dir
-
-    return project_root, project_root, project_root, None
-
-
-def resolve_unique_path(
-    parent_dir: str,
-    base_name: str,
-    extension: str,
-    allowed_extensions: Optional[set] = None,
-) -> str:
-    """Find a unique file path by appending _2, _3, etc. on collision.
-
-    Args:
-        parent_dir: Directory to check for collisions.
-        base_name: Base filename (without extension).
-        extension: File extension (without dot).
-        allowed_extensions: Set of extensions to check against.
-            If None, checks any existing file/dir with same name.
-
-    Returns:
-        Full path without extension (e.g. "/path/to/name_2").
-    """
-    sanitized = sanitize_name_for_os(base_name, is_folder=True)
-    counter = 1
-    while True:
-        suffix = f"_{counter}" if counter > 1 else ""
-        candidate = os.path.join(parent_dir, f"{sanitized}{suffix}")
-        if allowed_extensions is not None:
-            file_parts = (os.path.splitext(f) for f in os.listdir(parent_dir))
-            clash = any(
-                name == f"{sanitized}{suffix}"
-                and ext[1:].lower() in allowed_extensions
-                for name, ext in file_parts
-            )
-        else:
-            clash = os.path.exists(candidate)
-        if not clash:
-            return candidate
-        counter += 1

abogen/domain/pipeline_factory.py

@@ -1,128 +0,0 @@
-"""Pipeline creation, caching and lifecycle management.
-
-Provides a unified interface for creating and managing TTS pipelines
-across all UI layers (WebUI, PyQt, CLI).
-"""
-
-from __future__ import annotations
-
-from typing import Any, Dict, Optional
-
-from abogen.domain.device import select_device
-from abogen.domain.enums import Language
-from abogen.domain.voice_resolution import initialize_voice_cache
-from abogen.tts_plugin.utils import create_pipeline, is_plugin_registered
-
-# Kokoro-specific language mapping (engine's responsibility)
-_KOKORO_LANG_MAP = {
-    Language.EN_US: "a",
-    Language.EN_GB: "b",
-    Language.ES: "e",
-    Language.FR: "f",
-    Language.HI: "h",
-    Language.IT: "i",
-    Language.JA: "j",
-    Language.PT_BR: "p",
-    Language.ZH: "z",
-}
-
-
-def resolve_device(use_gpu: bool) -> str:
-    """Determine compute device from job and global config flags."""
-    from abogen.utils import load_config
-
-    cfg = load_config()
-    if use_gpu and cfg.get("use_gpu", True):
-        return select_device()
-    return "cpu"
-
-
-def create_pipeline_for_job(
-    provider: str,
-    language: str,
-    use_gpu: bool,
-) -> Any:
-    """Create a TTS pipeline with proper device selection.
-
-    Handles provider validation, GPU decision, and plugin checks.
-    """
-    provider = str(provider or "kokoro").strip().lower() or "kokoro"
-    if not is_plugin_registered(provider):
-        provider = "kokoro"
-
-    # Convert Language enum to Kokoro single-letter code
-    try:
-        lang = Language.from_str(language) if not isinstance(language, Language) else language
-    except ValueError:
-        lang = Language.EN_US  # fallback for unknown languages
-    kokoro_code = _KOKORO_LANG_MAP.get(lang, "a")
-
-    if provider == "supertonic":
-        return create_pipeline("supertonic")
-
-    device = resolve_device(use_gpu)
-    return create_pipeline("kokoro", lang_code=kokoro_code, device=device)
-
-
-def dispose_pipelines(pipelines: Dict[str, Any]) -> None:
-    """Dispose all pipelines in a dict and clear it."""
-    for p in pipelines.values():
-        try:
-            p.dispose()
-        except Exception:
-            pass
-    pipelines.clear()
-
-
-class PipelinePool:
-    """Cache and manage TTS pipelines by provider.
-
-    Usage::
-
-        pool = PipelinePool()
-        backend = pool.get("kokoro", "en", use_gpu=True)
-        # ... use backend ...
-        pool.dispose_all()
-    """
-
-    def __init__(self) -> None:
-        self._pipelines: Dict[str, Any] = {}
-        self._voice_cache_initialized = False
-
-    def get(
-        self,
-        provider: str,
-        language: str,
-        use_gpu: bool,
-        *,
-        job: Any = None,
-    ) -> Any:
-        """Get or create a cached pipeline for the given provider.
-
-        Args:
-            provider: TTS provider name ("kokoro" or "supertonic").
-            language: Language code (for kokoro).
-            use_gpu: Whether GPU acceleration is requested.
-            job: Optional job object for voice cache initialization.
-        """
-        provider = str(provider or "kokoro").strip().lower() or "kokoro"
-        if not is_plugin_registered(provider):
-            provider = "kokoro"
-
-        existing = self._pipelines.get(provider)
-        if existing is not None:
-            return existing
-
-        pipeline = create_pipeline_for_job(provider, language, use_gpu)
-        self._pipelines[provider] = pipeline
-
-        if provider == "kokoro" and not self._voice_cache_initialized and job is not None:
-            initialize_voice_cache(job)
-            self._voice_cache_initialized = True
-
-        return pipeline
-
-    def dispose_all(self) -> None:
-        """Dispose all cached pipelines."""
-        dispose_pipelines(self._pipelines)
-        self._voice_cache_initialized = False

abogen/domain/progress.py

@@ -1,72 +0,0 @@
-from __future__ import annotations
-
-"""Progress and ETR (estimated time remaining) calculation.
-
-Shared by Web UI and PyQt desktop GUI. Pure math, no UI dependencies.
-"""
-import time
-from dataclasses import dataclass, field
-
-
-@dataclass
-class ProgressTracker:
-    """Tracks character-based progress with ETR calculation.
-
-    Usage:
-        tracker = ProgressTracker(total_chars=50000)
-        # ... as processing occurs:
-        tracker.update(chars_done=5000)
-        print(tracker.etr_str)   # "00:04:30"
-        print(tracker.percent)   # 10
-    """
-    total_chars: int
-    _start_time: float = field(default_factory=time.time, repr=False)
-    _chars_done: int = field(default=0, repr=False)
-
-    def update(self, chars_done: int) -> None:
-        self._chars_done = chars_done
-
-    @property
-    def percent(self) -> int:
-        if self.total_chars <= 0:
-            return 0
-        return min(int(self._chars_done / self.total_chars * 100), 99)
-
-    @property
-    def etr_str(self) -> str:
-        elapsed = time.time() - self._start_time
-        if self._chars_done <= 0 or elapsed <= 0.5:
-            return "Processing..."
-        avg_time_per_char = elapsed / self._chars_done
-        remaining = self.total_chars - self._chars_done
-        if remaining <= 0:
-            return "00:00:00"
-        secs = avg_time_per_char * remaining
-        h = int(secs // 3600)
-        m = int((secs % 3600) // 60)
-        s = int(secs % 60)
-        return f"{h:02d}:{m:02d}:{s:02d}"
-
-
-def calc_etr_str(elapsed: float, done: int, total: int) -> str:
-    """Standalone ETR string calculation (matches PyQt original logic).
-
-    Args:
-        elapsed: seconds since processing started
-        done: items/characters processed so far
-        total: total items/characters to process
-
-    Returns:
-        ETR string like "01:23:45" or "Processing..."
-    """
-    if done <= 0 or elapsed <= 0.5:
-        return "Processing..."
-    avg_time_per_item = elapsed / done
-    remaining = total - done
-    if remaining <= 0:
-        return "00:00:00"
-    secs = avg_time_per_item * remaining
-    h = int(secs // 3600)
-    m = int((secs % 3600) // 60)
-    s = int(secs % 60)
-    return f"{h:02d}:{m:02d}:{s:02d}"

abogen/domain/pronunciation.py

@@ -1,261 +0,0 @@
-"""Pronunciation rule compilation and application.
-
-Pure functions for compiling token-level and sentence-level pronunciation
-overrides into regex patterns, applying them to text, and merging multiple
-override sources with precedence rules.
-"""
-
-from __future__ import annotations
-
-import re
-from typing import Any, Dict, Iterable, List, Mapping, Optional
-
-from abogen.entity_analysis import normalize_token as normalize_entity_token
-from abogen.entity_analysis import normalize_manual_override_token
-
-
-def compile_pronunciation_rules(
-    overrides: Optional[Iterable[Mapping[str, Any]]],
-) -> List[Dict[str, Any]]:
-    if not overrides:
-        return []
-
-    candidates: List[Dict[str, Any]] = []
-    seen: set[str] = set()
-
-    for entry in overrides:
-        if not isinstance(entry, Mapping):
-            continue
-        pronunciation_value = str(entry.get("pronunciation") or "").strip()
-        if not pronunciation_value:
-            continue
-
-        token_values: List[str] = []
-        token_raw = entry.get("token")
-        if token_raw:
-            token_value = str(token_raw).strip()
-            if token_value:
-                token_values.append(token_value)
-        normalized_raw = entry.get("normalized")
-        if normalized_raw:
-            normalized_value = str(normalized_raw).strip()
-            if normalized_value:
-                token_values.append(normalized_value)
-        if token_raw and not token_values:
-            fallback = normalize_entity_token(str(token_raw))
-            if fallback:
-                token_values.append(fallback)
-
-        if not token_values:
-            continue
-
-        usage_normalized = str(entry.get("normalized") or "").strip()
-        if not usage_normalized and token_values:
-            usage_normalized = normalize_entity_token(token_values[0]) or token_values[0]
-        usage_token = str(entry.get("token") or token_values[0])
-
-        for token_value in token_values:
-            key = token_value.casefold()
-            if key in seen:
-                continue
-            seen.add(key)
-            candidates.append(
-                {
-                    "token": token_value,
-                    "normalized": usage_normalized,
-                    "replacement": pronunciation_value,
-                }
-            )
-
-    if not candidates:
-        return []
-
-    candidates.sort(key=lambda item: len(item["token"]), reverse=True)
-    compiled: List[Dict[str, Any]] = []
-    for candidate in candidates:
-        token_value = candidate["token"]
-        pronunciation_value = candidate["replacement"]
-        escaped = re.escape(token_value)
-        pattern = re.compile(rf"(?i)(?<!\w){escaped}(?P<possessive>'s|\u2019s|\u2019)?(?!\w)")
-        compiled.append(
-            {
-                "pattern": pattern,
-                "replacement": pronunciation_value,
-                "normalized": candidate.get("normalized") or token_value,
-                "token": candidate.get("token") or token_value,
-            }
-        )
-
-    return compiled
-
-
-def compile_heteronym_sentence_rules(
-    overrides: Optional[Iterable[Mapping[str, Any]]],
-) -> List[Dict[str, Any]]:
-    if not overrides:
-        return []
-
-    compiled: List[Dict[str, Any]] = []
-    seen: set[str] = set()
-
-    for entry in overrides:
-        if not isinstance(entry, Mapping):
-            continue
-        sentence = str(entry.get("sentence") or "").strip()
-        if not sentence:
-            continue
-        choice = str(entry.get("choice") or "").strip()
-        if not choice:
-            continue
-
-        replacement_sentence = ""
-        options = entry.get("options")
-        if isinstance(options, list):
-            for opt in options:
-                if not isinstance(opt, Mapping):
-                    continue
-                if str(opt.get("key") or "").strip() == choice:
-                    replacement_sentence = str(opt.get("replacement_sentence") or "").strip()
-                    break
-        if not replacement_sentence:
-            continue
-
-        rule_key = f"{sentence}\n{choice}".casefold()
-        if rule_key in seen:
-            continue
-        seen.add(rule_key)
-
-        parts = [p for p in re.split(r"\s+", sentence) if p]
-        if not parts:
-            continue
-        pattern_text = r"\s+".join(re.escape(p) for p in parts)
-        pattern = re.compile(pattern_text)
-        compiled.append({"pattern": pattern, "replacement": replacement_sentence})
-
-    compiled.sort(key=lambda item: len(item["pattern"].pattern), reverse=True)
-    return compiled
-
-
-def apply_heteronym_sentence_rules(text: str, rules: List[Dict[str, Any]]) -> str:
-    if not text or not rules:
-        return text
-    result = text
-    for rule in rules:
-        pattern = rule["pattern"]
-        replacement = rule["replacement"]
-        result = pattern.sub(replacement, result)
-    return result
-
-
-def apply_pronunciation_rules(
-    text: str,
-    rules: List[Dict[str, Any]],
-    usage_counter: Optional[Dict[str, int]] = None,
-) -> str:
-    if not text or not rules:
-        return text
-
-    result = text
-    for rule in rules:
-        pattern = rule["pattern"]
-        pronunciation_value = rule["replacement"]
-        usage_key = str(rule.get("normalized") or "").strip()
-
-        def _replacement(match: re.Match[str]) -> str:
-            suffix = match.group("possessive") or ""
-            if usage_counter is not None and usage_key:
-                usage_counter[usage_key] = usage_counter.get(usage_key, 0) + 1
-            return pronunciation_value + suffix
-
-        result = pattern.sub(_replacement, result)
-
-    return result
-
-
-def merge_pronunciation_overrides(job: Any) -> List[Dict[str, Any]]:
-    """Return pronunciation override entries, ensuring manual overrides are included.
-
-    Pending jobs keep both ``manual_overrides`` and ``pronunciation_overrides``, but the
-    latter can be stale if the UI didn't resync before enqueue. During conversion,
-    we must merge manual overrides so they always apply (before TTS).
-
-    Precedence: manual overrides win over existing entries for the same normalized key.
-    """
-
-    collected: Dict[str, Dict[str, Any]] = {}
-
-    existing = getattr(job, "pronunciation_overrides", None)
-    if isinstance(existing, list):
-        for entry in existing:
-            if not isinstance(entry, Mapping):
-                continue
-            token_value = str(entry.get("token") or "").strip()
-            pronunciation_value = str(entry.get("pronunciation") or "").strip()
-            if not token_value or not pronunciation_value:
-                continue
-            normalized = str(entry.get("normalized") or "").strip() or normalize_entity_token(token_value)
-            if not normalized:
-                continue
-            collected[normalized] = {
-                "token": token_value,
-                "normalized": normalized,
-                "pronunciation": pronunciation_value,
-                "voice": str(entry.get("voice") or "").strip() or None,
-                "notes": str(entry.get("notes") or "").strip() or None,
-                "context": str(entry.get("context") or "").strip() or None,
-                "source": str(entry.get("source") or "pronunciation"),
-                "language": getattr(job, "language", None),
-            }
-
-    speakers = getattr(job, "speakers", None)
-    if isinstance(speakers, dict):
-        for payload in speakers.values():
-            if not isinstance(payload, Mapping):
-                continue
-            token_value = str(payload.get("token") or "").strip()
-            pronunciation_value = str(payload.get("pronunciation") or "").strip()
-            if not token_value or not pronunciation_value:
-                continue
-            normalized = normalize_entity_token(token_value)
-            if not normalized:
-                continue
-            collected[normalized] = {
-                "token": token_value,
-                "normalized": normalized,
-                "pronunciation": pronunciation_value,
-                "voice": str(
-                    payload.get("resolved_voice")
-                    or payload.get("voice")
-                    or getattr(job, "voice", "")
-                ).strip()
-                or None,
-                "notes": None,
-                "context": None,
-                "source": "speaker",
-                "language": getattr(job, "language", None),
-            }
-
-    manual = getattr(job, "manual_overrides", None)
-    if isinstance(manual, list):
-        for entry in manual:
-            if not isinstance(entry, Mapping):
-                continue
-            token_value = str(entry.get("token") or "").strip()
-            pronunciation_value = str(entry.get("pronunciation") or "").strip()
-            if not token_value or not pronunciation_value:
-                continue
-            normalized = str(entry.get("normalized") or "").strip() or normalize_manual_override_token(token_value)
-            if not normalized:
-                continue
-            collected[normalized] = {
-                "token": token_value,
-                "normalized": normalized,
-                "pronunciation": pronunciation_value,
-                "voice": str(entry.get("voice") or "").strip() or None,
-                "notes": str(entry.get("notes") or "").strip() or None,
-                "context": str(entry.get("context") or "").strip() or None,
-                "source": str(entry.get("source") or "manual"),
-                "language": getattr(job, "language", None),
-            }
-
-    return list(collected.values())

abogen/domain/settings_core.py

@@ -1,580 +0,0 @@
-"""Shared settings core.
-
-Defines the SETTINGS_REGISTRY — the single source of truth for all settings.
-Every setting has a key, type, default, validation rules, and UI scope.
-Both Web UI and Desktop GUI must reference this registry.
-"""
-
-from __future__ import annotations
-
-import os
-import re
-from dataclasses import dataclass, field
-from typing import Any, Callable, Dict, Mapping, Optional, Sequence
-
-from abogen.constants import (
-    LANGUAGE_DESCRIPTIONS,
-    SUBTITLE_FORMATS,
-    SUPPORTED_SOUND_FORMATS,
-)
-from abogen.tts_plugin.utils import get_default_voice
-from abogen.normalization_settings import (
-    DEFAULT_LLM_PROMPT,
-    environment_llm_defaults,
-)
-
-
-# ── Schema ───────────────────────────────────────────────────────────
-
-@dataclass(frozen=True)
-class Setting:
-    """Contract for a single setting.
-
-    Attributes:
-        key: Config dict key (e.g. "output_format").
-        type_: Python type (bool, int, float, str, list).
-        default: Default value or callable returning one.
-        min_value: Minimum for numeric types.
-        max_value: Maximum for numeric types.
-        valid_values: Allowed values for str types (None = any).
-        gui_only: True if only used by PyQt Desktop GUI.
-        web_only: True if only used by Web UI.
-        normalizer: Optional callable(value, default) -> normalized_value.
-        description: Human-readable explanation.
-    """
-    key: str
-    type_: type
-    default: Any
-    min_value: float | None = None
-    max_value: float | None = None
-    valid_values: tuple[Any, ...] | None = None
-    gui_only: bool = False
-    web_only: bool = False
-    normalizer: Callable | None = None
-    description: str = ""
-
-    def coerce(self, value: Any, fallback: Any | None = None) -> Any:
-        """Coerce value to the declared type, returning fallback on failure."""
-        fb = fallback if fallback is not None else self.default
-        if self.type_ is bool:
-            if isinstance(value, bool):
-                return value
-            if isinstance(value, str):
-                return value.lower() in {"true", "1", "yes", "on"}
-            if value is None:
-                return fb
-            return bool(value)
-        if self.type_ is int:
-            try:
-                v = int(value)
-            except (TypeError, ValueError):
-                return fb
-            if self.min_value is not None:
-                v = max(int(self.min_value), v)
-            if self.max_value is not None:
-                v = min(int(self.max_value), v)
-            return v
-        if self.type_ is float:
-            try:
-                v = float(value)
-            except (TypeError, ValueError):
-                return fb
-            if self.min_value is not None:
-                v = max(self.min_value, v)
-            if self.max_value is not None:
-                v = min(self.max_value, v)
-            return v
-        if self.type_ is str:
-            if isinstance(value, str):
-                v = value.strip()
-                if self.valid_values and v not in self.valid_values:
-                    return fb
-                return v
-            return fb
-        if self.type_ is list:
-            if isinstance(value, (list, tuple, set)):
-                return list(value)
-            return fb
-        return value
-
-
-# ── Normalizers (used by Setting.normalizer) ─────────────────────────
-
-def _norm_save_mode(value: Any, default: str) -> str:
-    if isinstance(value, str):
-        if value in SAVE_MODE_LABELS:
-            return value
-        if value in LEGACY_SAVE_MODE_MAP:
-            return LEGACY_SAVE_MODE_MAP[value]
-    return default
-
-
-def _norm_voice_spec(value: Any, default: str) -> str:
-    if isinstance(value, str):
-        text = value.strip()
-        if not text:
-            return default
-        spec, profile_name = split_profile_spec(text)
-        if profile_name:
-            return f"speaker:{profile_name}"
-        return spec
-    return default
-
-
-def _norm_speaker_spec(value: Any, default: str) -> str:
-    if isinstance(value, str):
-        text = value.strip()
-        if not text:
-            return ""
-        spec, profile_name = split_profile_spec(text)
-        if profile_name:
-            return f"speaker:{profile_name}"
-        return spec
-    return ""
-
-
-def _norm_language_list(value: Any, default: list) -> list:
-    if isinstance(value, (list, tuple, set)):
-        return [code for code in value if isinstance(code, str) and code in LANGUAGE_DESCRIPTIONS]
-    if isinstance(value, str):
-        parts = [item.strip().lower() for item in value.split(",") if item.strip()]
-        return [code for code in parts if code in LANGUAGE_DESCRIPTIONS]
-    return default
-
-
-def _norm_stripped_str(value: Any, default: str) -> str:
-    return str(value or "").strip()
-
-
-def _norm_prompt(value: Any, default: str) -> str:
-    candidate = str(value or "").strip()
-    return candidate if candidate else default
-
-
-# ── Registry ─────────────────────────────────────────────────────────
-
-def _default_output_format() -> str:
-    return "wav"
-
-
-def _default_save_mode() -> str:
-    return "default_output" if has_output_override() else "save_next_to_input"
-
-
-def _default_llm(key: str) -> str:
-    return environment_llm_defaults().get(key, "")
-
-
-SETTINGS_REGISTRY: list[Setting] = [
-    # ── Core output ──────────────────────────────────────────────
-    Setting("output_format", str, "wav",
-            valid_values=tuple(SUPPORTED_SOUND_FORMATS),
-            description="Audio output format"),
-    Setting("subtitle_format", str, "srt",
-            valid_values=tuple(item[0] for item in SUBTITLE_FORMATS),
-            description="Subtitle file format"),
-    Setting("save_mode", str, _default_save_mode,
-            normalizer=_norm_save_mode,
-            description="Where to save output files"),
-    Setting("separate_chapters_format", str, "wav",
-            valid_values=("wav", "flac", "mp3", "opus"),
-            description="Format for separately saved chapters"),
-    Setting("chunk_level", str, "paragraph",
-            valid_values=("paragraph", "sentence"),
-            description="Text chunking granularity"),
-
-    # ── Voice ────────────────────────────────────────────────────
-    Setting("default_speaker", str, "",
-            normalizer=_norm_speaker_spec,
-            description="Default speaker name"),
-    Setting("default_voice", str, lambda: get_default_voice("kokoro"),
-            normalizer=_norm_voice_spec,
-            description="Default TTS voice"),
-    Setting("speed", float, 1.0, min_value=0.5, max_value=3.0,
-            gui_only=True,
-            description="TTS speed multiplier"),
-    Setting("supertonic_total_steps", int, 5, min_value=2, max_value=15,
-            description="SuperTonic processing steps"),
-    Setting("supertonic_speed", float, 1.0, min_value=0.7, max_value=2.0,
-            description="SuperTonic speed"),
-
-    # ── Chapter handling ─────────────────────────────────────────
-    Setting("silence_between_chapters", float, 2.0, min_value=0.0,
-            description="Silence gap between chapters (seconds)"),
-    Setting("chapter_intro_delay", float, 0.5, min_value=0.0,
-            description="Delay after chapter heading (seconds)"),
-    Setting("read_title_intro", bool, False,
-            description="Read chapter title as intro"),
-    Setting("read_closing_outro", bool, True,
-            description="Read closing/outro text"),
-    Setting("normalize_chapter_opening_caps", bool, True,
-            description="Normalize chapter opening caps"),
-    Setting("auto_prefix_chapter_titles", bool, True,
-            description="Auto-prefix chapter titles"),
-    Setting("save_chapters_separately", bool, False,
-            description="Save each chapter as separate file"),
-    Setting("merge_chapters_at_end", bool, True,
-            description="Merge chapters into single file"),
-    Setting("save_as_project", bool, False,
-            description="Save as editable project"),
-    Setting("generate_epub3", bool, False,
-            description="Generate EPUB3 output"),
-
-    # ── GPU / performance ────────────────────────────────────────
-    Setting("use_gpu", bool, True,
-            description="Use GPU acceleration"),
-
-    # ── Text processing ──────────────────────────────────────────
-    Setting("replace_single_newlines", bool, False,
-            description="Replace single newlines with spaces"),
-    Setting("max_subtitle_words", int, 50, min_value=1, max_value=500,
-            description="Max words per subtitle"),
-    Setting("enable_entity_recognition", bool, True,
-            description="Enable entity recognition"),
-
-    # ── Speaker analysis ─────────────────────────────────────────
-    Setting("speaker_analysis_threshold", int, 3, min_value=1, max_value=25,
-            description="Speaker analysis threshold"),
-    Setting("speaker_pronunciation_sentence", str, "This is {{name}} speaking.",
-            description="Template for pronunciation samples"),
-    Setting("speaker_random_languages", list, [],
-            normalizer=_norm_language_list,
-            description="Languages for random speaker assignment"),
-
-    # ── LLM ──────────────────────────────────────────────────────
-    Setting("llm_base_url", str, lambda: _default_llm("llm_base_url"),
-            normalizer=_norm_stripped_str,
-            description="LLM API base URL"),
-    Setting("llm_api_key", str, lambda: _default_llm("llm_api_key"),
-            normalizer=_norm_stripped_str,
-            description="LLM API key"),
-    Setting("llm_model", str, lambda: _default_llm("llm_model"),
-            normalizer=_norm_stripped_str,
-            description="LLM model name"),
-    Setting("llm_timeout", float, lambda: _default_llm("llm_timeout") or 30.0,
-            min_value=1.0,
-            description="LLM request timeout"),
-    Setting("llm_prompt", str, lambda: _default_llm("llm_prompt") or DEFAULT_LLM_PROMPT,
-            normalizer=_norm_prompt,
-            description="LLM normalization prompt"),
-    Setting("llm_context_mode", str, lambda: _default_llm("llm_context_mode") or "sentence",
-            valid_values=("sentence",),
-            description="LLM context mode"),
-
-    # ── Normalization (booleans) ─────────────────────────────────
-    Setting("normalization_numbers", bool, True,
-            description="Convert grouped numbers to words"),
-    Setting("normalization_currency", bool, True,
-            description="Convert currency symbols"),
-    Setting("normalization_footnotes", bool, True,
-            description="Remove footnote indicators"),
-    Setting("normalization_titles", bool, True,
-            description="Expand titles and suffixes"),
-    Setting("normalization_terminal", bool, True,
-            description="Ensure terminal punctuation"),
-    Setting("normalization_phoneme_hints", bool, True,
-            description="Add phoneme hints for possessives"),
-    Setting("normalization_caps_quotes", bool, True,
-            description="Convert ALL CAPS in quotes"),
-    Setting("normalization_internet_slang", bool, False,
-            description="Expand internet slang"),
-    Setting("normalization_apostrophes_contractions", bool, True,
-            description="Expand contractions"),
-    Setting("normalization_apostrophes_plural_possessives", bool, True,
-            description="Collapse plural possessives"),
-    Setting("normalization_apostrophes_sibilant_possessives", bool, True,
-            description="Mark sibilant possessives"),
-    Setting("normalization_apostrophes_decades", bool, True,
-            description="Expand decades"),
-    Setting("normalization_apostrophes_leading_elisions", bool, True,
-            description="Expand leading elisions"),
-    Setting("normalization_contraction_aux_be", bool, True,
-            description="Expand auxiliary 'be'"),
-    Setting("normalization_contraction_aux_have", bool, True,
-            description="Expand auxiliary 'have'"),
-    Setting("normalization_contraction_modal_will", bool, True,
-            description="Expand modal 'will'"),
-    Setting("normalization_contraction_modal_would", bool, True,
-            description="Expand modal 'would'"),
-    Setting("normalization_contraction_negation_not", bool, True,
-            description="Expand negation 'not'"),
-    Setting("normalization_contraction_let_us", bool, True,
-            description="Expand 'let's'"),
-
-    # ── Normalization (strings) ──────────────────────────────────
-    Setting("normalization_apostrophe_mode", str, "spacy",
-            valid_values=("off", "spacy", "llm"),
-            description="Apostrophe handling mode"),
-    Setting("normalization_numbers_year_style", str, "american",
-            valid_values=("american", "off"),
-            description="Year style for number normalization"),
-
-    # ── PyQt GUI-only ────────────────────────────────────────────
-    Setting("theme", str, "system",
-            gui_only=True,
-            description="UI theme"),
-    Setting("check_updates", bool, True,
-            gui_only=True,
-            description="Check for updates on startup"),
-    Setting("subtitle_mode", str, "Sentence",
-            gui_only=True,
-            description="Subtitle display mode"),
-    Setting("selected_format", str, "wav",
-            gui_only=True,
-            description="Last selected audio format"),
-    Setting("selected_voice", str, "af_heart",
-            gui_only=True,
-            description="Last selected voice"),
-    Setting("selected_profile_name", str, None,
-            gui_only=True,
-            description="Last selected profile name"),
-    Setting("log_window_max_lines", int, 2000, min_value=100,
-            gui_only=True,
-            description="Max lines in log window"),
-    Setting("use_silent_gaps", bool, True,
-            gui_only=True,
-            description="Use silent gaps between chunks"),
-    Setting("subtitle_speed_method", str, "tts",
-            gui_only=True,
-            valid_values=("tts", "ffmpeg"),
-            description="Speed adjustment method for subtitles"),
-    Setting("use_spacy_segmentation", bool, True,
-            gui_only=True,
-            description="Use spaCy for sentence segmentation"),
-    Setting("word_substitutions_enabled", bool, False,
-            gui_only=True,
-            description="Enable word substitutions"),
-    Setting("word_substitutions_list", str, "",
-            gui_only=True,
-            description="Word substitutions list"),
-    Setting("case_sensitive_substitutions", bool, False,
-            gui_only=True,
-            description="Case-sensitive substitutions"),
-    Setting("replace_all_caps", bool, False,
-            gui_only=True,
-            description="Replace ALL CAPS text"),
-    Setting("replace_numerals", bool, False,
-            gui_only=True,
-            description="Replace numerals with words"),
-    Setting("fix_nonstandard_punctuation", bool, False,
-            gui_only=True,
-            description="Fix nonstandard punctuation"),
-    Setting("queue_override_settings", bool, False,
-            gui_only=True,
-            description="Override settings per queue item"),
-    Setting("disable_kokoro_internet", bool, False,
-            description="Disable Kokoro internet access"),
-]
-
-
-# ── Registry helpers ─────────────────────────────────────────────────
-
-_REGISTRY_BY_KEY: dict[str, Setting] = {s.key: s for s in SETTINGS_REGISTRY}
-
-SETTING_KEYS: frozenset[str] = frozenset(_REGISTRY_BY_KEY.keys())
-GUI_ONLY_KEYS: frozenset[str] = frozenset(s.key for s in SETTINGS_REGISTRY if s.gui_only)
-WEB_ONLY_KEYS: frozenset[str] = frozenset(s.key for s in SETTINGS_REGISTRY if s.web_only)
-SHARED_KEYS: frozenset[str] = SETTING_KEYS - GUI_ONLY_KEYS - WEB_ONLY_KEYS
-
-BOOLEAN_SETTINGS: frozenset[str] = frozenset(s.key for s in SETTINGS_REGISTRY if s.type_ is bool)
-FLOAT_SETTINGS: frozenset[str] = frozenset(s.key for s in SETTINGS_REGISTRY if s.type_ is float)
-INT_SETTINGS: frozenset[str] = frozenset(s.key for s in SETTINGS_REGISTRY if s.type_ is int)
-
-# Backward-compatible aliases (used by existing code)
-_NORMALIZATION_BOOLEAN_KEYS: frozenset[str] = frozenset(
-    s.key for s in SETTINGS_REGISTRY
-    if s.type_ is bool and s.key.startswith("normalization_")
-)
-_NORMALIZATION_STRING_KEYS: frozenset[str] = frozenset(
-    s.key for s in SETTINGS_REGISTRY
-    if s.type_ is str and s.key.startswith("normalization_")
-)
-
-
-def get_setting(key: str) -> Setting | None:
-    """Look up a setting by key."""
-    return _REGISTRY_BY_KEY.get(key)
-
-
-def has_output_override() -> bool:
-    return bool(os.environ.get("ABOGEN_OUTPUT_DIR") or os.environ.get("ABOGEN_OUTPUT_ROOT"))
-
-
-# ── Defaults ─────────────────────────────────────────────────────────
-
-def settings_defaults() -> Dict[str, Any]:
-    """Default values for all shared settings (excludes gui_only)."""
-    result: Dict[str, Any] = {}
-    for s in SETTINGS_REGISTRY:
-        if s.gui_only:
-            continue
-        result[s.key] = s.default() if callable(s.default) else s.default
-    return result
-
-
-def all_settings_defaults() -> Dict[str, Any]:
-    """Default values for ALL settings (including gui_only)."""
-    result: Dict[str, Any] = {}
-    for s in SETTINGS_REGISTRY:
-        result[s.key] = s.default() if callable(s.default) else s.default
-    return result
-
-
-def load_settings() -> Dict[str, Any]:
-    """Load and normalize settings from config file."""
-    from abogen.utils import load_config
-    defaults = settings_defaults()
-    cfg = load_config() or {}
-    settings: Dict[str, Any] = {}
-    for key, default in defaults.items():
-        raw_value = cfg.get(key, default)
-        settings[key] = normalize_setting_value(key, raw_value, defaults)
-    return settings
-
-
-# ── Normalization (delegates to Setting.coerce) ──────────────────────
-
-def normalize_setting_value(key: str, value: Any, defaults: Dict[str, Any]) -> Any:
-    """Normalize a single setting value using the registry schema."""
-    setting = _REGISTRY_BY_KEY.get(key)
-    if setting is None:
-        return value if value is not None else defaults.get(key)
-
-    fallback = defaults.get(key, setting.default() if callable(setting.default) else setting.default)
-
-    if setting.normalizer is not None:
-        return setting.normalizer(value, fallback)
-
-    return setting.coerce(value, fallback)
-
-
-def validate_setting(key: str, value: Any) -> tuple[bool, str]:
-    """Validate a setting value against its schema. Returns (ok, error_message)."""
-    setting = _REGISTRY_BY_KEY.get(key)
-    if setting is None:
-        return False, f"Unknown setting: {key}"
-    if setting.type_ is str and setting.valid_values is not None:
-        v = str(value or "").strip()
-        if v and v not in setting.valid_values:
-            return False, f"Invalid value '{v}' for {key}. Allowed: {setting.valid_values}"
-    if setting.type_ is int:
-        try:
-            iv = int(value)
-        except (TypeError, ValueError):
-            return False, f"Invalid integer value for {key}: {value!r}"
-        if setting.min_value is not None and iv < setting.min_value:
-            return False, f"{key} must be >= {setting.min_value}, got {iv}"
-        if setting.max_value is not None and iv > setting.max_value:
-            return False, f"{key} must be <= {setting.max_value}, got {iv}"
-    if setting.type_ is float:
-        try:
-            fv = float(value)
-        except (TypeError, ValueError):
-            return False, f"Invalid float value for {key}: {value!r}"
-        if setting.min_value is not None and fv < setting.min_value:
-            return False, f"{key} must be >= {setting.min_value}, got {fv}"
-        if setting.max_value is not None and fv > setting.max_value:
-            return False, f"{key} must be <= {setting.max_value}, got {fv}"
-    return True, ""
-
-
-# ── Constants (backward-compatible) ──────────────────────────────────
-
-SAVE_MODE_LABELS = {
-    "save_next_to_input": "Save next to input file",
-    "save_to_desktop": "Save to Desktop",
-    "choose_output_folder": "Choose output folder",
-    "default_output": "Use default save location",
-}
-
-LEGACY_SAVE_MODE_MAP = {label: key for key, label in SAVE_MODE_LABELS.items()}
-
-CHUNK_LEVEL_OPTIONS = [
-    {"value": "paragraph", "label": "Paragraphs"},
-    {"value": "sentence", "label": "Sentences"},
-]
-
-CHUNK_LEVEL_VALUES = frozenset(option["value"] for option in CHUNK_LEVEL_OPTIONS)
-
-DEFAULT_ANALYSIS_THRESHOLD = 3
-
-
-# ── Coercion helpers (backward-compatible, delegate to Setting.coerce) ──
-
-def coerce_bool(value: Any, default: bool) -> bool:
-    return Setting("_", bool, default).coerce(value, default)
-
-
-def coerce_float(value: Any, default: float) -> float:
-    return Setting("_", float, default).coerce(value, default)
-
-
-def coerce_int(value: Any, default: int, *, minimum: int = 1, maximum: int = 200) -> int:
-    return Setting("_", int, default, min_value=minimum, max_value=maximum).coerce(value, default)
-
-
-def split_profile_spec(value: Any) -> tuple[str, str | None]:
-    """Split 'speaker:Name' or 'profile:Name' into (raw, name)."""
-    text = str(value or "").strip()
-    if not text:
-        return "", None
-    lowered = text.lower()
-    if lowered.startswith("profile:") or lowered.startswith("speaker:"):
-        _, _, remainder = text.partition(":")
-        name = remainder.strip()
-        return "", name or None
-    return text, None
-
-
-def normalize_save_mode(value: Any, default: str) -> str:
-    return _norm_save_mode(value, default)
-
-
-# ── LLM helpers ──────────────────────────────────────────────────────
-
-_PROMPT_TOKEN_RE = re.compile(r"{{\s*([a-zA-Z0-9_]+)\s*}}")
-
-
-def llm_ready(settings: Mapping[str, Any]) -> bool:
-    base_url = str(settings.get("llm_base_url") or "").strip()
-    return bool(base_url)
-
-
-def render_prompt_template(template: str, context: Mapping[str, str]) -> str:
-    if not template:
-        return ""
-
-    def _replace(match: re.Match[str]) -> str:
-        key = match.group(1)
-        return context.get(key, "")
-
-    return _PROMPT_TOKEN_RE.sub(_replace, template)
-
-
-# ── Integration defaults ─────────────────────────────────────────────
-
-def integration_defaults() -> Dict[str, Dict[str, Any]]:
-    """Default values for integration settings."""
-    return {
-        "calibre_opds": {
-            "enabled": False,
-            "base_url": "",
-            "username": "",
-            "password": "",
-            "verify_ssl": True,
-        },
-        "audiobookshelf": {
-            "enabled": False,
-            "base_url": "",
-            "api_token": "",
-            "library_id": "",
-            "collection_id": "",
-            "folder_id": "",
-            "verify_ssl": True,
-            "send_cover": True,
-            "send_chapters": True,
-            "send_subtitles": False,
-            "auto_send": False,
-            "timeout": 30.0,
-        },
-    }

abogen/domain/split_pattern.py

@@ -1,50 +0,0 @@
-from __future__ import annotations
-
-"""Unified split pattern logic extracted from 3 copies."""
-import re
-
-from abogen.domain.enums import Language, SubtitleMode
-
-PUNCTUATION_SENTENCE = r".!?。！？"
-PUNCTUATION_SENTENCE_COMMA = r".!?,。！？、，"
-
-
-def get_split_pattern(language: str, subtitle_mode: str) -> str:
-    """Get the appropriate split pattern based on language and subtitle mode.
-
-    Args:
-        language: Language code (a, b, e, f, etc.)
-        subtitle_mode: Subtitle mode ("Sentence", "Sentence + Comma", "Line", etc.)
-
-    Returns:
-        Split pattern string
-    """
-    try:
-        lang = Language.from_str(language) if not isinstance(language, Language) else language
-    except ValueError:
-        lang = None  # unknown language — treat as non-English, non-CJK
-    try:
-        mode = SubtitleMode.from_str(subtitle_mode) if not isinstance(subtitle_mode, SubtitleMode) else subtitle_mode
-    except ValueError:
-        mode = SubtitleMode.DISABLED
-
-    # For English, always use newline splitting only
-    if lang in (Language.EN_US, Language.EN_GB):
-        return "\n"
-
-    # Determine spacing pattern based on language
-    spacing = r"\s*" if lang and lang.is_cjk else r"\s+"
-
-    # For CJK languages, when subtitle mode is Disabled or Line, prefer
-    # punctuation-based splitting instead of plain newline splitting.
-    if mode in (SubtitleMode.DISABLED, SubtitleMode.LINE) and lang and lang.is_cjk:
-        return rf"(?<=[{PUNCTUATION_SENTENCE}]){spacing}|\n+"
-
-    if mode == SubtitleMode.LINE:
-        return "\n"
-    elif mode == SubtitleMode.SENTENCE:
-        return rf"(?<=[{PUNCTUATION_SENTENCE}]){spacing}|\n+"
-    elif mode == SubtitleMode.SENTENCE_COMMA:
-        return rf"(?<=[{PUNCTUATION_SENTENCE_COMMA}]){spacing}|\n+"
-    else:
-        return r"\n+"

abogen/domain/subtitle_generation.py

@@ -1,372 +0,0 @@
-"""Subtitle generation utilities for audiobook generation.
-
-This module provides functions for processing TTS tokens into subtitle entries
-according to various subtitle modes (Line, Sentence, Sentence + Comma,
-Sentence + Highlighting).
-"""
-
-from __future__ import annotations
-
-import re
-from typing import List, Optional, Tuple
-
-from abogen.domain.enums import Language, SubtitleMode
-
-
-# Punctuation constants for sentence splitting
-PUNCTUATION_SENTENCE = ".!?\u061f\u3002\uff01\uff1f"  # .!? .?. ??
-PUNCTUATION_SENTENCE_COMMA = ".!?,\u3001\u061f\u3002\uff01\uff0c\uff1f"  # .!?, ,. ??
-
-
-def process_subtitle_tokens(
-    tokens_with_timestamps: List[dict],
-    subtitle_entries: List[Tuple[float, float, str]],
-    max_subtitle_words: int,
-    subtitle_mode: str,
-    lang_code: str,
-    use_spacy_segmentation: bool = False,
-    fallback_end_time: Optional[float] = None,
-) -> None:
-    """Process TTS tokens into subtitle entries according to the subtitle mode.
-    
-    This function modifies subtitle_entries in-place by appending new entries.
-    
-    Args:
-        tokens_with_timestamps: List of token dictionaries with 'start', 'end', 'text',
-            and 'whitespace' keys.
-        subtitle_entries: List to append subtitle entries to (modified in-place).
-            Each entry is a tuple of (start_time, end_time, text).
-        max_subtitle_words: Maximum number of words per subtitle entry.
-        subtitle_mode: One of "Disabled", "Line", "Sentence", "Sentence + Comma",
-            "Sentence + Highlighting", or a string like "5" for word-count mode.
-        lang_code: Language code for spaCy processing (e.g., "a" for English).
-        use_spacy_segmentation: Whether to use spaCy for sentence boundary detection.
-        fallback_end_time: Fallback end time for the last entry if none is available.
-    """
-    if not tokens_with_timestamps:
-        return
-
-    processed_tokens = tokens_with_timestamps
-
-    # For English with spaCy enabled and sentence-based modes, use spaCy for sentence boundaries
-    # spaCy is disabled when subtitle mode is "Disabled" or "Line"
-    use_spacy_for_english = (
-        use_spacy_segmentation
-        and subtitle_mode not in [SubtitleMode.DISABLED, SubtitleMode.LINE]
-        and lang_code in [Language.EN_US, Language.EN_GB]
-        and subtitle_mode in [SubtitleMode.SENTENCE, SubtitleMode.SENTENCE_COMMA]
-    )
-
-    if subtitle_mode == SubtitleMode.SENTENCE_HIGHLIGHT:
-        _process_karaoke_highlighting(
-            processed_tokens, subtitle_entries, max_subtitle_words, fallback_end_time
-        )
-    elif subtitle_mode in [SubtitleMode.SENTENCE, SubtitleMode.SENTENCE_COMMA, SubtitleMode.LINE]:
-        if use_spacy_for_english and subtitle_mode != SubtitleMode.LINE:
-            _process_spacy_sentences(
-                processed_tokens, subtitle_entries, max_subtitle_words,
-                subtitle_mode, lang_code, fallback_end_time
-            )
-        else:
-            _process_regex_sentences(
-                processed_tokens, subtitle_entries, max_subtitle_words,
-                subtitle_mode, fallback_end_time
-            )
-    else:
-        # Word count-based grouping (e.g., "5" for 5-word groups)
-        _process_word_count(
-            processed_tokens, subtitle_entries, max_subtitle_words,
-            subtitle_mode, fallback_end_time
-        )
-
-
-def _process_karaoke_highlighting(
-    tokens: List[dict],
-    subtitle_entries: List[Tuple[float, float, str]],
-    max_subtitle_words: int,
-    fallback_end_time: Optional[float],
-) -> None:
-    """Process tokens for Sentence + Highlighting mode (karaoke effect)."""
-    separator = rf"[{re.escape(PUNCTUATION_SENTENCE)}]"
-    current_sentence = []
-    word_count = 0
-
-    for token in tokens:
-        current_sentence.append(token)
-        word_count += 1
-
-        # Split sentences based on separator or word count
-        if (
-            re.search(separator, token["text"]) and token.get("whitespace") == " "
-        ) or word_count >= max_subtitle_words:
-            if current_sentence:
-                # Create karaoke subtitle entry for this sentence
-                start_time = current_sentence[0]["start"]
-                end_time = current_sentence[-1]["end"]
-
-                # Generate karaoke text with timing
-                karaoke_text = ""
-                for t in current_sentence:
-                    # Calculate duration in centiseconds
-                    duration = (
-                        t["end"] - t["start"]
-                        if t.get("end") is not None and t.get("start") is not None
-                        else 0.5
-                    )
-                    duration_cs = int(duration * 100)
-                    # Add karaoke effect
-                    karaoke_text += f"{{\\kf{duration_cs}}}{t['text']}{t.get('whitespace', '') or ''}"
-
-                subtitle_entries.append(
-                    (start_time, end_time, karaoke_text.strip())
-                )
-                current_sentence = []
-                word_count = 0
-
-    # Add any remaining tokens as a sentence
-    if current_sentence:
-        start_time = current_sentence[0]["start"]
-        end_time = current_sentence[-1]["end"]
-
-        # Generate karaoke text for remaining tokens
-        karaoke_text = ""
-        for t in current_sentence:
-            duration = t["end"] - t["start"] if t.get("end") and t.get("start") else 0.5
-            duration_cs = int(duration * 100)
-            karaoke_text += f"{{\\kf{duration_cs}}}{t['text']}{t.get('whitespace', '') or ''}"
-        subtitle_entries.append((start_time, end_time, karaoke_text.strip()))
-
-    # Fallback for last entry
-    _apply_fallback_end_time(subtitle_entries, fallback_end_time)
-
-
-def _process_spacy_sentences(
-    tokens: List[dict],
-    subtitle_entries: List[Tuple[float, float, str]],
-    max_subtitle_words: int,
-    subtitle_mode: str,
-    lang_code: str,
-    fallback_end_time: Optional[float],
-) -> None:
-    """Process tokens using spaCy for sentence boundary detection."""
-    try:
-        from abogen.spacy_utils import get_spacy_model
-    except ImportError:
-        # Fall back to regex if spaCy is not available
-        _process_regex_sentences(
-            tokens, subtitle_entries, max_subtitle_words,
-            subtitle_mode, fallback_end_time
-        )
-        return
-
-    nlp = get_spacy_model(lang_code)
-    if not nlp:
-        _process_regex_sentences(
-            tokens, subtitle_entries, max_subtitle_words,
-            subtitle_mode, fallback_end_time
-        )
-        return
-
-    # Build full text and track character positions to token indices
-    full_text = ""
-    for token in tokens:
-        text_part = token["text"] + (token.get("whitespace") or "")
-        full_text += text_part
-
-    # Get sentence boundaries from spaCy
-    doc = nlp(full_text)
-    sentence_boundaries = [sent.end_char for sent in doc.sents]
-
-    # For "Sentence + Comma" mode, also split on commas
-    if subtitle_mode == SubtitleMode.SENTENCE_COMMA:
-        comma_positions = [
-            i + 1 for i, c in enumerate(full_text) if c == ","
-        ]
-        sentence_boundaries = sorted(
-            set(sentence_boundaries + comma_positions)
-        )
-
-    # Group tokens by sentence boundaries
-    current_sentence = []
-    word_count = 0
-    current_char_pos = 0
-    boundary_idx = 0
-
-    for token in tokens:
-        current_sentence.append(token)
-        word_count += 1
-        text_len = len(token["text"]) + len(token.get("whitespace") or "")
-        current_char_pos += text_len
-
-        # Check if we've hit a sentence boundary or max words
-        at_boundary = (
-            boundary_idx < len(sentence_boundaries)
-            and current_char_pos >= sentence_boundaries[boundary_idx]
-        )
-        if at_boundary or word_count >= max_subtitle_words:
-            if current_sentence:
-                start_time = current_sentence[0]["start"]
-                end_time = current_sentence[-1]["end"]
-                sentence_text = "".join(
-                    t["text"] + (t.get("whitespace") or "")
-                    for t in current_sentence
-                )
-                subtitle_entries.append(
-                    (start_time, end_time, sentence_text.strip())
-                )
-                current_sentence = []
-                word_count = 0
-            if at_boundary:
-                boundary_idx += 1
-
-    # Add remaining tokens
-    if current_sentence:
-        start_time = current_sentence[0]["start"]
-        end_time = current_sentence[-1]["end"]
-        sentence_text = "".join(
-            t["text"] + (t.get("whitespace") or "")
-            for t in current_sentence
-        )
-        subtitle_entries.append(
-            (start_time, end_time, sentence_text.strip())
-        )
-
-    # Fallback for last entry
-    _apply_fallback_end_time(subtitle_entries, fallback_end_time)
-
-
-def _process_regex_sentences(
-    tokens: List[dict],
-    subtitle_entries: List[Tuple[float, float, str]],
-    max_subtitle_words: int,
-    subtitle_mode: str,
-    fallback_end_time: Optional[float],
-) -> None:
-    """Process tokens using regex for sentence boundary detection."""
-    # Define separator pattern based on mode
-    if subtitle_mode == SubtitleMode.LINE:
-        separator = r"\n"
-    elif subtitle_mode == SubtitleMode.SENTENCE:
-        # Use punctuation without comma
-        separator = rf"[{re.escape(PUNCTUATION_SENTENCE)}]"
-    else:  # Sentence + Comma
-        # Use punctuation with comma
-        separator = rf"[{re.escape(PUNCTUATION_SENTENCE_COMMA)}]"
-
-    current_sentence = []
-    word_count = 0
-
-    for token in tokens:
-        current_sentence.append(token)
-        word_count += 1
-
-        # Split sentences based on separator or word count
-        if (
-            re.search(separator, token["text"]) and token.get("whitespace") == " "
-        ) or word_count >= max_subtitle_words:
-            if current_sentence:
-                # Create subtitle entry for this sentence
-                start_time = current_sentence[0]["start"]
-                end_time = current_sentence[-1]["end"]
-
-                # Simplified text joining logic
-                sentence_text = ""
-                for t in current_sentence:
-                    sentence_text += t["text"] + (t.get("whitespace") or "")
-
-                subtitle_entries.append(
-                    (start_time, end_time, sentence_text.strip())
-                )
-                current_sentence = []
-                word_count = 0
-
-    # Add any remaining tokens as a sentence (split multi-sentence FakeToken)
-    if current_sentence:
-        start_time = current_sentence[0]["start"]
-        end_time = current_sentence[-1]["end"]
-
-        sentence_text = ""
-        for t in current_sentence:
-            sentence_text += t["text"] + (t.get("whitespace") or "")
-        sentence_text = sentence_text.strip()
-
-        if len(current_sentence) == 1:
-            parts = re.split(rf"(?<={separator})\s+", sentence_text)
-            if len(parts) > 1:
-                d = end_time - start_time
-                for i, p in enumerate(parts):
-                    e = end_time if i == len(parts) - 1 else start_time + d * len(p) / len(sentence_text)
-                    subtitle_entries.append((start_time, e, p.strip()))
-                    start_time = e
-                current_sentence = []
-
-        if current_sentence:
-            subtitle_entries.append((start_time, end_time, sentence_text))
-
-    # Fallback for last entry
-    _apply_fallback_end_time(subtitle_entries, fallback_end_time)
-
-
-def _process_word_count(
-    tokens: List[dict],
-    subtitle_entries: List[Tuple[float, float, str]],
-    max_subtitle_words: int,
-    subtitle_mode: str,
-    fallback_end_time: Optional[float],
-) -> None:
-    """Process tokens by counting spaces (word count mode)."""
-    try:
-        word_count = int(subtitle_mode.split()[0])
-        word_count = min(word_count, max_subtitle_words)
-    except (ValueError, IndexError):
-        word_count = 1
-
-    current_group = []
-    space_count = 0
-
-    for token in tokens:
-        current_group.append(token)
-
-        # Count spaces after tokens (in the whitespace field)
-        if token.get("whitespace", "") == " ":
-            space_count += 1
-
-            # Split after counting N spaces
-            if space_count >= word_count:
-                text = "".join(
-                    t["text"] + (t.get("whitespace") or "")
-                    for t in current_group
-                )
-                subtitle_entries.append(
-                    (
-                        current_group[0]["start"],
-                        current_group[-1]["end"],
-                        text.strip(),
-                    )
-                )
-                current_group = []
-                space_count = 0
-
-    # Add any remaining tokens
-    if current_group:
-        text = "".join(
-            t["text"] + (t.get("whitespace") or "") for t in current_group
-        )
-        subtitle_entries.append(
-            (current_group[0]["start"], current_group[-1]["end"], text.strip())
-        )
-
-    # Fallback for last entry
-    _apply_fallback_end_time(subtitle_entries, fallback_end_time)
-
-
-def _apply_fallback_end_time(
-    subtitle_entries: List[Tuple[float, float, str]],
-    fallback_end_time: Optional[float],
-) -> None:
-    """Apply fallback end time to the last entry if needed."""
-    if subtitle_entries and fallback_end_time is not None:
-        last_entry = subtitle_entries[-1]
-        start, end, text = last_entry
-        if end is None or end <= start or end <= 0:
-            subtitle_entries[-1] = (start, fallback_end_time, text)

abogen/domain/subtitle_processor.py

@@ -1,279 +0,0 @@
-"""Subtitle-to-audio processing pipeline.
-
-Converts subtitle files (SRT/ASS/VTT/timestamp text) into audio by
-generating TTS for each entry and mixing into a buffer.
-"""
-
-from __future__ import annotations
-
-import logging
-import time
-from dataclasses import dataclass
-from typing import Any, Callable, List, Optional, Tuple
-
-import numpy as np
-
-from abogen.domain.audio_buffer import (
-    create_silence,
-    fit_audio_to_duration,
-    ffmpeg_time_stretch,
-    mix_audio,
-    normalize_audio,
-    SAMPLE_RATE,
-)
-from abogen.domain.audio_helpers import to_float32
-from abogen.domain.progress import calc_etr_str
-from abogen.subtitle_utils import (
-    parse_ass_file,
-    parse_srt_file,
-    parse_vtt_file,
-    parse_timestamp_text_file,
-)
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class SubtitleEntry:
-    """A single subtitle entry with timing."""
-    start: float
-    end: Optional[float]
-    text: str
-
-
-def parse_subtitle_file(
-    file_path: str,
-    is_timestamp_text: bool = False,
-) -> List[Tuple[float, Optional[float], str]]:
-    """Parse a subtitle file into (start, end, text) tuples.
-
-    Args:
-        file_path: Path to subtitle file.
-        is_timestamp_text: Whether to treat as timestamp text file.
-
-    Returns:
-        List of (start_time, end_time, text) tuples.
-    """
-    if is_timestamp_text:
-        return parse_timestamp_text_file(file_path)
-
-    import os
-    ext = os.path.splitext(file_path)[1].lower()
-    if ext == ".srt":
-        return parse_srt_file(file_path)
-    elif ext == ".vtt":
-        return parse_vtt_file(file_path)
-    else:
-        return parse_ass_file(file_path)
-
-
-def format_time_range(
-    start: float,
-    end: Optional[float],
-    is_auto_end: bool = False,
-) -> str:
-    """Format a time range for display in logs.
-
-    Args:
-        start: Start time in seconds.
-        end: End time in seconds, or None.
-        is_auto_end: Whether end time is auto-detected.
-
-    Returns:
-        Formatted string like "00:01:23,456 - 00:01:25,789" or "00:01:23 - AUTO".
-    """
-    def _fmt(seconds: float) -> str:
-        h = int(seconds // 3600)
-        m = int(seconds % 3600 // 60)
-        s = int(seconds % 60)
-        ms = int((seconds - int(seconds)) * 1000)
-        result = f"{h:02d}:{m:02d}:{s:02d}"
-        if ms > 0:
-            result += f",{ms:03d}"
-        return result
-
-    if is_auto_end or end is None:
-        return f"{_fmt(start)} - AUTO"
-    return f"{_fmt(start)} - {_fmt(end)}"
-
-
-def speed_up_audio(
-    audio: np.ndarray,
-    speed_factor: float,
-    method: str = "tts",
-    *,
-    backend: Any = None,
-    text: str = "",
-    voice: Any = None,
-    base_speed: float = 1.0,
-    sample_rate: int = SAMPLE_RATE,
-) -> np.ndarray:
-    """Speed up audio to fit a time window.
-
-    Args:
-        audio: Input audio buffer.
-        speed_factor: Required speed multiplier.
-        method: "ffmpeg" for time-stretch, "tts" for regeneration.
-        backend: TTS backend (required if method="tts").
-        text: Text to regenerate (required if method="tts").
-        voice: Voice to use for regeneration.
-        base_speed: Base speed for TTS.
-        sample_rate: Sample rate.
-
-    Returns:
-        Speed-adjusted audio buffer.
-    """
-    if speed_factor <= 1.0:
-        return audio
-
-    if method == "ffmpeg":
-        logger.info("FFmpeg time-stretch: %.2fx", speed_factor)
-        return ffmpeg_time_stretch(audio, speed_factor, sample_rate)
-
-    # TTS regeneration
-    if backend is None:
-        return audio
-    new_speed = base_speed * speed_factor
-    logger.info("Regenerating at %.2fx speed", new_speed)
-    results = [
-        r for r in backend(text, voice=voice, speed=new_speed, split_pattern=None)
-    ]
-    chunks = [r.audio for r in results]
-    if not chunks:
-        return audio
-    return np.concatenate([to_float32(c) for c in chunks])
-
-
-def process_subtitle_entries(
-    subtitles: List[Tuple[float, Optional[float], str]],
-    *,
-    backend: Any,
-    voice: Any,
-    speed: float = 1.0,
-    cancel_check: Callable[[], bool] = lambda: False,
-    log_callback: Optional[Callable[[str], None]] = None,
-    progress_callback: Optional[Callable[[int, str], None]] = None,
-    replace_newlines: bool = True,
-    use_gaps: bool = False,
-    is_timestamp_text: bool = False,
-    subtitle_speed_method: str = "tts",
-    sample_rate: int = SAMPLE_RATE,
-) -> np.ndarray:
-    """Process subtitle entries: generate TTS for each and mix into buffer.
-
-    This is the core domain logic for subtitle-to-audio conversion.
-    UI-specific concerns (signals, widgets) are handled via callbacks.
-
-    Args:
-        subtitles: List of (start, end, text) tuples.
-        backend: TTS pipeline callable.
-        voice: Resolved voice for TTS.
-        speed: TTS speed.
-        cancel_check: Returns True if processing should stop.
-        log_callback: Called with log messages.
-        progress_callback: Called with (percent, etr_string).
-        replace_newlines: Replace \\n with spaces in text.
-        use_gaps: Whether to use silent gaps between subtitles.
-        is_timestamp_text: Whether input is timestamp text.
-        subtitle_speed_method: "ffmpeg" or "tts" for speed adjustment.
-        sample_rate: Audio sample rate.
-
-    Returns:
-        Mixed audio buffer (float32).
-    """
-    if not subtitles:
-        return np.array([], dtype="float32")
-
-    max_end = max((end for _, end, _ in subtitles if end is not None), default=0)
-    buffer_samples = int(max_end * sample_rate) + sample_rate
-    audio_buffer = np.zeros(buffer_samples, dtype="float32")
-    etr_start = time.time()
-    total = len(subtitles)
-
-    for idx, (start_time, end_time, text) in enumerate(subtitles, 1):
-        if cancel_check():
-            break
-
-        processed_text = text.replace("\n", " ") if replace_newlines else text
-        next_start = (
-            subtitles[idx][0]
-            if (use_gaps and idx < total)
-            else float("inf")
-        )
-        subtitle_duration = None if end_time is None else end_time - start_time
-
-        is_auto_end = is_timestamp_text or (use_gaps and idx == total) or end_time is None
-        if log_callback:
-            log_callback(
-                f"\n[{idx}/{total}] {format_time_range(start_time, end_time, is_auto_end)}: {processed_text}"
-            )
-
-        # Generate TTS
-        results = [
-            r for r in backend(
-                processed_text, voice=voice, speed=speed, split_pattern=None
-            )
-            if not cancel_check()
-        ]
-        if cancel_check():
-            break
-
-        audio_chunks = [r.audio for r in results]
-        full_audio = (
-            np.concatenate([to_float32(a) for a in audio_chunks])
-            if audio_chunks
-            else np.zeros(int((subtitle_duration or 0) * sample_rate), dtype="float32")
-        )
-        audio_duration = len(full_audio) / sample_rate
-
-        # Timing adjustment
-        if is_timestamp_text:
-            end_time = start_time + audio_duration
-            subtitle_duration = audio_duration
-        elif use_gaps:
-            end_time = min(start_time + audio_duration, next_start)
-            subtitle_duration = end_time - start_time
-        elif subtitle_duration is None:
-            subtitle_duration = audio_duration
-            end_time = start_time + audio_duration
-
-        # Speed up if needed
-        speedup_threshold = next_start - start_time if use_gaps else subtitle_duration
-        if audio_duration > speedup_threshold and speedup_threshold > 0:
-            speed_factor = audio_duration / speedup_threshold
-            full_audio = speed_up_audio(
-                full_audio, speed_factor,
-                method=subtitle_speed_method,
-                backend=backend, text=processed_text,
-                voice=voice, base_speed=speed,
-                sample_rate=sample_rate,
-            )
-            audio_duration = len(full_audio) / sample_rate
-
-        # Adjust duration after speed change
-        if use_gaps:
-            end_time = min(start_time + audio_duration, next_start)
-            subtitle_duration = end_time - start_time
-        elif subtitle_duration is None:
-            subtitle_duration = audio_duration
-            end_time = start_time + audio_duration
-
-        # Pad or trim to subtitle duration
-        full_audio = fit_audio_to_duration(full_audio, subtitle_duration, sample_rate)
-
-        # Mix into buffer
-        start_sample = int(start_time * sample_rate)
-        audio_buffer = mix_audio(audio_buffer, full_audio, start_sample)
-
-        # Progress
-        if progress_callback:
-            percent = min(int(idx / total * 100), 99)
-            etr = calc_etr_str(time.time() - etr_start, idx, total)
-            progress_callback(percent, etr)
-
-    # Normalize if needed
-    if np.abs(audio_buffer).max() > 1.0:
-        logger.info("Normalizing audio (peak: %.2f)", np.abs(audio_buffer).max())
-        audio_buffer = normalize_audio(audio_buffer)
-
-    return audio_buffer

abogen/domain/text_chapters.py

@@ -1,59 +0,0 @@
-"""Chapter parsing from raw text.
-
-Provides a unified function for splitting text by chapter markers,
-used by both WebUI and PyQt conversion runners.
-"""
-
-from __future__ import annotations
-
-import re
-from typing import List, Tuple
-
-from abogen.subtitle_utils import clean_text
-
-
-_CHAPTER_MARKER_RE = re.compile(r"<<CHAPTER_MARKER:(.*?)>>", re.IGNORECASE)
-
-
-def parse_chapters_from_text(
-    text: str,
-    default_title: str = "text",
-    clean: bool = True,
-) -> List[Tuple[str, str]]:
-    """Split raw text into chapters using chapter marker patterns.
-
-    Preserves content before the first marker as "Introduction" if present.
-    Optionally applies clean_text() to each chapter segment.
-
-    Args:
-        text: Raw text possibly containing <<CHAPTER_MARKER:Title>> markers.
-        default_title: Fallback title when no markers are found.
-        clean: Whether to apply clean_text() to each segment.
-
-    Returns:
-        List of (title, text) tuples.
-    """
-    matches = list(_CHAPTER_MARKER_RE.finditer(text))
-    if not matches:
-        cleaned = clean_text(text) if clean else text
-        return [(default_title, cleaned)]
-
-    chapters: List[Tuple[str, str]] = []
-
-    # Preserve content before first marker as "Introduction"
-    first_start = matches[0].start()
-    if first_start > 0:
-        intro_text = text[:first_start].strip()
-        if intro_text:
-            chapters.append(("Introduction", clean_text(intro_text) if clean else intro_text))
-
-    for idx, match in enumerate(matches):
-        start = match.end()
-        end = matches[idx + 1].start() if idx + 1 < len(matches) else len(text)
-        chapter_name = match.group(1).strip() or default_title
-        chapter_text = text[start:end].strip()
-        if clean:
-            chapter_text = clean_text(chapter_text)
-        chapters.append((chapter_name, chapter_text))
-
-    return chapters

abogen/domain/title_builder.py

@@ -1,97 +0,0 @@
-from __future__ import annotations
-
-from pathlib import Path
-from typing import Any, Dict, List, Mapping, Optional
-
-from .metadata_helpers import (
-    ensure_sentence,
-    extract_series_metadata,
-    format_author_sentence,
-    format_series_sentence,
-    normalize_metadata_map,
-)
-
-
-def build_title_intro_text(
-    metadata: Optional[Mapping[str, Any]],
-    fallback_basename: str,
-) -> str:
-    """Build the title introduction text from metadata."""
-    normalized = normalize_metadata_map(metadata)
-    fallback_title = Path(fallback_basename).stem if fallback_basename else ""
-    title = (
-        normalized.get("title")
-        or normalized.get("book_title")
-        or normalized.get("album")
-        or fallback_title
-    )
-    if not title:
-        title = fallback_title
-    subtitle = normalized.get("subtitle") or normalized.get("sub_title")
-    if subtitle and title and subtitle.casefold() == title.casefold():
-        subtitle = ""
-
-    author_value = ""
-    for candidate in ("artist", "album_artist", "author", "authors", "writer", "composer"):
-        value = normalized.get(candidate)
-        if value:
-            author_value = value
-            break
-
-    series_name, series_number = extract_series_metadata(normalized)
-    series_sentence = format_series_sentence(series_name, series_number)
-
-    sentences: List[str] = []
-    if series_sentence:
-        sentences.append(ensure_sentence(series_sentence))
-    if title:
-        sentences.append(ensure_sentence(title))
-    if subtitle:
-        sentences.append(ensure_sentence(subtitle))
-    author_sentence = format_author_sentence(author_value)
-    if author_sentence:
-        sentences.append(ensure_sentence(author_sentence))
-    return " ".join(sentences).strip()
-
-
-def build_outro_text(
-    metadata: Optional[Mapping[str, Any]],
-    fallback_basename: str,
-) -> str:
-    """Build the outro/closing text from metadata."""
-    normalized = normalize_metadata_map(metadata)
-    fallback_title = Path(fallback_basename).stem if fallback_basename else ""
-    title = (
-        normalized.get("title")
-        or normalized.get("book_title")
-        or normalized.get("album")
-        or fallback_title
-    )
-    author_value = ""
-    for candidate in ("authors", "author", "album_artist", "artist", "writer", "composer"):
-        value = normalized.get(candidate)
-        if value:
-            author_value = value
-            break
-    author_sentence = format_author_sentence(author_value)
-    authors_fragment = (
-        author_sentence[3:].strip() if author_sentence.lower().startswith("by ") else author_sentence.strip()
-    )
-
-    if title and authors_fragment:
-        closing_line = f"The end of {title} from {authors_fragment}"
-    elif title:
-        closing_line = f"The end of {title}"
-    elif authors_fragment:
-        closing_line = f"The end from {authors_fragment}"
-    else:
-        closing_line = "The end"
-
-    series_name, series_number = extract_series_metadata(normalized)
-    series_sentence = format_series_sentence(series_name, series_number)
-
-    sentences: List[str] = [ensure_sentence(closing_line)]
-    if series_sentence:
-        sentences.append(ensure_sentence(series_sentence))
-
-    return " ".join(sentence for sentence in sentences if sentence).strip()

abogen/domain/tokens.py

@@ -1,13 +0,0 @@
-"""Shared token stubs for TTS processing."""
-
-from __future__ import annotations
-
-
-class FakeToken:
-    """Minimal token stub for languages without per-word token support."""
-
-    def __init__(self, text: str, start: float, end: float):
-        self.text = text
-        self.start_ts = start
-        self.end_ts = end
-        self.whitespace = ""

abogen/domain/voice_loader.py

@@ -1,128 +0,0 @@
-"""Voice loading and caching utilities.
-
-This module provides unified voice loading with caching support for both
-PyQt and WebUI interfaces.
-"""
-
-from __future__ import annotations
-
-from typing import Any, Dict, Optional, Tuple
-
-from abogen.voice_formulas import get_new_voice
-
-
-class VoiceCache:
-    """Thread-safe voice cache for loaded voice tensors."""
-    
-    def __init__(self):
-        self._cache: Dict[str, Any] = {}
-    
-    def get(self, voice_spec: str) -> Optional[Any]:
-        """Get cached voice by spec."""
-        return self._cache.get(voice_spec)
-    
-    def set(self, voice_spec: str, voice: Any) -> None:
-        """Cache a loaded voice."""
-        self._cache[voice_spec] = voice
-    
-    def contains(self, voice_spec: str) -> bool:
-        """Check if voice is in cache."""
-        return voice_spec in self._cache
-    
-    def clear(self) -> None:
-        """Clear all cached voices."""
-        self._cache.clear()
-
-    def keys(self):
-        """Return cached voice specs."""
-        return self._cache.keys()
-
-    def __contains__(self, voice_spec: str) -> bool:
-        return self.contains(voice_spec)
-
-
-def resolve_voice(
-    voice_spec: str,
-    pipeline: Any,
-    use_gpu: bool,
-    cache: Optional[VoiceCache] = None,
-) -> Any:
-    """Resolve voice spec to actual voice tensor or name.
-    
-    If voice_spec contains '*' (formula), loads the voice using get_new_voice.
-    Otherwise, returns the voice_spec as-is (it's a voice name).
-    
-    Uses optional cache to avoid reloading same voice multiple times.
-    
-    Args:
-        voice_spec: Voice specification (name or formula string with '*').
-        pipeline: TTS pipeline instance for loading formula voices.
-        use_gpu: Whether to use GPU for voice loading.
-        cache: Optional VoiceCache instance for caching loaded voices.
-        
-    Returns:
-        Loaded voice tensor (for formulas) or voice name string.
-    """
-    # Check cache first
-    if cache and cache.contains(voice_spec):
-        return cache.get(voice_spec)
-
-    # Load voice
-    if "*" in voice_spec:
-        if pipeline is None or not hasattr(pipeline, "load_single_voice"):
-            return voice_spec
-        loaded_voice = get_new_voice(pipeline, voice_spec, use_gpu)
-    else:
-        loaded_voice = voice_spec
-    
-    # Cache it
-    if cache:
-        cache.set(voice_spec, loaded_voice)
-    
-    return loaded_voice
-
-
-def load_voice_cached(
-    voice_name: str,
-    pipeline: Any,
-    use_gpu: bool,
-    cache: Any = None,
-) -> Any:
-    """Load voice with caching (compatibility wrapper for PyQt).
-
-    This function maintains backward compatibility with the PyQt interface
-    while using the unified voice loading logic.
-
-    Args:
-        voice_name: Voice name or formula string.
-        pipeline: TTS pipeline instance.
-        use_gpu: Whether to use GPU.
-        cache: Optional VoiceCache or dict to use as cache.
-
-    Returns:
-        Loaded voice tensor or voice name string.
-    """
-    # Check cache (supports both VoiceCache and plain dict)
-    if cache is not None:
-        if isinstance(cache, VoiceCache):
-            if cache.contains(voice_name):
-                return cache.get(voice_name)
-        elif voice_name in cache:
-            return cache[voice_name]
-
-    # Load voice
-    if "*" in voice_name:
-        if pipeline is None or not hasattr(pipeline, "load_single_voice"):
-            return voice_name
-        loaded_voice = get_new_voice(pipeline, voice_name, use_gpu)
-    else:
-        loaded_voice = voice_name
-
-    # Cache it
-    if cache is not None:
-        if isinstance(cache, VoiceCache):
-            cache.set(voice_name, loaded_voice)
-        else:
-            cache[voice_name] = loaded_voice
-
-    return loaded_voice

abogen/domain/voice_resolution.py

@@ -1,190 +0,0 @@
-"""Voice resolution helpers.
-
-Functions for resolving voice specifications, collecting required voice IDs,
-and determining the voice to use for chapters and chunks.
-"""
-
-from __future__ import annotations
-
-from typing import Any, Dict, Optional, Set
-
-from abogen.tts_plugin.utils import get_voices, get_default_voice
-from abogen.voice_formulas import extract_voice_ids
-from abogen.voice_cache import ensure_voice_assets
-
-
-def spec_to_voice_ids(spec: Any) -> Set[str]:
-    text = str(spec or "").strip()
-    if not text:
-        return set()
-    if text == "__custom_mix":
-        return set()
-    if "*" in text:
-        try:
-            return set(extract_voice_ids(text))
-        except ValueError:
-            return set()
-    if text in get_voices("kokoro"):
-        return {text}
-    return set()
-
-
-def job_voice_fallback(job: Any) -> str:
-    base = str(getattr(job, "voice", "") or "").strip()
-    if base and base != "__custom_mix":
-        return base
-
-    speakers = getattr(job, "speakers", None)
-    if isinstance(speakers, dict):
-        narrator = speakers.get("narrator")
-        if isinstance(narrator, dict):
-            for key in ("resolved_voice", "voice_formula", "voice"):
-                value = narrator.get(key)
-                candidate = str(value or "").strip()
-                if candidate and candidate != "__custom_mix":
-                    return candidate
-        for payload in speakers.values() or []:
-            if not isinstance(payload, dict):
-                continue
-            for key in ("resolved_voice", "voice_formula", "voice"):
-                value = payload.get(key)
-                candidate = str(value or "").strip()
-                if candidate and candidate != "__custom_mix":
-                    return candidate
-
-    for chapter in getattr(job, "chapters", []) or []:
-        if not isinstance(chapter, dict):
-            continue
-        for key in ("resolved_voice", "voice_formula", "voice"):
-            candidate = str(chapter.get(key) or "").strip()
-            if candidate and candidate != "__custom_mix":
-                return candidate
-
-    return ""
-
-
-def collect_required_voice_ids(job: Any) -> Set[str]:
-    voices: Set[str] = set()
-    voices.update(spec_to_voice_ids(job.voice))
-    voices.update(spec_to_voice_ids(job_voice_fallback(job)))
-
-    for chapter in getattr(job, "chapters", []) or []:
-        if not isinstance(chapter, dict):
-            continue
-        for key in ("resolved_voice", "voice_formula", "voice"):
-            voices.update(spec_to_voice_ids(chapter.get(key)))
-
-    for chunk in getattr(job, "chunks", []) or []:
-        if not isinstance(chunk, dict):
-            continue
-        for key in ("resolved_voice", "voice_formula", "voice"):
-            voices.update(spec_to_voice_ids(chunk.get(key)))
-
-    speakers = getattr(job, "speakers", {})
-    if isinstance(speakers, dict):
-        for payload in speakers.values() or []:
-            if not isinstance(payload, dict):
-                continue
-            for key in ("resolved_voice", "voice_formula", "voice"):
-                voices.update(spec_to_voice_ids(payload.get(key)))
-
-    voices.update(get_voices("kokoro"))
-    return voices
-
-
-def initialize_voice_cache(job: Any) -> None:
-    try:
-        targets = collect_required_voice_ids(job)
-        downloaded, errors = ensure_voice_assets(
-            targets,
-            on_progress=lambda message: job.add_log(message, level="debug"),
-        )
-    except RuntimeError as exc:
-        job.add_log(f"Voice cache unavailable: {exc}", level="warning")
-        return
-
-    if downloaded:
-        job.add_log(
-            f"Cached {len(downloaded)} voice asset{'s' if len(downloaded) != 1 else ''} locally.",
-            level="info",
-        )
-
-    for voice_id, error in errors.items():
-        job.add_log(f"Failed to cache voice '{voice_id}': {error}", level="warning")
-
-
-def chapter_voice_spec(job: Any, override: Optional[Dict[str, Any]]) -> str:
-    if not override:
-        return job_voice_fallback(job)
-
-    resolved = str(override.get("resolved_voice", "")).strip()
-    if resolved:
-        return resolved
-
-    formula = str(override.get("voice_formula", "")).strip()
-    if formula:
-        return formula
-
-    voice = str(override.get("voice", "")).strip()
-    if voice:
-        return voice
-
-    return job_voice_fallback(job)
-
-
-def chunk_voice_spec(job: Any, chunk: Dict[str, Any], fallback: str) -> str:
-    for key in ("resolved_voice", "voice_formula", "voice"):
-        value = chunk.get(key)
-        if value:
-            return str(value)
-
-    speaker_id = chunk.get("speaker_id")
-    speakers = getattr(job, "speakers", None)
-    if isinstance(speakers, dict) and speaker_id in speakers:
-        speaker_entry = speakers.get(speaker_id) or {}
-        if isinstance(speaker_entry, dict):
-            for key in ("resolved_voice", "voice_formula", "voice"):
-                value = speaker_entry.get(key)
-                if value:
-                    return str(value)
-            profile_formula = speaker_entry.get("voice_formula")
-            if profile_formula:
-                return str(profile_formula)
-
-    profile_name = chunk.get("voice_profile")
-    if profile_name:
-        if isinstance(speakers, dict):
-            speaker_entry = speakers.get(profile_name)
-            if isinstance(speaker_entry, dict):
-                for key in ("resolved_voice", "voice_formula", "voice"):
-                    value = speaker_entry.get(key)
-                    if value:
-                        return str(value)
-
-    if fallback:
-        return fallback
-    return job_voice_fallback(job)
-
-
-def resolve_fallback_voice_spec(
-    base_spec: str,
-    job_voice: str,
-    voice_cache_keys: list[str],
-    provider: str = "kokoro",
-) -> str:
-    """Resolve the voice spec for intro/outro with a priority fallback chain.
-
-    Priority: base_spec → job_voice → first voice_cache key → default voice.
-    ``"__custom_mix"`` is treated as empty (it is not a usable voice spec).
-    """
-    spec = base_spec or job_voice
-    if spec == "__custom_mix":
-        spec = job_voice or ""
-    if not spec:
-        for key in voice_cache_keys:
-            if key and key != "__custom_mix":
-                spec = key.split(":", 1)[-1]
-                break
-    if not spec:
-        spec = get_default_voice(provider)
-    return spec

abogen/domain/voice_utils.py

@@ -1,130 +0,0 @@
-from __future__ import annotations
-
-from typing import Any, Dict, Mapping, Optional, Tuple, Set
-
-from abogen.voice_formulas import extract_voice_ids, get_new_voice
-from abogen.tts_plugin.utils import get_voices
-
-
-def infer_provider_from_spec(value: Any, fallback: str = "kokoro") -> str:
-    """Infer TTS provider from voice specification."""
-    raw = str(value or "").strip()
-    if not raw:
-        return fallback
-    if raw.upper() == raw and raw.replace("_", "").isalnum():
-        return "supertonic"
-    if raw == "__custom_mix" or "*" in raw or "+" in raw:
-        return "kokoro"
-    if raw in get_voices("kokoro"):
-        return "kokoro"
-    return fallback
-
-
-def supertonic_voice_from_spec(spec: Any, fallback: str) -> str:
-    """Normalize a voice specification for Supertonic.
-
-    This function only performs Supertonic-specific normalization (uppercase conversion
-    and fallback handling). Backend resolution is handled by the registry.
-    """
-    raw = str(spec or "").strip()
-    fallback_raw = str(fallback or "").strip()
-
-    # Normalize to uppercase for Supertonic voice IDs
-    upper = raw.upper() if raw else ""
-
-    # If empty or contains formula characters, use fallback
-    if not upper or "*" in upper or "+" in upper:
-        upper = fallback_raw.upper() if fallback_raw else ""
-
-    # If still empty, use default Supertonic voice
-    if not upper or "*" in upper or "+" in upper:
-        upper = "M1"
-
-    return upper
-
-
-def split_speaker_reference(value: Any) -> Tuple[Optional[str], str]:
-    """Parse speaker/profile reference from string.
-
-    Expected format: "speaker:name" or "profile:name"
-    Returns (name, original) or (None, original) if not a valid reference.
-    """
-    raw = str(value or "").strip()
-    if not raw or ":" not in raw:
-        return None, raw
-    prefix, remainder = raw.split(":", 1)
-    prefix = prefix.strip().lower()
-    if prefix not in {"speaker", "profile"}:
-        return None, raw
-    name = remainder.strip()
-    return (name or None), raw
-
-
-def formula_from_kokoro_entry(entry: Mapping[str, Any]) -> str:
-    """Build voice formula string from kokoro entry."""
-    voices = entry.get("voices") or []
-    if not voices:
-        return ""
-    total = 0.0
-    parts: list[tuple[str, float]] = []
-    for item in voices:
-        if not isinstance(item, (list, tuple)) or len(item) < 2:
-            continue
-        name = str(item[0] or "").strip()
-        try:
-            weight = float(item[1])
-        except (TypeError, ValueError):
-            continue
-        if name and weight > 0:
-            parts.append((name, weight))
-            total += weight
-
-    if not parts:
-        return ""
-
-    normalized = [(name, weight / total) for name, weight in parts]
-    return " + ".join(f"{name}*{weight:.6f}" for name, weight in normalized)
-
-
-def coerce_truthy(value: Any, default: bool = True) -> bool:
-    """Coerce a value to boolean with default."""
-    if isinstance(value, bool):
-        return value
-    if isinstance(value, str):
-        return value.lower() not in {"false", "0", "no", "off", ""}
-    if value is None:
-        return default
-    return bool(value)
-
-
-def resolve_voice_target(
-    raw_spec: str,
-    normalized_profiles: Dict[str, Dict[str, Any]],
-    *,
-    job_voice: str = "M1",
-    job_tts_provider: str = "kokoro",
-    job_supertonic_total_steps: int = 5,
-    job_speed: float = 1.0,
-) -> Tuple[str, str, Optional[float], Optional[int]]:
-    """Resolve a raw voice spec into (provider, voice_spec, speed_override, steps_override).
-
-    Pure function — all dependencies are passed as parameters.
-    """
-    spec = str(raw_spec or "").strip()
-    speaker_name, _ = split_speaker_reference(spec)
-    if speaker_name and speaker_name in normalized_profiles:
-        entry = normalized_profiles[speaker_name]
-        provider = str(entry.get("provider") or "kokoro").strip().lower() or "kokoro"
-        if provider == "supertonic":
-            voice = str(entry.get("voice") or job_voice or "M1").strip() or "M1"
-            steps = int(entry.get("total_steps") or job_supertonic_total_steps or 5)
-            speed = float(entry.get("speed") or job_speed or 1.0)
-            return "supertonic", supertonic_voice_from_spec(voice, job_voice), speed, steps
-        formula = formula_from_kokoro_entry(entry)
-        return "kokoro", formula or spec, None, None
-
-    fallback_provider = str(job_tts_provider or "kokoro").strip().lower() or "kokoro"
-    inferred = infer_provider_from_spec(spec, fallback=fallback_provider)
-    if inferred == "supertonic":
-        return "supertonic", supertonic_voice_from_spec(spec, job_voice), None, None
-    return "kokoro", spec, None, None

abogen/frontend/__init__.py

@@ -0,0 +1,8 @@
+"""
+Abogen Flet Frontend Package.
+
+This package provides a unified, dual-target (desktop + web) user interface
+for the Abogen audiobook generation application, built with the Flet framework.
+"""
+
+__all__ = ["main"]

abogen/frontend/components/__init__.py

@@ -0,0 +1,32 @@
+"""Components sub-package."""
+from .widgets import (
+    resolve_icon,
+    build_drop_zone,
+    build_log_terminal,
+    log_entry,
+    build_progress_row,
+    build_primary_button,
+    build_secondary_button,
+    build_card,
+    build_section_header,
+    build_status_badge,
+    labelled_row,
+    show_snack,
+    build_divider,
+)
+
+__all__ = [
+    "build_drop_zone",
+    "resolve_icon",
+    "build_log_terminal",
+    "log_entry",
+    "build_progress_row",
+    "build_primary_button",
+    "build_secondary_button",
+    "build_card",
+    "build_section_header",
+    "build_status_badge",
+    "labelled_row",
+    "show_snack",
+    "build_divider",
+]

abogen/frontend/components/widgets.py

@@ -0,0 +1,630 @@
+"""
+Reusable UI components for the Abogen Flet frontend.
+
+Each function in this module returns a standalone Flet control or small
+widget tree.  Components read the current palette from the page's theme
+mode and should not hold any mutable state themselves – state lives in the
+session's ``AppState`` object.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Callable, List, Optional
+
+import flet as ft
+
+from ..utils.theme import get_palette, RADIUS_MD, RADIUS_SM, SPACE_SM, SPACE_MD, SPACE_LG
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+
+def resolve_icon(icon: Any) -> Any:
+    """Convert a snake_case icon name to Flet IconData when possible."""
+    if isinstance(icon, str):
+        return getattr(ft.Icons, icon.upper(), icon)
+    return icon
+
+
+# ---------------------------------------------------------------------------
+# Drop-zone (file input area)
+# ---------------------------------------------------------------------------
+
+
+def build_drop_zone(
+    *,
+    on_pick: Callable[[], None],
+    label: str = "Drag & drop your file here or click to browse",
+    sub_label: str = "Supports: .txt · .epub · .pdf · .md · .srt · .ass · .vtt",
+    accent: bool = False,
+    error: bool = False,
+    filename: Optional[str] = None,
+    file_size: Optional[str] = None,
+    char_count: Optional[str] = None,
+    page: Optional[ft.Page] = None,
+) -> ft.GestureDetector:
+    """
+    Build an interactive file drop-zone widget.
+
+    The zone shows a dashed border and centred instructions by default,
+    switching to an 'active' green style when a file is loaded and a red
+    style when an error has occurred.
+
+    Args:
+        on_pick: Callback invoked when the user clicks or activates the zone.
+        label: Primary instruction text.
+        sub_label: Secondary hint text shown beneath the label.
+        accent: When True, renders the 'active/success' green style.
+        error: When True, renders the 'error/red' style.
+        filename: When provided, replaces the instruction text with file info.
+        file_size: Human-readable file size to display alongside the filename.
+        char_count: Character count to display alongside file info.
+        page: The current Flet ``Page``; used to derive the active palette.
+
+    Returns:
+        A ``ft.GestureDetector`` wrapping the visual drop-zone container.
+    """
+    dark = page is not None and page.theme_mode == ft.ThemeMode.DARK
+    p = get_palette(page) if page else None
+
+    # Colour scheme
+    if error:
+        border_color = "#e84e3c" if dark else "#c0392b"
+        bg_color = "#1a0a08" if dark else "#fff5f5"
+        text_color = "#e84e3c" if dark else "#c0392b"
+        icon_name = "error_outline"
+    elif accent:
+        border_color = "#42ad4a" if dark else "#2e9437"
+        bg_color = "#091810" if dark else "#f0fff1"
+        text_color = "#42ad4a" if dark else "#2e9437"
+        icon_name = "check_circle_outline"
+    else:
+        border_color = "#3a4466" if dark else "#a8b4d0"
+        bg_color = "#151928" if dark else "#f7f8fd"
+        text_color = "#9ba3b8" if dark else "#5a6172"
+        icon_name = "upload_file"
+
+    if filename:
+        # Compact file-info display
+        info_rows: List[ft.Control] = [
+            ft.Row(
+                [
+                    ft.Icon(resolve_icon("insert_drive_file"), color=text_color, size=28),
+                    ft.Column(
+                        [
+                            ft.Text(
+                                filename,
+                                weight=ft.FontWeight.W_600,
+                                size=13,
+                                color=text_color,
+                                no_wrap=False,
+                                max_lines=2,
+                                overflow=ft.TextOverflow.ELLIPSIS,
+                            ),
+                        ],
+                        tight=True,
+                        expand=True,
+                    ),
+                ],
+                alignment=ft.MainAxisAlignment.CENTER,
+                spacing=SPACE_SM,
+            )
+        ]
+        if file_size or char_count:
+            chips: List[ft.Control] = []
+            if file_size:
+                chips.append(
+                    ft.Text(f"📄 {file_size}", size=11, color=text_color, italic=True)
+                )
+            if char_count:
+                chips.append(
+                    ft.Text(f"🔤 {char_count} chars", size=11, color=text_color, italic=True)
+                )
+            info_rows.append(
+                ft.Row(chips, alignment=ft.MainAxisAlignment.CENTER, spacing=SPACE_MD)
+            )
+        content = ft.Column(
+            info_rows,
+            alignment=ft.MainAxisAlignment.CENTER,
+            horizontal_alignment=ft.CrossAxisAlignment.CENTER,
+            spacing=SPACE_SM,
+        )
+    else:
+        content = ft.Column(
+            [
+                ft.Icon(resolve_icon(icon_name), size=48, color=border_color, opacity=0.8),
+                ft.Text(
+                    label,
+                    size=14,
+                    weight=ft.FontWeight.W_500,
+                    color=text_color,
+                    text_align=ft.TextAlign.CENTER,
+                ),
+                ft.Text(
+                    sub_label,
+                    size=11,
+                    color=text_color,
+                    opacity=0.6,
+                    text_align=ft.TextAlign.CENTER,
+                ),
+            ],
+            alignment=ft.MainAxisAlignment.CENTER,
+            horizontal_alignment=ft.CrossAxisAlignment.CENTER,
+            spacing=SPACE_SM,
+        )
+
+    inner = ft.Container(
+        content=content,
+        border=ft.Border.all(2, border_color),
+        border_radius=RADIUS_MD,
+        bgcolor=bg_color,
+        padding=ft.Padding.all(SPACE_LG),
+        height=160,
+        alignment=ft.Alignment.CENTER,
+        expand=True,
+    )
+
+    return ft.GestureDetector(
+        content=ft.Row([inner], spacing=0),
+        on_tap=lambda _: on_pick(),
+        mouse_cursor=ft.MouseCursor.CLICK,
+    )
+
+
+# ---------------------------------------------------------------------------
+# Log terminal
+# ---------------------------------------------------------------------------
+
+
+def build_log_terminal(
+    *,
+    ref: Optional[ft.Ref] = None,
+    max_height: int = 260,
+    page: Optional[ft.Page] = None,
+) -> ft.Container:
+    """
+    Build a scrollable, read-only log terminal widget.
+
+    Args:
+        ref: Optional ``ft.Ref[ft.ListView]`` to bind the inner list-view so
+             callers can append entries programmatically.
+        max_height: Maximum pixel height before vertical scrolling activates.
+        page: Current Flet ``Page`` for palette derivation.
+
+    Returns:
+        A styled ``ft.Container`` wrapping a ``ft.ListView``.
+    """
+    dark = page is not None and page.theme_mode == ft.ThemeMode.DARK
+    bg = "#0d1117" if dark else "#f8f9fc"
+    text_color = "#b0b8cc" if dark else "#3d4358"
+    border_color = "#252a38" if dark else "#dce0ea"
+
+    list_view = ft.ListView(
+        expand=True,
+        auto_scroll=True,
+        spacing=1,
+        padding=ft.Padding.all(SPACE_SM),
+    )
+    if ref is not None:
+        ref.current = list_view
+
+    return ft.Container(
+        content=list_view,
+        bgcolor=bg,
+        border=ft.Border.all(1, border_color),
+        border_radius=RADIUS_SM,
+        height=max_height,
+        clip_behavior=ft.ClipBehavior.HARD_EDGE,
+    )
+
+
+def log_entry(message: str, level: str = "info", page: Optional[ft.Page] = None) -> ft.Text:
+    """
+    Create a single log-line ``ft.Text`` widget with appropriate colour coding.
+
+    Args:
+        message: The log message string.
+        level: Severity string: ``'info'``, ``'success'``, ``'error'``,
+               ``'warning'``, ``'debug'``, ``'critical'``.
+        page: Current Flet ``Page`` for dark/light mode detection.
+
+    Returns:
+        A styled ``ft.Text`` control.
+    """
+    dark = page is not None and page.theme_mode == ft.ThemeMode.DARK
+    palette: dict[str, str] = {
+        "info": "#9ba3b8" if dark else "#5a6172",
+        "success": "#42ad4a" if dark else "#2e9437",
+        "error": "#e84e3c" if dark else "#c0392b",
+        "warning": "#f5a623" if dark else "#d4870a",
+        "debug": "#5a6172" if dark else "#9ba3b8",
+        "critical": "#ff5722",
+        "trace": "#4e5568" if dark else "#b0b8cc",
+    }
+    color = palette.get(level.lower(), palette["info"])
+    return ft.Text(message, size=12, color=color, selectable=True, no_wrap=False)
+
+
+# ---------------------------------------------------------------------------
+# Progress row
+# ---------------------------------------------------------------------------
+
+
+def build_progress_row(
+    *,
+    progress_value: float = 0.0,
+    etr_text: str = "",
+    page: Optional[ft.Page] = None,
+) -> ft.Column:
+    """
+    Build a progress-bar + ETR-label column.
+
+    Args:
+        progress_value: Float in [0.0, 1.0].
+        etr_text: Pre-formatted estimated-time-remaining string.
+        page: Current ``Page`` for palette derivation.
+
+    Returns:
+        A ``ft.Column`` containing the progress bar and label.
+    """
+    dark = page is not None and page.theme_mode == ft.ThemeMode.DARK
+    fill = "#5b8af5" if dark else "#3a5fc4"
+    bg = "#1e2230" if dark else "#e4e8f0"
+
+    bar = ft.ProgressBar(
+        value=progress_value,
+        color=fill,
+        bgcolor=bg,
+        height=8,
+        border_radius=ft.BorderRadius.all(4),
+        expand=True,
+    )
+    label = ft.Text(
+        etr_text,
+        size=11,
+        color="#9ba3b8" if dark else "#5a6172",
+        text_align=ft.TextAlign.CENTER,
+    )
+    return ft.Column(
+        [bar, label],
+        spacing=SPACE_SM,
+        horizontal_alignment=ft.CrossAxisAlignment.CENTER,
+    )
+
+
+# ---------------------------------------------------------------------------
+# Primary action button
+# ---------------------------------------------------------------------------
+
+
+def build_primary_button(
+    text: str,
+    *,
+    icon: Optional[str] = None,
+    on_click: Optional[Callable] = None,
+    disabled: bool = False,
+    width: Optional[int] = None,
+    page: Optional[ft.Page] = None,
+) -> ft.ElevatedButton:
+    """
+    Build a prominent, styled primary action button.
+
+    Args:
+        text: Button label.
+        icon: Optional Flet icon name (e.g. ``'play_arrow'``).
+        on_click: Click callback.
+        disabled: Whether the button is non-interactive.
+        width: Optional fixed pixel width.
+        page: Current ``Page`` for accent colour derivation.
+
+    Returns:
+        A styled ``ft.ElevatedButton``.
+    """
+    dark = page is not None and page.theme_mode == ft.ThemeMode.DARK
+    bg = "#5b8af5" if dark else "#3a5fc4"
+    on_bg = "#ffffff"
+
+    style = ft.ButtonStyle(
+        bgcolor={
+            ft.ControlState.DEFAULT: bg,
+            ft.ControlState.HOVERED: "#3a5fc4" if dark else "#2a4fae",
+            ft.ControlState.DISABLED: "#2a2f3f" if dark else "#c0c8d8",
+        },
+        color={
+            ft.ControlState.DEFAULT: on_bg,
+            ft.ControlState.DISABLED: "#4e5568" if dark else "#9ba3b8",
+        },
+        elevation={"default": 2, "hovered": 4},
+        padding=ft.Padding.symmetric(horizontal=SPACE_LG, vertical=SPACE_MD),
+        shape=ft.RoundedRectangleBorder(radius=RADIUS_SM),
+        animation_duration=150,
+    )
+
+    return ft.ElevatedButton(
+        content=text,
+        icon=resolve_icon(icon),
+        on_click=on_click,
+        disabled=disabled,
+        width=width,
+        style=style,
+        height=48,
+    )
+
+
+# ---------------------------------------------------------------------------
+# Secondary / ghost button
+# ---------------------------------------------------------------------------
+
+
+def build_secondary_button(
+    text: str,
+    *,
+    icon: Optional[str] = None,
+    on_click: Optional[Callable] = None,
+    disabled: bool = False,
+    page: Optional[ft.Page] = None,
+) -> ft.OutlinedButton:
+    """
+    Build a secondary outlined button.
+
+    Args:
+        text: Button label.
+        icon: Optional Flet icon name.
+        on_click: Click callback.
+        disabled: Whether the button is non-interactive.
+        page: Current ``Page`` for border colour derivation.
+
+    Returns:
+        A styled ``ft.OutlinedButton``.
+    """
+    dark = page is not None and page.theme_mode == ft.ThemeMode.DARK
+    border_clr = "#3a4466" if dark else "#a8b4d0"
+    text_clr = "#e8eaf0" if dark else "#1a1d27"
+
+    style = ft.ButtonStyle(
+        side={
+            ft.ControlState.DEFAULT: ft.BorderSide(1.5, border_clr),
+            ft.ControlState.HOVERED: ft.BorderSide(1.5, "#5b8af5" if dark else "#3a5fc4"),
+        },
+        color={
+            ft.ControlState.DEFAULT: text_clr,
+            ft.ControlState.HOVERED: "#5b8af5" if dark else "#3a5fc4",
+            ft.ControlState.DISABLED: "#4e5568" if dark else "#9ba3b8",
+        },
+        padding=ft.Padding.symmetric(horizontal=SPACE_LG, vertical=SPACE_MD),
+        shape=ft.RoundedRectangleBorder(radius=RADIUS_SM),
+        animation_duration=150,
+    )
+
+    return ft.OutlinedButton(
+        content=text,
+        icon=resolve_icon(icon),
+        on_click=on_click,
+        disabled=disabled,
+        style=style,
+        height=44,
+    )
+
+
+# ---------------------------------------------------------------------------
+# Section card
+# ---------------------------------------------------------------------------
+
+
+def build_card(
+    content: ft.Control,
+    *,
+    padding: int = SPACE_LG,
+    page: Optional[ft.Page] = None,
+) -> ft.Container:
+    """
+    Wrap a control in a styled card container.
+
+    Args:
+        content: The child control to embed.
+        padding: Internal padding in pixels.
+        page: Current ``Page`` for palette derivation.
+
+    Returns:
+        A styled ``ft.Container``.
+    """
+    dark = page is not None and page.theme_mode == ft.ThemeMode.DARK
+    bg = "#181b23" if dark else "#ffffff"
+    border_clr = "#2c3147" if dark else "#dce0ea"
+
+    return ft.Container(
+        content=content,
+        bgcolor=bg,
+        border=ft.Border.all(1, border_clr),
+        border_radius=RADIUS_MD,
+        padding=ft.Padding.all(padding),
+        shadow=ft.BoxShadow(
+            spread_radius=0,
+            blur_radius=12,
+            color=ft.Colors.with_opacity(0.12 if dark else 0.06, ft.Colors.BLACK),
+            offset=ft.Offset(0, 2),
+        ),
+    )
+
+
+# ---------------------------------------------------------------------------
+# Section header
+# ---------------------------------------------------------------------------
+
+
+def build_section_header(
+    title: str,
+    *,
+    subtitle: Optional[str] = None,
+    icon: Optional[str] = None,
+    page: Optional[ft.Page] = None,
+) -> ft.Row:
+    """
+    Build a consistent section header row with an optional icon.
+
+    Args:
+        title: Section heading text.
+        subtitle: Optional explanatory sub-text.
+        icon: Optional Flet icon name.
+        page: Current ``Page`` for palette derivation.
+
+    Returns:
+        A ``ft.Row`` containing the icon and text column.
+    """
+    dark = page is not None and page.theme_mode == ft.ThemeMode.DARK
+    title_color = "#e8eaf0" if dark else "#1a1d27"
+    sub_color = "#9ba3b8" if dark else "#5a6172"
+    accent = "#5b8af5" if dark else "#3a5fc4"
+
+    children: List[ft.Control] = []
+    if icon:
+        children.append(ft.Icon(resolve_icon(icon), size=20, color=accent))
+
+    text_parts: List[ft.Control] = [
+        ft.Text(title, size=15, weight=ft.FontWeight.W_600, color=title_color)
+    ]
+    if subtitle:
+        text_parts.append(ft.Text(subtitle, size=11, color=sub_color))
+
+    children.append(
+        ft.Column(text_parts, spacing=1, tight=True, expand=True)
+    )
+
+    return ft.Row(children, spacing=SPACE_SM, vertical_alignment=ft.CrossAxisAlignment.START)
+
+
+# ---------------------------------------------------------------------------
+# Status badge
+# ---------------------------------------------------------------------------
+
+
+def build_status_badge(
+    label: str,
+    *,
+    variant: str = "info",
+    page: Optional[ft.Page] = None,
+) -> ft.Container:
+    """
+    Build a small status badge chip.
+
+    Args:
+        label: Badge text.
+        variant: Colour variant: ``'info'``, ``'success'``, ``'error'``,
+                 ``'warning'``, ``'neutral'``.
+        page: Current ``Page`` for theme derivation.
+
+    Returns:
+        A pill-shaped ``ft.Container``.
+    """
+    dark = page is not None and page.theme_mode == ft.ThemeMode.DARK
+    palette = {
+        "info":    ("#1a2a5e" if dark else "#dde8ff", "#5b8af5" if dark else "#3a5fc4"),
+        "success": ("#0d2010" if dark else "#d4f4d7", "#42ad4a" if dark else "#2e9437"),
+        "error":   ("#2a0a08" if dark else "#ffe0dc", "#e84e3c" if dark else "#c0392b"),
+        "warning": ("#2a1a00" if dark else "#fff4d8", "#f5a623" if dark else "#d4870a"),
+        "neutral": ("#1e2230" if dark else "#edf0f5", "#9ba3b8" if dark else "#5a6172"),
+    }
+    bg, fg = palette.get(variant, palette["info"])
+
+    return ft.Container(
+        content=ft.Text(label, size=10, weight=ft.FontWeight.W_600, color=fg),
+        bgcolor=bg,
+        border_radius=999,
+        padding=ft.Padding.symmetric(horizontal=8, vertical=3),
+    )
+
+
+# ---------------------------------------------------------------------------
+# Labelled control row
+# ---------------------------------------------------------------------------
+
+
+def labelled_row(
+    label: str,
+    control: ft.Control,
+    *,
+    label_width: int = 200,
+    tooltip: Optional[str] = None,
+    page: Optional[ft.Page] = None,
+) -> ft.Row:
+    """
+    Lay a label and a control side-by-side in a consistent row.
+
+    Args:
+        label: Human-readable label text.
+        control: The UI control placed to the right of the label.
+        label_width: Fixed pixel width of the label column.
+        tooltip: Optional tooltip text on the label.
+        page: Current ``Page`` for palette derivation.
+
+    Returns:
+        A ``ft.Row`` with the label pinned to a fixed width.
+    """
+    dark = page is not None and page.theme_mode == ft.ThemeMode.DARK
+    lbl_color = "#9ba3b8" if dark else "#5a6172"
+
+    lbl = ft.Text(label, size=13, color=lbl_color, weight=ft.FontWeight.W_500, width=label_width)
+    if tooltip:
+        lbl.tooltip = tooltip
+
+    return ft.Row(
+        [lbl, ft.Container(content=control, expand=True)],
+        alignment=ft.MainAxisAlignment.START,
+        vertical_alignment=ft.CrossAxisAlignment.CENTER,
+        spacing=SPACE_MD,
+    )
+
+
+# ---------------------------------------------------------------------------
+# Snack-bar helper
+# ---------------------------------------------------------------------------
+
+
+def show_snack(
+    page: ft.Page,
+    message: str,
+    *,
+    error: bool = False,
+    duration: int = 3000,
+) -> None:
+    """
+    Display a brief snack-bar notification.
+
+    Args:
+        page: The Flet ``Page`` instance.
+        message: Text to display.
+        error: When True, colours the bar red instead of the default accent.
+        duration: Visible duration in milliseconds.
+    """
+    dark = page.theme_mode == ft.ThemeMode.DARK
+    bg = "#e84e3c" if error else ("#5b8af5" if dark else "#3a5fc4")
+    page.snack_bar = ft.SnackBar(
+        content=ft.Text(message, color="#ffffff", size=13),
+        bgcolor=bg,
+        duration=duration,
+        show_close_icon=True,
+        close_icon_color="#ffffff",
+    )
+    page.snack_bar.open = True
+    page.update()
+
+
+# ---------------------------------------------------------------------------
+# Divider helper
+# ---------------------------------------------------------------------------
+
+
+def build_divider(page: Optional[ft.Page] = None) -> ft.Divider:
+    """
+    Build a styled horizontal rule divider.
+
+    Args:
+        page: Current ``Page`` for palette derivation.
+
+    Returns:
+        A ``ft.Divider``.
+    """
+    dark = page is not None and page.theme_mode == ft.ThemeMode.DARK
+    return ft.Divider(color="#252a38" if dark else "#e8ebf2", height=1, thickness=1)

abogen/frontend/main.py

@@ -0,0 +1,365 @@
+"""
+Abogen Flet Frontend – main entry point.
+
+Run as desktop app:
+    python -m abogen.frontend.main
+
+Run as web app (binds to port 8080 by default):
+    python -m abogen.frontend.main --web --port 8080
+
+Architecture
+------------
+One ``ft.app()`` call launches the server.  For every new browser tab (or the
+desktop window) Flet invokes ``_app_entry(page)`` in its own coroutine, which
+creates a fresh ``AppState`` and wires together the navigation rail and views.
+This guarantees complete per-session isolation in multi-user web deployments.
+"""
+from __future__ import annotations
+
+import argparse
+import sys
+from pathlib import Path
+from typing import Optional
+
+import flet as ft
+
+from .state import AppState
+from .components import resolve_icon
+from .views.dashboard import DashboardView
+from .views.settings import SettingsView
+from .views.queue_view import QueueView
+from .utils.theme import make_theme, DARK, LIGHT, SPACE_SM, SPACE_MD, SPACE_LG, RADIUS_MD
+from abogen.constants import PROGRAM_NAME as APP_NAME
+
+
+# ---------------------------------------------------------------------------
+# Navigation destinations
+# ---------------------------------------------------------------------------
+
+_NAV_ITEMS = [
+    ("Convert", "swap_horiz", "swap_horiz"),
+    ("Queue",   "list_alt",   "list_alt"),
+    ("Settings", "settings",  "settings"),
+]
+
+_ASSETS_DIR = Path(__file__).resolve().parents[1] / "assets"
+
+
+def _build_sidebar_item(
+    *,
+    label: str,
+    icon: str,
+    selected: bool,
+    palette,
+    on_click,
+) -> ft.Container:
+    accent = palette.accent if selected else palette.text_secondary
+    bg = palette.sidebar_selected_bg if selected else palette.sidebar_bg
+    return ft.Container(
+        content=ft.Row(
+            [
+                ft.Icon(resolve_icon(icon), size=20, color=accent),
+                ft.Text(
+                    label,
+                    size=13,
+                    weight=ft.FontWeight.W_600 if selected else ft.FontWeight.W_500,
+                    color=accent,
+                ),
+            ],
+            spacing=SPACE_MD,
+            vertical_alignment=ft.CrossAxisAlignment.CENTER,
+        ),
+        bgcolor=bg,
+        border_radius=RADIUS_MD,
+        padding=ft.Padding.symmetric(horizontal=SPACE_MD, vertical=10),
+        ink=True,
+        on_click=on_click,
+    )
+
+
+# ---------------------------------------------------------------------------
+# Per-session entry point
+# ---------------------------------------------------------------------------
+
+def _app_entry(page: ft.Page) -> None:
+    try:
+        # ── State ────────────────────────────────────────────────────────────
+        state = AppState()
+        state.load_from_config()
+
+        # ── Page basics ──────────────────────────────────────────────────────
+        page.title = APP_NAME
+        page.padding = 0
+        page.spacing = 0
+        page.bgcolor = DARK.bg_base
+        page.theme_mode = ft.ThemeMode.DARK
+        page.theme = make_theme(dark=True)
+        page.dark_theme = make_theme(dark=True)
+        page.fonts = {}
+        page.window.min_width = 520
+        page.window.min_height = 600
+        page.update()
+
+        # ── Content area ref ─────────────────────────────────────────────────
+        content_area = ft.Column(expand=True, spacing=0)
+        sidebar_body = ft.Column(spacing=SPACE_SM)
+        theme_button_host = ft.Container()
+        brand_title = ft.Text(
+            APP_NAME,
+            size=18,
+            weight=ft.FontWeight.W_700,
+            color=DARK.text_primary,
+        )
+        brand_fallback_icon = ft.Icon(resolve_icon("speaker_notes"), size=32, color=DARK.accent)
+        divider = ft.VerticalDivider(width=1, color=DARK.border)
+
+        # ── Views ────────────────────────────────────────────────────────────
+        dashboard_view = DashboardView(page, state)
+        settings_view = SettingsView(page, state)
+        queue_view = QueueView(page, state)
+
+        views = [
+            dashboard_view.build,
+            queue_view.build,
+            settings_view.build,
+        ]
+        _selected_index = [0]
+
+        def _refresh_sidebar() -> None:
+            dark = page.theme_mode == ft.ThemeMode.DARK
+            pal = DARK if dark else LIGHT
+            sidebar_body.controls = [
+                _build_sidebar_item(
+                    label=label,
+                    icon=icon,
+                    selected=index == _selected_index[0],
+                    palette=pal,
+                    on_click=lambda _, i=index: _navigate(i),
+                )
+                for index, (label, icon, _) in enumerate(_NAV_ITEMS)
+            ]
+            sidebar.bgcolor = pal.sidebar_bg
+            divider.color = pal.border
+            brand_title.color = pal.text_primary
+            brand_fallback_icon.color = pal.accent
+            theme_button_host.content = ft.Container(
+                content=ft.Icon(
+                    resolve_icon("dark_mode" if dark else "light_mode"),
+                    size=20,
+                    color=pal.text_secondary,
+                ),
+                tooltip="Toggle theme",
+                border_radius=RADIUS_MD,
+                padding=8,
+                ink=True,
+                on_click=lambda _: _toggle_theme(page, _refresh_sidebar),
+            )
+
+        def _navigate(index: int) -> None:
+            _selected_index[0] = index
+            content_area.controls.clear()
+            built = views[index]()
+            content_area.controls.append(
+                ft.Container(
+                    content=built,
+                    expand=True,
+                    padding=ft.Padding.symmetric(horizontal=SPACE_LG, vertical=SPACE_LG),
+                )
+            )
+            _refresh_sidebar()
+            page.update()
+
+        # ── Sidebar ──────────────────────────────────────────────────────────
+        pal = DARK
+        sidebar = ft.Container(
+            width=220,
+            bgcolor=pal.sidebar_bg,
+            padding=ft.Padding.all(SPACE_MD),
+            content=ft.Column(
+                [
+                    ft.Container(
+                        content=ft.Row(
+                            [
+                                ft.Image(
+                                    src="icon.png",
+                                    width=36,
+                                    height=36,
+                                    fit=ft.BoxFit.CONTAIN,
+                                    error_content=brand_fallback_icon,
+                                ),
+                                brand_title,
+                            ],
+                            spacing=SPACE_MD,
+                            vertical_alignment=ft.CrossAxisAlignment.CENTER,
+                        ),
+                        padding=ft.Padding.only(top=SPACE_SM, bottom=SPACE_LG),
+                    ),
+                    sidebar_body,
+                    ft.Container(expand=True),
+                    ft.Row([theme_button_host], alignment=ft.MainAxisAlignment.END),
+                ],
+                expand=True,
+                spacing=SPACE_SM,
+            ),
+        )
+        _refresh_sidebar()
+
+        # ── Page handle for pubsub (queue → dashboard) ───────────────────────
+        def _handle_pubsub(topic: str) -> None:
+            if topic == "start_queue":
+                _navigate(0)
+
+        page.pubsub.subscribe(_handle_pubsub)
+
+        # ── Layout ────────────────────────────────────────────────────────────
+        page.add(
+            ft.Row(
+                [
+                    sidebar,
+                    divider,
+                    ft.Container(content=content_area, expand=True),
+                ],
+                expand=True,
+                spacing=0,
+                vertical_alignment=ft.CrossAxisAlignment.START,
+            )
+        )
+
+        # Show dashboard by default
+        _navigate(0)
+        page.update()
+    except Exception as e:
+        import traceback
+        traceback.print_exc()
+        print(f"ERROR IN _app_entry: {e}")
+        raise
+
+
+def _toggle_theme(page: ft.Page, refresh_sidebar) -> None:
+    """Switch between dark and light theme modes."""
+    if page.theme_mode == ft.ThemeMode.DARK:
+        page.theme_mode = ft.ThemeMode.LIGHT
+        page.bgcolor = LIGHT.bg_base
+    else:
+        page.theme_mode = ft.ThemeMode.DARK
+        page.bgcolor = DARK.bg_base
+
+    page.theme = make_theme(page.theme_mode == ft.ThemeMode.DARK)
+    refresh_sidebar()
+    page.update()
+
+
+# ---------------------------------------------------------------------------
+# CLI helpers & entry point
+# ---------------------------------------------------------------------------
+
+def _is_port_free(host: str, port: int) -> bool:
+    import socket
+    try:
+        with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
+            s.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
+            s.bind((host, port))
+            return True
+    except OSError:
+        return False
+
+
+def _find_free_port(host: str, start_port: int) -> int:
+    import socket
+    port = start_port
+    while port < 65535:
+        try:
+            with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
+                s.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
+                s.bind((host, port))
+                return port
+        except OSError:
+            port += 1
+    return start_port
+
+
+def main() -> None:
+    """
+    Start the Abogen Flet frontend.
+
+    Parses ``--web`` and ``--port`` CLI arguments to choose desktop vs. web
+    mode, then hands control to ``ft.app()``.
+    """
+    import logging
+    logging.basicConfig(level=logging.INFO)
+    logging.getLogger("flet").setLevel(logging.INFO)
+
+    parser = argparse.ArgumentParser(description=f"{APP_NAME} – Flet frontend")
+    parser.add_argument(
+        "--web", action="store_true",
+        help="Run as a web server instead of a desktop window.",
+    )
+    parser.add_argument(
+        "--port", type=int, default=8080,
+        help="Port for the web server (default: 8080). Ignored in desktop mode.",
+    )
+    parser.add_argument(
+        "--host", default="127.0.0.1",
+        help="Host for the web server (default: 127.0.0.1). Use 0.0.0.0 to expose publicly.",
+    )
+    args = parser.parse_args()
+
+    if args.web:
+        port_specified = "--port" in sys.argv
+        target_port = args.port
+
+        if not port_specified:
+            target_port = _find_free_port(args.host, 8080)
+            if target_port != 8080:
+                print(f"Port 8080 is in use. Automatically routed to free port: {target_port}")
+        else:
+            if not _is_port_free(args.host, target_port):
+                print(f"Error: Port {target_port} is already in use on {args.host}.", file=sys.stderr)
+                print("Please select a different port or omit the --port flag to find one automatically.", file=sys.stderr)
+                sys.exit(1)
+
+        print(f"Starting Abogen WebUI on http://{args.host}:{target_port} ...")
+        ft.app(
+            target=_app_entry,
+            view=ft.AppView.WEB_BROWSER,
+            port=target_port,
+            host=args.host,
+            assets_dir=str(_ASSETS_DIR) if _ASSETS_DIR.exists() else None,
+            no_cdn=True,
+            web_renderer="canvaskit",
+        )
+    else:
+        try:
+            ft.app(
+                target=_app_entry,
+                view=ft.AppView.FLET_APP,
+                assets_dir=str(_ASSETS_DIR) if _ASSETS_DIR.exists() else None,
+            )
+        except Exception as e:
+            print(f"Warning: Failed to launch native desktop window: {e}", file=sys.stderr)
+            print("Falling back to running as a web application in your default browser...", file=sys.stderr)
+            target_port = _find_free_port("127.0.0.1", 8080)
+            print(f"Starting Abogen WebUI on http://127.0.0.1:{target_port} ...")
+            ft.app(
+                target=_app_entry,
+                view=ft.AppView.WEB_BROWSER,
+                port=target_port,
+                host="127.0.0.1",
+                assets_dir=str(_ASSETS_DIR) if _ASSETS_DIR.exists() else None,
+                no_cdn=True,
+                web_renderer="canvaskit",
+            )
+
+
+def main_web() -> None:
+    """
+    Start the Abogen Flet frontend as a web server.
+    """
+    import sys
+    if "--web" not in sys.argv:
+        sys.argv.insert(1, "--web")
+    main()
+
+
+if __name__ == "__main__":
+    main()

abogen/frontend/state/__init__.py

@@ -0,0 +1,4 @@
+"""State sub-package – exports AppState and ConversionJob."""
+from .app_state import AppState, ConversionJob
+
+__all__ = ["AppState", "ConversionJob"]

abogen/frontend/state/app_state.py

@@ -0,0 +1,451 @@
+"""
+Centralized, per-session application state for the Abogen Flet frontend.
+
+Each Flet page (session) gets its own instance of AppState, which guarantees
+complete isolation between simultaneous web-browser clients and the desktop
+window. The class carries every configuration variable, file buffer reference,
+and generation progress field that the rest of the UI reads or writes.
+
+This module intentionally has no Flet imports so it can be unit-tested without
+a running Flet server.
+"""
+
+from __future__ import annotations
+
+import threading
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Any, Callable, Dict, List, Optional
+
+from abogen.utils import load_config, save_config
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+
+def _default_config() -> Dict[str, Any]:
+    """Load the persisted user config dict, returning an empty dict on failure."""
+    try:
+        return load_config() or {}
+    except Exception:
+        return {}
+
+
+# ---------------------------------------------------------------------------
+# Per-session state
+# ---------------------------------------------------------------------------
+
+
+@dataclass
+class ConversionJob:
+    """Lightweight descriptor of a single queued conversion job."""
+
+    file_path: str
+    """Absolute path to the text/epub/pdf/txt input file."""
+
+    display_name: str
+    """User-visible filename (may be the original epub/pdf path)."""
+
+    voice: str
+    """Voice formula string (e.g. 'af_heart' or 'af_heart*0.5+am_adam*0.5')."""
+
+    lang_code: str
+    """Single-char language prefix used by Kokoro (e.g. 'a', 'b', 'e')."""
+
+    speed: float = 1.0
+    """Playback speed multiplier, range 0.1 – 2.0."""
+
+    output_format: str = "mp3"
+    """Output audio container format."""
+
+    subtitle_mode: str = "Disabled"
+    """Subtitle generation mode."""
+
+    save_option: str = "Save next to input file"
+    """Save location strategy."""
+
+    output_folder: Optional[str] = None
+    """Absolute path when save_option is 'Choose output folder'."""
+
+    char_count: int = 0
+    """Pre-computed character count for ETR estimation."""
+
+    replace_single_newlines: bool = True
+    save_chapters_separately: Optional[bool] = None
+    merge_chapters_at_end: Optional[bool] = None
+
+
+@dataclass
+class AppState:
+    """
+    Single source of truth for one Flet session.
+
+    Instantiated once per ``ft.app()`` call on desktop, and once per browser
+    tab on web.  All UI components receive a reference to this object and
+    read/write it to keep themselves in sync.
+
+    Thread-safety: mutation from background threads should be done via the
+    provided ``_lock``.  The UI update callbacks (``on_log``,
+    ``on_progress``, etc.) are always invoked on the Flet event loop via
+    ``page.run_task()`` and must be set by the view layer.
+    """
+
+    # -----------------------------------------------------------------------
+    # Runtime identity
+    # -----------------------------------------------------------------------
+    _lock: threading.Lock = field(default_factory=threading.Lock, repr=False, compare=False)
+
+    # -----------------------------------------------------------------------
+    # Persisted user config (loaded once, written on every change)
+    # -----------------------------------------------------------------------
+    config: Dict[str, Any] = field(default_factory=_default_config)
+
+    # -----------------------------------------------------------------------
+    # File / input state
+    # -----------------------------------------------------------------------
+    selected_file: Optional[str] = None
+    """Path to the processed text file (may be a temp cache copy for epub/pdf)."""
+
+    selected_file_type: Optional[str] = None
+    """'txt' | 'epub' | 'pdf' | 'markdown' | None"""
+
+    selected_book_path: Optional[str] = None
+    """Original epub/pdf path before being converted to txt."""
+
+    displayed_file_path: Optional[str] = None
+    """Path shown in the UI drop-zone (original book or txt file)."""
+
+    selected_chapters: List[str] = field(default_factory=list)
+    """Ordered list of selected chapter href tokens (or page numbers for PDFs)."""
+
+    save_chapters_separately: Optional[bool] = None
+    merge_chapters_at_end: Optional[bool] = None
+    save_as_project: bool = False
+    char_count: int = 0
+
+    # -----------------------------------------------------------------------
+    # Voice / language
+    # -----------------------------------------------------------------------
+    selected_voice: str = "af_heart"
+    selected_lang: str = "a"
+    selected_profile_name: Optional[str] = None
+    mixed_voice_state: Optional[List[Any]] = None
+    """List of [voice_id, weight] pairs when the formula mixer is in use."""
+
+    # -----------------------------------------------------------------------
+    # Conversion parameters
+    # -----------------------------------------------------------------------
+    speed: float = 1.0
+    use_gpu: bool = True
+    selected_format: str = "wav"
+    subtitle_mode: str = "Sentence"
+    subtitle_format: str = "ass_centered_narrow"
+    replace_single_newlines: bool = True
+    save_option: str = "Save next to input file"
+    selected_output_folder: Optional[str] = None
+    silence_duration: float = 2.0
+    max_subtitle_words: int = 50
+    separate_chapters_format: str = "wav"
+    use_silent_gaps: bool = True
+    subtitle_speed_method: str = "tts"
+    use_spacy_segmentation: bool = True
+    chunk_level: str = "paragraph"
+    generate_epub3: bool = False
+
+    # TTS provider
+    tts_provider: str = "kokoro"
+    supertonic_total_steps: int = 5
+
+    # Chapter options
+    chapter_intro_delay: float = 0.5
+    read_title_intro: bool = False
+    read_closing_outro: bool = True
+    auto_prefix_chapter_titles: bool = True
+    normalize_chapter_opening_caps: bool = True
+
+    # Speaker analysis
+    speaker_analysis_threshold: int = 3
+
+    # Word substitutions
+    word_substitutions_enabled: bool = False
+    word_substitutions_list: str = ""
+    case_sensitive_substitutions: bool = False
+    replace_all_caps: bool = False
+    replace_numerals: bool = False
+    fix_nonstandard_punctuation: bool = False
+
+    # -----------------------------------------------------------------------
+    # Conversion runtime state
+    # -----------------------------------------------------------------------
+    is_converting: bool = False
+    is_cancelled: bool = False
+    progress: float = 0.0
+    """Fractional progress 0.0 – 1.0."""
+    etr_seconds: Optional[float] = None
+    """Estimated seconds remaining, or None if unknown."""
+    last_output_path: Optional[str] = None
+    log_lines: List[str] = field(default_factory=list)
+    """Buffered log messages, capped at LOG_MAX_LINES."""
+
+    LOG_MAX_LINES: int = 2000
+
+    # -----------------------------------------------------------------------
+    # Queue
+    # -----------------------------------------------------------------------
+    queued_items: List[ConversionJob] = field(default_factory=list)
+    current_queue_index: int = 0
+
+    # -----------------------------------------------------------------------
+    # Callbacks (set by the view layer, not serialised)
+    # -----------------------------------------------------------------------
+    on_log: Optional[Callable[[str, str], None]] = field(default=None, repr=False, compare=False)
+    """Called from any thread: ``on_log(message, level)``."""
+
+    on_progress: Optional[Callable[[float, Optional[float]], None]] = field(
+        default=None, repr=False, compare=False
+    )
+    """Called from any thread: ``on_progress(fraction, etr_seconds)``."""
+
+    on_conversion_finished: Optional[Callable[[str, Optional[str]], None]] = field(
+        default=None, repr=False, compare=False
+    )
+    """Called from any thread: ``on_conversion_finished(message, output_path)``."""
+
+    # -----------------------------------------------------------------------
+    # Integrations
+    # -----------------------------------------------------------------------
+    audiobookshelf_enabled: bool = False
+    audiobookshelf_base_url: str = ""
+    audiobookshelf_api_token: str = ""
+    audiobookshelf_library_id: str = ""
+    audiobookshelf_folder_id: str = ""
+    audiobookshelf_verify_ssl: bool = True
+    audiobookshelf_auto_send: bool = False
+    audiobookshelf_send_cover: bool = True
+    audiobookshelf_send_chapters: bool = True
+    audiobookshelf_send_subtitles: bool = False
+    audiobookshelf_timeout: float = 30.0
+
+    calibre_opds_enabled: bool = False
+    calibre_opds_base_url: str = ""
+    calibre_opds_username: str = ""
+    calibre_opds_password: str = ""
+    calibre_opds_verify_ssl: bool = True
+
+    # -----------------------------------------------------------------------
+    # Public helpers
+    # -----------------------------------------------------------------------
+
+    def load_from_config(self) -> None:
+        """
+        Populate all fields from the persisted JSON config file.
+
+        Called once at startup and whenever the settings page is saved.
+        Thread-safe.
+        """
+        with self._lock:
+            cfg = _default_config()
+            self.config = cfg
+
+            self.selected_voice = cfg.get("selected_voice", "af_heart")
+            self.selected_lang = self.selected_voice[0] if self.selected_voice else "a"
+            self.selected_profile_name = cfg.get("selected_profile_name")
+            self.speed = cfg.get("speed", 1.0)
+            self.use_gpu = cfg.get("use_gpu", True)
+            self.selected_format = cfg.get("selected_format", "wav")
+            self.subtitle_mode = cfg.get("subtitle_mode", "Sentence")
+            self.subtitle_format = cfg.get("subtitle_format", "ass_centered_narrow")
+            self.replace_single_newlines = cfg.get("replace_single_newlines", True)
+            self.save_option = cfg.get("save_option", "Save next to input file")
+            self.selected_output_folder = cfg.get("selected_output_folder")
+            self.silence_duration = cfg.get("silence_duration", 2.0)
+            self.max_subtitle_words = cfg.get("max_subtitle_words", 50)
+            self.separate_chapters_format = cfg.get("separate_chapters_format", "wav")
+            self.use_silent_gaps = cfg.get("use_silent_gaps", True)
+            self.subtitle_speed_method = cfg.get("subtitle_speed_method", "tts")
+            self.use_spacy_segmentation = cfg.get("use_spacy_segmentation", True)
+            self.chunk_level = cfg.get("chunk_level", "paragraph")
+            self.generate_epub3 = cfg.get("generate_epub3", False)
+            self.tts_provider = cfg.get("tts_provider", "kokoro")
+            self.supertonic_total_steps = cfg.get("supertonic_total_steps", 5)
+            self.chapter_intro_delay = cfg.get("chapter_intro_delay", 0.5)
+            self.read_title_intro = cfg.get("read_title_intro", False)
+            self.read_closing_outro = cfg.get("read_closing_outro", True)
+            self.auto_prefix_chapter_titles = cfg.get("auto_prefix_chapter_titles", True)
+            self.normalize_chapter_opening_caps = cfg.get("normalize_chapter_opening_caps", True)
+            self.speaker_analysis_threshold = cfg.get("speaker_analysis_threshold", 3)
+            self.word_substitutions_enabled = cfg.get("word_substitutions_enabled", False)
+            self.word_substitutions_list = cfg.get("word_substitutions_list", "")
+            self.case_sensitive_substitutions = cfg.get("case_sensitive_substitutions", False)
+            self.replace_all_caps = cfg.get("replace_all_caps", False)
+            self.replace_numerals = cfg.get("replace_numerals", False)
+            self.fix_nonstandard_punctuation = cfg.get("fix_nonstandard_punctuation", False)
+
+            # Integrations
+            integrations: Dict[str, Any] = cfg.get("integrations", {})
+            abs_cfg = integrations.get("audiobookshelf", {})
+            self.audiobookshelf_enabled = bool(abs_cfg.get("enabled", False))
+            self.audiobookshelf_base_url = str(abs_cfg.get("base_url", ""))
+            self.audiobookshelf_api_token = str(abs_cfg.get("api_token", ""))
+            self.audiobookshelf_library_id = str(abs_cfg.get("library_id", ""))
+            self.audiobookshelf_folder_id = str(abs_cfg.get("folder_id", ""))
+            self.audiobookshelf_verify_ssl = bool(abs_cfg.get("verify_ssl", True))
+            self.audiobookshelf_auto_send = bool(abs_cfg.get("auto_send", False))
+            self.audiobookshelf_send_cover = bool(abs_cfg.get("send_cover", True))
+            self.audiobookshelf_send_chapters = bool(abs_cfg.get("send_chapters", True))
+            self.audiobookshelf_send_subtitles = bool(abs_cfg.get("send_subtitles", False))
+            self.audiobookshelf_timeout = float(abs_cfg.get("timeout", 30.0))
+
+            cal_cfg = integrations.get("calibre_opds", {})
+            self.calibre_opds_enabled = bool(cal_cfg.get("enabled", False))
+            self.calibre_opds_base_url = str(cal_cfg.get("base_url", ""))
+            self.calibre_opds_username = str(cal_cfg.get("username", ""))
+            self.calibre_opds_password = str(cal_cfg.get("password", ""))
+            self.calibre_opds_verify_ssl = bool(cal_cfg.get("verify_ssl", True))
+
+    def persist_config(self) -> None:
+        """
+        Write the current config snapshot back to disk.
+
+        Only the fields that map to the JSON config are written; runtime state
+        (progress, log_lines, callbacks) is not persisted.
+        Thread-safe.
+        """
+        with self._lock:
+            cfg = self.config.copy()
+            cfg["selected_voice"] = self.selected_voice
+            cfg["selected_profile_name"] = self.selected_profile_name
+            cfg["speed"] = self.speed
+            cfg["use_gpu"] = self.use_gpu
+            cfg["selected_format"] = self.selected_format
+            cfg["subtitle_mode"] = self.subtitle_mode
+            cfg["subtitle_format"] = self.subtitle_format
+            cfg["replace_single_newlines"] = self.replace_single_newlines
+            cfg["save_option"] = self.save_option
+            cfg["selected_output_folder"] = self.selected_output_folder
+            cfg["silence_duration"] = self.silence_duration
+            cfg["max_subtitle_words"] = self.max_subtitle_words
+            cfg["separate_chapters_format"] = self.separate_chapters_format
+            cfg["use_silent_gaps"] = self.use_silent_gaps
+            cfg["subtitle_speed_method"] = self.subtitle_speed_method
+            cfg["use_spacy_segmentation"] = self.use_spacy_segmentation
+            cfg["chunk_level"] = self.chunk_level
+            cfg["generate_epub3"] = self.generate_epub3
+            cfg["tts_provider"] = self.tts_provider
+            cfg["supertonic_total_steps"] = self.supertonic_total_steps
+            cfg["chapter_intro_delay"] = self.chapter_intro_delay
+            cfg["read_title_intro"] = self.read_title_intro
+            cfg["read_closing_outro"] = self.read_closing_outro
+            cfg["auto_prefix_chapter_titles"] = self.auto_prefix_chapter_titles
+            cfg["normalize_chapter_opening_caps"] = self.normalize_chapter_opening_caps
+            cfg["speaker_analysis_threshold"] = self.speaker_analysis_threshold
+            cfg["word_substitutions_enabled"] = self.word_substitutions_enabled
+            cfg["word_substitutions_list"] = self.word_substitutions_list
+            cfg["case_sensitive_substitutions"] = self.case_sensitive_substitutions
+            cfg["replace_all_caps"] = self.replace_all_caps
+            cfg["replace_numerals"] = self.replace_numerals
+            cfg["fix_nonstandard_punctuation"] = self.fix_nonstandard_punctuation
+            # Integrations
+            cfg.setdefault("integrations", {})
+            cfg["integrations"]["audiobookshelf"] = {
+                "enabled": self.audiobookshelf_enabled,
+                "base_url": self.audiobookshelf_base_url,
+                "api_token": self.audiobookshelf_api_token,
+                "library_id": self.audiobookshelf_library_id,
+                "folder_id": self.audiobookshelf_folder_id,
+                "verify_ssl": self.audiobookshelf_verify_ssl,
+                "auto_send": self.audiobookshelf_auto_send,
+                "send_cover": self.audiobookshelf_send_cover,
+                "send_chapters": self.audiobookshelf_send_chapters,
+                "send_subtitles": self.audiobookshelf_send_subtitles,
+                "timeout": self.audiobookshelf_timeout,
+            }
+            cfg["integrations"]["calibre_opds"] = {
+                "enabled": self.calibre_opds_enabled,
+                "base_url": self.calibre_opds_base_url,
+                "username": self.calibre_opds_username,
+                "password": self.calibre_opds_password,
+                "verify_ssl": self.calibre_opds_verify_ssl,
+            }
+            self.config = cfg
+            try:
+                save_config(cfg)
+            except Exception:
+                pass
+
+    def append_log(self, message: str, level: str = "info") -> None:
+        """
+        Thread-safely append a log line and trigger the UI callback.
+
+        Caps the internal buffer at ``LOG_MAX_LINES`` to prevent unbounded
+        memory growth during very long conversion tasks.
+        """
+        with self._lock:
+            self.log_lines.append(f"[{level.upper()}] {message}")
+            if len(self.log_lines) > self.LOG_MAX_LINES:
+                # Trim oldest 10 % to amortise the cost of trimming
+                trim = self.LOG_MAX_LINES // 10
+                self.log_lines = self.log_lines[trim:]
+
+        cb = self.on_log
+        if cb is not None:
+            try:
+                cb(message, level)
+            except Exception:
+                pass
+
+    def update_progress(self, fraction: float, etr: Optional[float] = None) -> None:
+        """
+        Update fractional progress and ETR, then notify the UI callback.
+
+        Args:
+            fraction: Value in [0.0, 1.0].
+            etr: Estimated seconds remaining, or None.
+        """
+        with self._lock:
+            self.progress = max(0.0, min(1.0, fraction))
+            self.etr_seconds = etr
+
+        cb = self.on_progress
+        if cb is not None:
+            try:
+                cb(fraction, etr)
+            except Exception:
+                pass
+
+    def get_voice_formula(self) -> str:
+        """
+        Return the effective voice formula string.
+
+        Uses the mixed_voice_state if the formula mixer is active, otherwise
+        returns the raw selected_voice.
+        """
+        if self.mixed_voice_state:
+            parts = [f"{name}*{weight}" for name, weight in self.mixed_voice_state]
+            return " + ".join(filter(None, parts))
+        return self.selected_voice or "af_heart"
+
+    def reset_file_state(self) -> None:
+        """Clear all file-related fields without touching voice/settings."""
+        with self._lock:
+            self.selected_file = None
+            self.selected_file_type = None
+            self.selected_book_path = None
+            self.displayed_file_path = None
+            self.selected_chapters = []
+            self.save_chapters_separately = None
+            self.merge_chapters_at_end = None
+            self.save_as_project = False
+            self.char_count = 0
+
+    def reset_conversion_state(self) -> None:
+        """Clear all runtime conversion fields to start fresh."""
+        with self._lock:
+            self.is_converting = False
+            self.is_cancelled = False
+            self.progress = 0.0
+            self.etr_seconds = None
+            self.last_output_path = None
+            self.log_lines = []

abogen/frontend/utils/__init__.py

@@ -0,0 +1,38 @@
+"""Utils sub-package."""
+from .helpers import (
+    human_readable_size,
+    format_duration,
+    format_etr,
+    detect_file_type,
+    is_supported_file,
+    is_book_type,
+    voice_lang_code,
+    language_label,
+    grouped_voices,
+    voice_display_name,
+    parse_voice_formula,
+    format_number,
+    safe_basename,
+    output_format_label,
+    subtitle_format_label,
+    SUPPORTED_EXTENSIONS,
+)
+
+__all__ = [
+    "human_readable_size",
+    "format_duration",
+    "format_etr",
+    "detect_file_type",
+    "is_supported_file",
+    "is_book_type",
+    "voice_lang_code",
+    "language_label",
+    "grouped_voices",
+    "voice_display_name",
+    "parse_voice_formula",
+    "format_number",
+    "safe_basename",
+    "output_format_label",
+    "subtitle_format_label",
+    "SUPPORTED_EXTENSIONS",
+]

abogen/frontend/utils/conversion_bridge.py

@@ -0,0 +1,462 @@
+"""
+Background conversion bridge for the Abogen Flet frontend.
+
+This module wraps the existing ``abogen.webui.conversion_runner`` (and its
+``ConversionService`` / ``Job`` machinery) in an async-friendly interface that
+can push real-time progress and log updates back to the Flet event loop without
+blocking the UI thread.
+
+Key design decisions
+--------------------
+* All heavy work is offloaded to daemon threads. The Flet page event loop
+  is never blocked.
+* Progress and log callbacks are scheduled back onto the Flet page via
+  ``page.run_task()`` so Flet's session isolation remains intact.
+* Cancellation is cooperative: the underlying job's ``cancel_requested``
+  flag is set, and the runner checks it at chunk boundaries.
+* The module is a pure adapter – it does NOT duplicate any processing logic
+  from the core pipeline.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import os
+import tempfile
+import threading
+import time
+import traceback
+from pathlib import Path
+from typing import Any, Callable, Dict, List, Optional
+
+import flet as ft
+
+from abogen.utils import (
+    get_gpu_acceleration,
+    get_user_cache_path,
+    get_user_output_path,
+    load_numpy_kpipeline,
+    prevent_sleep_end,
+    prevent_sleep_start,
+)
+from abogen.webui.service import (
+    ConversionService,
+    Job,
+    JobStatus,
+    PendingJob,
+    build_service,
+)
+from abogen.webui.conversion_runner import run_conversion_job
+
+from ..state import AppState
+
+# ---------------------------------------------------------------------------
+# Module-level singleton ConversionService (shared across sessions, as in the
+# web UI – but each job carries its own output folder keyed by session).
+# ---------------------------------------------------------------------------
+
+_SERVICE_LOCK = threading.Lock()
+_SERVICE: Optional[ConversionService] = None
+
+
+def _get_service() -> ConversionService:
+    """
+    Return (creating if necessary) the module-level ConversionService.
+
+    The service manages the background worker thread and persistent job state.
+    Thread-safe via a module-level lock.
+    """
+    global _SERVICE
+    with _SERVICE_LOCK:
+        if _SERVICE is None:
+            output_root = Path(get_user_output_path("frontend"))
+            uploads_root = Path(get_user_cache_path("frontend/uploads"))
+            _SERVICE = build_service(
+                runner=run_conversion_job,
+                output_root=output_root,
+                uploads_root=uploads_root,
+            )
+    return _SERVICE
+
+
+# ---------------------------------------------------------------------------
+# Public conversion bridge
+# ---------------------------------------------------------------------------
+
+
+class ConversionBridge:
+    """
+    Thin adapter between the Flet UI session and the core conversion pipeline.
+
+    One ``ConversionBridge`` instance is created per Flet page (session) and
+    is responsible for:
+    1. Accepting a conversion request from the UI.
+    2. Writing the input text to a temp file if needed.
+    3. Submitting the job to ``ConversionService``.
+    4. Polling the job from a daemon thread and forwarding progress/logs to
+       the Flet page via ``page.run_task()``.
+    5. Providing a ``cancel()`` method that sets the cooperative flag.
+    """
+
+    def __init__(self, page: ft.Page, state: AppState) -> None:
+        """
+        Initialise the bridge.
+
+        Args:
+            page: The Flet ``Page`` for this session. Used to schedule
+                  UI callbacks on the correct event loop.
+            state: The session's ``AppState`` instance.
+        """
+        self._page = page
+        self._state = state
+        self._current_job: Optional[Job] = None
+        self._poll_thread: Optional[threading.Thread] = None
+        self._stop_poll = threading.Event()
+        self._seen_log_count = 0
+
+    # ------------------------------------------------------------------
+    # Public API
+    # ------------------------------------------------------------------
+
+    def start(
+        self,
+        *,
+        input_file: str,
+        voice: str,
+        lang_code: str,
+        speed: float,
+        output_format: str,
+        subtitle_mode: str,
+        subtitle_format: str,
+        use_gpu: bool,
+        save_option: str,
+        output_folder: Optional[str],
+        replace_single_newlines: bool,
+        char_count: int,
+        chapters: Optional[List[Dict[str, Any]]] = None,
+        save_chapters_separately: bool = False,
+        merge_chapters_at_end: bool = True,
+        separate_chapters_format: str = "wav",
+        silence_between_chapters: float = 2.0,
+        max_subtitle_words: int = 50,
+        chapter_intro_delay: float = 0.5,
+        read_title_intro: bool = False,
+        read_closing_outro: bool = True,
+        auto_prefix_chapter_titles: bool = True,
+        normalize_chapter_opening_caps: bool = True,
+        tts_provider: str = "kokoro",
+        supertonic_total_steps: int = 5,
+        chunk_level: str = "paragraph",
+        generate_epub3: bool = False,
+        word_substitutions_enabled: bool = False,
+        word_substitutions_list: str = "",
+        case_sensitive_substitutions: bool = False,
+        replace_all_caps: bool = False,
+        replace_numerals: bool = False,
+        fix_nonstandard_punctuation: bool = False,
+    ) -> None:
+        """
+        Submit a conversion job and begin the progress-polling loop.
+
+        This method returns immediately; all heavy work runs on daemon threads.
+        UI callbacks (``state.on_log``, ``state.on_progress``,
+        ``state.on_conversion_finished``) are scheduled on the Flet event loop.
+
+        Args:
+            input_file: Absolute path to the text/epub/pdf input file.
+            voice: Kokoro voice formula string.
+            lang_code: Single-char language code.
+            speed: Playback speed multiplier (0.1 – 2.0).
+            output_format: Audio container key (``'wav'``, ``'mp3'``, …).
+            subtitle_mode: Subtitle generation mode string.
+            subtitle_format: Subtitle container key (``'srt'``, ``'ass_wide'``, …).
+            use_gpu: Whether to request GPU acceleration.
+            save_option: Save-location strategy string.
+            output_folder: Explicit output folder or None.
+            replace_single_newlines: Pre-processing flag.
+            char_count: Pre-computed character count for ETR estimation.
+            chapters: Optional list of chapter dicts for epub/pdf.
+            save_chapters_separately: Split chapters into separate files.
+            merge_chapters_at_end: Merge chapter files into one after generation.
+            separate_chapters_format: Format for individual chapter files.
+            silence_between_chapters: Silence gap (seconds) between chapters.
+            max_subtitle_words: Maximum words per subtitle block.
+            chapter_intro_delay: Silence before chapter title announcement (s).
+            read_title_intro: Announce book title at the start.
+            read_closing_outro: Announce book title at the end.
+            auto_prefix_chapter_titles: Prepend "Chapter N." to titles.
+            normalize_chapter_opening_caps: Fix ALL-CAPS opening lines.
+            tts_provider: ``'kokoro'`` or ``'supertonic'``.
+            supertonic_total_steps: Quality steps for the Supertonic pipeline.
+            chunk_level: ``'paragraph'`` or ``'sentence'`` chunking granularity.
+            generate_epub3: Also produce an EPUB3 audiobook package.
+            word_substitutions_enabled: Toggle word-substitution pre-processing.
+            word_substitutions_list: Newline-delimited ``word|replacement`` rules.
+            case_sensitive_substitutions: Case-sensitive matching for substitutions.
+            replace_all_caps: Lowercase ALL-CAPS words.
+            replace_numerals: Convert digits to spoken words.
+            fix_nonstandard_punctuation: Normalise curly quotes etc.
+        """
+        if self._state.is_converting:
+            return
+
+        # Resolve the effective output folder
+        resolved_output: Optional[Path] = self._resolve_output_folder(
+            save_option=save_option,
+            output_folder=output_folder,
+            input_file=input_file,
+        )
+
+        # Store the input file as a Path
+        stored_path = Path(input_file)
+        original_filename = stored_path.name
+
+        # Block signals until the job is submitted
+        prevent_sleep_start()
+        self._state.is_converting = True
+        self._state.is_cancelled = False
+        self._state.progress = 0.0
+        self._state.etr_seconds = None
+        self._state.log_lines = []
+        self._seen_log_count = 0
+
+        # Enqueue the job on the service
+        service = _get_service()
+        job = service.enqueue(
+            original_filename=original_filename,
+            stored_path=stored_path,
+            language=lang_code,
+            voice=voice,
+            speed=speed,
+            tts_provider=tts_provider,
+            supertonic_total_steps=supertonic_total_steps,
+            use_gpu=use_gpu,
+            subtitle_mode=subtitle_mode,
+            output_format=output_format,
+            save_mode=self._save_mode_key(save_option),
+            output_folder=resolved_output,
+            replace_single_newlines=replace_single_newlines,
+            subtitle_format=subtitle_format,
+            total_characters=char_count,
+            chapters=chapters or [],
+            save_chapters_separately=save_chapters_separately,
+            merge_chapters_at_end=merge_chapters_at_end,
+            separate_chapters_format=separate_chapters_format,
+            silence_between_chapters=silence_between_chapters,
+            max_subtitle_words=max_subtitle_words,
+            chapter_intro_delay=chapter_intro_delay,
+            read_title_intro=read_title_intro,
+            read_closing_outro=read_closing_outro,
+            auto_prefix_chapter_titles=auto_prefix_chapter_titles,
+            normalize_chapter_opening_caps=normalize_chapter_opening_caps,
+            chunk_level=chunk_level,
+            generate_epub3=generate_epub3,
+        )
+        self._current_job = job
+
+        # Persist word-substitution settings to config so the runner picks them up
+        self._state.word_substitutions_enabled = word_substitutions_enabled
+        self._state.word_substitutions_list = word_substitutions_list
+        self._state.case_sensitive_substitutions = case_sensitive_substitutions
+        self._state.replace_all_caps = replace_all_caps
+        self._state.replace_numerals = replace_numerals
+        self._state.fix_nonstandard_punctuation = fix_nonstandard_punctuation
+        self._state.persist_config()
+
+        # Start the poll thread
+        self._stop_poll.clear()
+        self._poll_thread = threading.Thread(
+            target=self._poll_job_loop, daemon=True, name="abogen-poll"
+        )
+        self._poll_thread.start()
+
+    def cancel(self) -> None:
+        """
+        Request cancellation of the currently running job.
+
+        Sets the cooperative flag on the underlying ``Job`` object; the runner
+        will stop after completing the current text chunk.
+        """
+        if self._current_job is not None:
+            self._state.is_cancelled = True
+            try:
+                _get_service().cancel(self._current_job.id)
+            except Exception:
+                pass
+
+    # ------------------------------------------------------------------
+    # Internal helpers
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def _save_mode_key(option: str) -> str:
+        """
+        Convert the human-readable save option to the service's internal key.
+
+        Args:
+            option: UI-facing string (``'Save next to input file'``, …).
+
+        Returns:
+            Service key string.
+        """
+        mapping = {
+            "Save next to input file": "save_next_to_input",
+            "Save to Desktop": "save_to_desktop",
+            "Choose output folder": "custom",
+        }
+        return mapping.get(option, "save_next_to_input")
+
+    @staticmethod
+    def _resolve_output_folder(
+        save_option: str,
+        output_folder: Optional[str],
+        input_file: str,
+    ) -> Optional[Path]:
+        """
+        Return the output ``Path`` based on the save option, or None for
+        the "next to input" strategy (the runner handles that internally).
+
+        Args:
+            save_option: UI-facing save strategy string.
+            output_folder: Explicit path when ``save_option`` is ``'Choose output folder'``.
+            input_file: Path to the source file for the ``'Save to Desktop'`` strategy.
+
+        Returns:
+            Resolved ``Path`` or ``None``.
+        """
+        if save_option == "Choose output folder" and output_folder:
+            p = Path(output_folder)
+            p.mkdir(parents=True, exist_ok=True)
+            return p
+        if save_option == "Save to Desktop":
+            desktop = Path.home() / "Desktop"
+            desktop.mkdir(exist_ok=True)
+            return desktop
+        # "Save next to input file" – let the runner decide
+        return None
+
+    def _poll_job_loop(self) -> None:
+        """
+        Background daemon loop that polls the current Job for updates.
+
+        Runs until the job enters a terminal state or until ``_stop_poll``
+        is set.  Uses ``page.run_task()`` to schedule UI updates on the Flet
+        event loop without triggering thread-safety violations.
+        """
+        job = self._current_job
+        if job is None:
+            return
+
+        service = _get_service()
+        POLL_INTERVAL = 0.25  # seconds
+
+        while not self._stop_poll.is_set():
+            # Re-fetch the current job state (it's mutated in-place by the runner)
+            current = service.get_job(job.id)
+            if current is None:
+                break
+
+            # Forward new log lines
+            new_logs = current.logs[self._seen_log_count:]
+            self._seen_log_count += len(new_logs)
+            for log_entry in new_logs:
+                level = getattr(log_entry, "level", "info")
+                message = getattr(log_entry, "message", str(log_entry))
+                self._schedule_log(message, level)
+
+            # Forward progress
+            if current.progress is not None:
+                etr = getattr(current, "estimated_time_remaining", None)
+                self._schedule_progress(float(current.progress), etr)
+
+            # Check for terminal states
+            status = current.status
+            if status in (
+                JobStatus.COMPLETED,
+                JobStatus.FAILED,
+                JobStatus.CANCELLED,
+            ):
+                output_path: Optional[str] = None
+                if current.result and current.result.audio_path:
+                    output_path = str(current.result.audio_path)
+                if status == JobStatus.COMPLETED:
+                    finish_msg = "Conversion completed successfully."
+                elif status == JobStatus.CANCELLED:
+                    finish_msg = "Cancelled"
+                else:
+                    finish_msg = f"Conversion failed: {current.error or 'Unknown error'}"
+
+                self._schedule_finished(finish_msg, output_path)
+                break
+
+            time.sleep(POLL_INTERVAL)
+
+        prevent_sleep_end()
+        self._state.is_converting = False
+
+    def _schedule_log(self, message: str, level: str) -> None:
+        """Schedule a log update on the Flet event loop."""
+        state = self._state
+        page = self._page
+        state.append_log(message, level)
+
+        async def _update() -> None:
+            cb = state.on_log
+            if cb:
+                cb(message, level)
+            try:
+                page.update()
+            except Exception:
+                pass
+
+        try:
+            page.run_task(_update)
+        except Exception:
+            pass
+
+    def _schedule_progress(self, fraction: float, etr: Optional[float]) -> None:
+        """Schedule a progress update on the Flet event loop."""
+        state = self._state
+        page = self._page
+        state.progress = max(0.0, min(1.0, fraction))
+        state.etr_seconds = etr
+
+        async def _update() -> None:
+            cb = state.on_progress
+            if cb:
+                cb(fraction, etr)
+            try:
+                page.update()
+            except Exception:
+                pass
+
+        try:
+            page.run_task(_update)
+        except Exception:
+            pass
+
+    def _schedule_finished(
+        self, message: str, output_path: Optional[str]
+    ) -> None:
+        """Schedule a completion notification on the Flet event loop."""
+        state = self._state
+        page = self._page
+        state.last_output_path = output_path
+        self._stop_poll.set()
+
+        async def _update() -> None:
+            state.is_converting = False
+            state.progress = 1.0
+            state.last_output_path = output_path
+            cb = state.on_conversion_finished
+            if cb:
+                cb(message, output_path)
+            try:
+                page.update()
+            except Exception:
+                pass
+
+        try:
+            page.run_task(_update)
+        except Exception:
+            pass

abogen/frontend/utils/helpers.py

@@ -0,0 +1,313 @@
+"""
+Frontend-specific utilities for the Abogen Flet application.
+
+Contains helpers for:
+- Human-readable size / duration formatting
+- Voice formula parsing and display
+- File-type detection
+- ETR (Estimated Time Remaining) formatting
+- Path resolution that adapts to desktop vs. web context
+"""
+
+from __future__ import annotations
+
+import os
+import re
+from pathlib import Path
+from typing import List, Optional, Tuple
+
+from abogen.constants import (
+    LANGUAGE_DESCRIPTIONS,
+    SUPPORTED_INPUT_FORMATS,
+    SUPPORTED_SOUND_FORMATS,
+    SUBTITLE_FORMATS,
+    VOICES_INTERNAL,
+)
+
+
+# ---------------------------------------------------------------------------
+# Size / duration helpers
+# ---------------------------------------------------------------------------
+
+
+def human_readable_size(size_bytes: int, decimal_places: int = 2) -> str:
+    """
+    Convert a byte count into a human-readable string.
+
+    Args:
+        size_bytes: Number of bytes.
+        decimal_places: Significant decimal digits in the output.
+
+    Returns:
+        A string like ``"3.14 MB"`` or ``"1.00 KB"``.
+    """
+    for unit in ("B", "KB", "MB", "GB", "TB"):
+        if size_bytes < 1024.0:
+            return f"{size_bytes:.{decimal_places}f} {unit}"
+        size_bytes /= 1024.0  # type: ignore[assignment]
+    return f"{size_bytes:.{decimal_places}f} PB"
+
+
+def format_duration(seconds: float) -> str:
+    """
+    Format a duration in seconds as ``HH:MM:SS``.
+
+    Args:
+        seconds: Non-negative floating-point duration.
+
+    Returns:
+        A colon-delimited time string, e.g. ``"00:03:42"``.
+    """
+    total = max(0, int(seconds))
+    h, remainder = divmod(total, 3600)
+    m, s = divmod(remainder, 60)
+    return f"{h:02d}:{m:02d}:{s:02d}"
+
+
+def format_etr(etr_seconds: Optional[float]) -> str:
+    """
+    Format an estimated time remaining value for the UI.
+
+    Args:
+        etr_seconds: Seconds remaining, or None when unknown.
+
+    Returns:
+        Human-readable string such as ``"~3 min 42 sec"`` or ``"Calculating…"``.
+    """
+    if etr_seconds is None:
+        return "Calculating…"
+    total = max(0, int(etr_seconds))
+    if total < 60:
+        return f"~{total} sec"
+    m, s = divmod(total, 60)
+    if m < 60:
+        return f"~{m} min {s} sec"
+    h, m = divmod(m, 60)
+    return f"~{h} h {m} min"
+
+
+# ---------------------------------------------------------------------------
+# File helpers
+# ---------------------------------------------------------------------------
+
+
+SUPPORTED_EXTENSIONS: Tuple[str, ...] = (
+    ".txt",
+    ".epub",
+    ".pdf",
+    ".md",
+    ".markdown",
+    ".srt",
+    ".ass",
+    ".vtt",
+)
+"""All file extensions that the drop-zone accepts."""
+
+
+def detect_file_type(file_path: str) -> str:
+    """
+    Return a normalised file-type token for the given path.
+
+    Args:
+        file_path: Absolute or relative path to the input file.
+
+    Returns:
+        One of ``'txt'``, ``'epub'``, ``'pdf'``, ``'markdown'``,
+        ``'subtitle'``, or ``'unknown'``.
+    """
+    ext = Path(file_path).suffix.lower()
+    if ext == ".epub":
+        return "epub"
+    if ext == ".pdf":
+        return "pdf"
+    if ext in (".md", ".markdown"):
+        return "markdown"
+    if ext in (".srt", ".ass", ".vtt"):
+        return "subtitle"
+    if ext == ".txt":
+        return "txt"
+    return "unknown"
+
+
+def is_supported_file(file_path: str) -> bool:
+    """
+    Return True when the file extension is in the supported set.
+
+    Args:
+        file_path: Path whose extension is inspected.
+    """
+    return Path(file_path).suffix.lower() in SUPPORTED_EXTENSIONS
+
+
+def is_book_type(file_type: str) -> bool:
+    """
+    Return True for file types that contain chapters / pages.
+
+    Args:
+        file_type: Token from ``detect_file_type()``.
+    """
+    return file_type in ("epub", "pdf", "markdown")
+
+
+# ---------------------------------------------------------------------------
+# Voice helpers
+# ---------------------------------------------------------------------------
+
+
+def voice_lang_code(voice: str) -> str:
+    """
+    Extract the language code character from a Kokoro voice name.
+
+    The first character of every internal voice name encodes the language
+    (e.g. ``'a'`` for American English, ``'b'`` for British English).
+
+    Args:
+        voice: Raw voice string like ``'af_heart'`` or a formula.
+
+    Returns:
+        Single lowercase character, defaulting to ``'a'`` on failure.
+    """
+    if not voice:
+        return "a"
+    # For plain voice IDs the first char is the language
+    if voice[0].isalpha() and "_" in voice[:4]:
+        return voice[0].lower()
+    # Formula: extract first alpha char
+    match = re.search(r"\b([a-z])", voice)
+    return match.group(1) if match else "a"
+
+
+def language_label(lang_code: str) -> str:
+    """
+    Return the human-readable label for a language code.
+
+    Args:
+        lang_code: Single-character code (``'a'``, ``'b'``, …).
+
+    Returns:
+        Display string, e.g. ``"American English"``.
+    """
+    return LANGUAGE_DESCRIPTIONS.get(lang_code, lang_code.upper())
+
+
+def grouped_voices() -> List[Tuple[str, List[str]]]:
+    """
+    Return the internal voice list grouped by language for display.
+
+    Returns:
+        List of ``(language_label, [voice_id, …])`` tuples.
+    """
+    groups: dict[str, List[str]] = {}
+    for v in VOICES_INTERNAL:
+        lang = language_label(v[0])
+        groups.setdefault(lang, []).append(v)
+    return sorted(groups.items())
+
+
+def voice_display_name(voice_id: str) -> str:
+    """
+    Convert a raw voice ID like ``'af_heart'`` to a prettier display name.
+
+    Args:
+        voice_id: Raw internal voice identifier.
+
+    Returns:
+        Formatted string, e.g. ``"af_heart"`` (unchanged; may be enhanced later).
+    """
+    return voice_id
+
+
+def parse_voice_formula(formula: str) -> List[Tuple[str, float]]:
+    """
+    Parse a Kokoro voice mix formula into a list of ``(voice_id, weight)`` tuples.
+
+    Example:
+        ``"af_heart*0.7+am_adam*0.3"`` → ``[('af_heart', 0.7), ('am_adam', 0.3)]``
+
+    Args:
+        formula: Space- or ``+``-joined mix formula string.
+
+    Returns:
+        Parsed list; empty if parsing fails.
+    """
+    parts: List[Tuple[str, float]] = []
+    for token in re.split(r"[+\s]+", formula.strip()):
+        token = token.strip()
+        if not token:
+            continue
+        if "*" in token:
+            name, _, weight_str = token.partition("*")
+            try:
+                parts.append((name.strip(), float(weight_str.strip())))
+            except ValueError:
+                pass
+        else:
+            # Bare voice id — assume full weight
+            if token in VOICES_INTERNAL:
+                parts.append((token, 1.0))
+    return parts
+
+
+# ---------------------------------------------------------------------------
+# Number formatting
+# ---------------------------------------------------------------------------
+
+
+def format_number(n: int) -> str:
+    """
+    Format an integer with thousands separators.
+
+    Args:
+        n: Integer value.
+
+    Returns:
+        Formatted string, e.g. ``"1,234,567"``.
+    """
+    return f"{n:,}"
+
+
+# ---------------------------------------------------------------------------
+# Path helpers
+# ---------------------------------------------------------------------------
+
+
+def safe_basename(path: Optional[str]) -> str:
+    """
+    Return the basename of a path, or an empty string when path is None/empty.
+
+    Args:
+        path: Optional file-system path.
+    """
+    if not path:
+        return ""
+    return os.path.basename(path)
+
+
+def output_format_label(fmt: str) -> str:
+    """
+    Return a display label for an audio output format key.
+
+    Args:
+        fmt: Lowercase format key (``'wav'``, ``'mp3'``, …).
+    """
+    labels = {
+        "wav": "WAV (lossless)",
+        "flac": "FLAC (lossless compressed)",
+        "mp3": "MP3",
+        "opus": "Opus (best compression)",
+        "m4b": "M4B (with chapters)",
+    }
+    return labels.get(fmt, fmt.upper())
+
+
+def subtitle_format_label(key: str) -> str:
+    """
+    Return the display label for a subtitle format key.
+
+    Args:
+        key: Internal subtitle format key (e.g. ``'ass_centered_narrow'``).
+    """
+    for k, label in SUBTITLE_FORMATS:
+        if k == key:
+            return label
+    return key

abogen/frontend/utils/theme.py

@@ -0,0 +1,264 @@
+"""
+Design tokens and theme configuration for the Abogen Flet frontend.
+
+This module defines the application's complete colour palette, typography
+scale, spacing constants, and border radii in one canonical place.
+All component modules import from here; changing a value here propagates
+instantly across the entire UI.
+
+Flet's ``ft.Theme`` uses ``ColorScheme``, but for custom widgets we paint
+directly with hex colours drawn from ``LIGHT`` and ``DARK`` palettes.
+"""
+
+from __future__ import annotations
+
+import flet as ft
+from dataclasses import dataclass
+
+
+# ---------------------------------------------------------------------------
+# Colour palettes
+# ---------------------------------------------------------------------------
+
+
+@dataclass(frozen=True)
+class _Palette:
+    """A complete colour palette for one theme mode."""
+
+    # Backgrounds
+    bg_base: str        # Deepest background (window / page)
+    bg_surface: str     # Cards, panels, dialogs
+    bg_elevated: str    # Slightly raised elements (toolbar, sidebar)
+    bg_input: str       # Text-field / dropdown backgrounds
+
+    # Brand accent
+    accent: str         # Primary interactive colour (buttons, links)
+    accent_muted: str   # Hover tint over accents
+    accent_on: str      # Text drawn on top of accent fills
+
+    # Semantic
+    success: str
+    error: str
+    warning: str
+    info: str
+
+    # Text hierarchy
+    text_primary: str
+    text_secondary: str
+    text_disabled: str
+    text_on_accent: str
+
+    # Borders / dividers
+    border: str
+    border_focused: str
+    divider: str
+
+    # Specific UI atoms
+    drop_zone_border: str
+    drop_zone_bg: str
+    drop_zone_active_border: str
+    drop_zone_active_bg: str
+    log_bg: str
+    log_text: str
+    progress_bar_bg: str
+    progress_bar_fill: str
+    sidebar_bg: str
+    sidebar_selected_bg: str
+    sidebar_selected_text: str
+    nav_indicator: str
+
+
+DARK = _Palette(
+    bg_base="#0f1117",
+    bg_surface="#181b23",
+    bg_elevated="#1e2230",
+    bg_input="#252a38",
+
+    accent="#5b8af5",
+    accent_muted="#3a5fc4",
+    accent_on="#ffffff",
+
+    success="#42ad4a",
+    error="#e84e3c",
+    warning="#f5a623",
+    info="#5b8af5",
+
+    text_primary="#e8eaf0",
+    text_secondary="#9ba3b8",
+    text_disabled="#4e5568",
+    text_on_accent="#ffffff",
+
+    border="#2c3147",
+    border_focused="#5b8af5",
+    divider="#252a38",
+
+    drop_zone_border="#3a4466",
+    drop_zone_bg="#151928",
+    drop_zone_active_border="#42ad4a",
+    drop_zone_active_bg="#0d1f10",
+    log_bg="#0d1117",
+    log_text="#b0b8cc",
+    progress_bar_bg="#1e2230",
+    progress_bar_fill="#5b8af5",
+    sidebar_bg="#13161f",
+    sidebar_selected_bg="#252a38",
+    sidebar_selected_text="#5b8af5",
+    nav_indicator="#5b8af5",
+)
+
+LIGHT = _Palette(
+    bg_base="#f4f5f8",
+    bg_surface="#ffffff",
+    bg_elevated="#edf0f5",
+    bg_input="#f0f2f7",
+
+    accent="#3a5fc4",
+    accent_muted="#2a4fae",
+    accent_on="#ffffff",
+
+    success="#2e9437",
+    error="#c0392b",
+    warning="#d4870a",
+    info="#3a5fc4",
+
+    text_primary="#1a1d27",
+    text_secondary="#5a6172",
+    text_disabled="#9ba3b8",
+    text_on_accent="#ffffff",
+
+    border="#dce0ea",
+    border_focused="#3a5fc4",
+    divider="#e8ebf2",
+
+    drop_zone_border="#a8b4d0",
+    drop_zone_bg="#f7f8fd",
+    drop_zone_active_border="#2e9437",
+    drop_zone_active_bg="#f0fff1",
+    log_bg="#f8f9fc",
+    log_text="#3d4358",
+    progress_bar_bg="#e4e8f0",
+    progress_bar_fill="#3a5fc4",
+    sidebar_bg="#eff1f5",
+    sidebar_selected_bg="#dde3f2",
+    sidebar_selected_text="#3a5fc4",
+    nav_indicator="#3a5fc4",
+)
+
+
+# ---------------------------------------------------------------------------
+# Typography
+# ---------------------------------------------------------------------------
+
+FONT_FAMILY = "Inter, Segoe UI, Roboto, system-ui, sans-serif"
+FONT_SIZE_XS = 11
+FONT_SIZE_SM = 12
+FONT_SIZE_BASE = 14
+FONT_SIZE_MD = 16
+FONT_SIZE_LG = 20
+FONT_SIZE_XL = 26
+FONT_SIZE_DISPLAY = 34
+
+
+# ---------------------------------------------------------------------------
+# Spacing scale (pixels)
+# ---------------------------------------------------------------------------
+
+SPACE_XS = 4
+SPACE_SM = 8
+SPACE_MD = 12
+SPACE_LG = 16
+SPACE_XL = 24
+SPACE_2XL = 32
+SPACE_3XL = 48
+
+
+# ---------------------------------------------------------------------------
+# Border radii
+# ---------------------------------------------------------------------------
+
+RADIUS_SM = 6
+RADIUS_MD = 10
+RADIUS_LG = 16
+RADIUS_FULL = 999  # Pill-shaped
+
+
+# ---------------------------------------------------------------------------
+# Flet ColorScheme builders
+# ---------------------------------------------------------------------------
+
+
+def build_color_scheme(palette: _Palette) -> ft.ColorScheme:
+    """
+    Construct a ``ft.ColorScheme`` from a ``_Palette`` object.
+
+    Args:
+        palette: The ``DARK`` or ``LIGHT`` palette.
+
+    Returns:
+        A fully-populated Flet ``ColorScheme``.
+    """
+    return ft.ColorScheme(
+        primary=palette.accent,
+        on_primary=palette.accent_on,
+        primary_container=palette.accent_muted,
+        secondary=palette.accent,
+        on_secondary=palette.text_on_accent,
+        surface=palette.bg_surface,
+        on_surface=palette.text_primary,
+        on_surface_variant=palette.text_secondary,
+        error=palette.error,
+        on_error=palette.text_on_accent,
+        outline=palette.border,
+    )
+
+
+def build_text_theme() -> ft.TextTheme:
+    """
+    Construct a ``ft.TextTheme`` using the application's type scale.
+
+    Returns:
+        A Flet ``TextTheme`` with consistent font-size assignments.
+    """
+    return ft.TextTheme(
+        display_large=ft.TextStyle(size=FONT_SIZE_DISPLAY, weight=ft.FontWeight.W_700),
+        headline_large=ft.TextStyle(size=FONT_SIZE_XL, weight=ft.FontWeight.W_700),
+        headline_medium=ft.TextStyle(size=FONT_SIZE_LG, weight=ft.FontWeight.W_600),
+        title_large=ft.TextStyle(size=FONT_SIZE_MD, weight=ft.FontWeight.W_600),
+        title_medium=ft.TextStyle(size=FONT_SIZE_BASE, weight=ft.FontWeight.W_500),
+        body_large=ft.TextStyle(size=FONT_SIZE_BASE),
+        body_medium=ft.TextStyle(size=FONT_SIZE_SM),
+        label_large=ft.TextStyle(size=FONT_SIZE_SM, weight=ft.FontWeight.W_500),
+        label_medium=ft.TextStyle(size=FONT_SIZE_XS),
+    )
+
+
+def make_theme(dark: bool) -> ft.Theme:
+    """
+    Build a complete Flet ``Theme`` for the requested mode.
+
+    Args:
+        dark: True for dark-mode theme, False for light-mode theme.
+
+    Returns:
+        A configured ``ft.Theme`` instance.
+    """
+    palette = DARK if dark else LIGHT
+    return ft.Theme(
+        color_scheme=build_color_scheme(palette),
+        text_theme=build_text_theme(),
+        color_scheme_seed=palette.accent,
+        use_material3=True,
+    )
+
+
+def get_palette(page: ft.Page) -> _Palette:
+    """
+    Return the active colour palette for the given page.
+
+    Args:
+        page: The Flet ``Page`` instance.
+
+    Returns:
+        ``DARK`` or ``LIGHT`` depending on the page's theme mode.
+    """
+    return DARK if page.theme_mode == ft.ThemeMode.DARK else LIGHT

abogen/frontend/views/__init__.py

@@ -0,0 +1,6 @@
+"""Views sub-package for the Abogen Flet frontend."""
+from .dashboard import DashboardView
+from .settings import SettingsView
+from .queue_view import QueueView
+
+__all__ = ["DashboardView", "SettingsView", "QueueView"]

abogen/frontend/views/dashboard.py

@@ -0,0 +1,587 @@
+"""
+Dashboard view – the primary conversion screen.
+
+Hosts the file drop-zone, voice/speed/format controls, real-time log
+terminal, progress bar, and the Start/Cancel/Finish action row.
+
+All heavy work is delegated to ConversionBridge which runs on daemon
+threads and schedules UI updates back onto the Flet event loop.
+"""
+from __future__ import annotations
+
+import os
+import tempfile
+from pathlib import Path
+from typing import Optional
+
+import flet as ft
+
+from ..state import AppState
+from ..utils.helpers import (
+    detect_file_type, human_readable_size, format_number,
+    format_etr, grouped_voices, output_format_label,
+    subtitle_format_label, is_book_type, voice_lang_code, SUPPORTED_EXTENSIONS
+)
+from ..utils.theme import get_palette, RADIUS_MD, RADIUS_SM, SPACE_SM, SPACE_MD, SPACE_LG, SPACE_XL
+from ..utils.conversion_bridge import ConversionBridge
+from ..components import (
+    build_drop_zone, build_log_terminal, log_entry,
+    build_primary_button, build_secondary_button,
+    build_card, build_section_header, labelled_row, show_snack,
+)
+from abogen.constants import (
+    SUBTITLE_FORMATS, SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION,
+    LANGUAGE_DESCRIPTIONS, VOICES_INTERNAL,
+)
+from abogen.utils import get_gpu_acceleration, get_user_cache_path, calculate_text_length, clean_text
+
+
+class DashboardView:
+    """
+    The main conversion dashboard.
+
+    Instantiated once per Flet session and mounted as a ``ft.Column``
+    inside the page's content area.
+    """
+
+    def __init__(self, page: ft.Page, state: AppState) -> None:
+        self._page = page
+        self._state = state
+        self._bridge = ConversionBridge(page, state)
+
+        # Internal refs
+        self._log_list: Optional[ft.ListView] = None
+        self._progress_bar: Optional[ft.ProgressBar] = None
+        self._etr_label: Optional[ft.Text] = None
+        self._drop_zone_ref: Optional[ft.GestureDetector] = None
+        self._drop_zone_container: Optional[ft.Container] = None
+        self._file_picker: Optional[ft.FilePicker] = None
+
+        # Wire state callbacks
+        state.on_log = self._on_log
+        state.on_progress = self._on_progress
+        state.on_conversion_finished = self._on_finished
+
+        # Build UI refs
+        self._voice_dd: Optional[ft.Dropdown] = None
+        self._speed_slider: Optional[ft.Slider] = None
+        self._speed_label: Optional[ft.Text] = None
+        self._format_dd: Optional[ft.Dropdown] = None
+        self._subtitle_dd: Optional[ft.Dropdown] = None
+        self._subtitle_fmt_dd: Optional[ft.Dropdown] = None
+        self._gpu_switch: Optional[ft.Switch] = None
+        self._start_btn: Optional[ft.ElevatedButton] = None
+        self._cancel_btn: Optional[ft.OutlinedButton] = None
+        self._finish_col: Optional[ft.Column] = None
+        self._controls_col: Optional[ft.Column] = None
+        self._log_section: Optional[ft.Container] = None
+        self._progress_col: Optional[ft.Column] = None
+
+    # ------------------------------------------------------------------
+    # Build
+    # ------------------------------------------------------------------
+
+    def build(self) -> ft.Column:
+        """Return the complete dashboard column."""
+        p = self._page
+        dark = p.theme_mode == ft.ThemeMode.DARK
+        pal = get_palette(p)
+        if self._file_picker is None:
+            self._file_picker = ft.FilePicker()
+
+        # --- Drop zone ---
+        self._drop_zone_container = ft.Container()
+        self._refresh_drop_zone()
+
+        # --- Voice selector ---
+        voice_items = []
+        for lang_label, voices in grouped_voices():
+            voice_items.append(ft.dropdown.Option(key=f"__hdr_{lang_label}", text=f"── {lang_label} ──", disabled=True))
+            for v in voices:
+                voice_items.append(ft.dropdown.Option(key=v, text=v))
+
+        self._voice_dd = ft.Dropdown(
+            options=voice_items,
+            value=self._state.selected_voice,
+            on_select=self._on_voice_changed,
+            dense=True,
+            expand=True,
+            border_radius=RADIUS_SM,
+        )
+
+        # --- Speed slider ---
+        self._speed_label = ft.Text(f"{self._state.speed:.2f}", size=13, width=40)
+        self._speed_slider = ft.Slider(
+            min=0.1, max=2.0, value=self._state.speed,
+            divisions=190, label="{value}",
+            on_change=self._on_speed_changed,
+            expand=True,
+        )
+
+        # --- Format ---
+        self._format_dd = ft.Dropdown(
+            options=[ft.dropdown.Option(key=k, text=output_format_label(k))
+                     for k in ("wav", "flac", "mp3", "opus", "m4b")],
+            value=self._state.selected_format,
+            on_select=lambda e: self._set_field("selected_format", e.control.value),
+            dense=True, expand=True, border_radius=RADIUS_SM,
+        )
+
+        # --- Subtitle mode ---
+        sub_modes = ["Disabled", "Line", "Sentence", "Sentence + Comma",
+                     "Sentence + Highlighting"] + [f"{i} word{'s' if i > 1 else ''}" for i in range(1, 11)]
+        self._subtitle_dd = ft.Dropdown(
+            options=[ft.dropdown.Option(m) for m in sub_modes],
+            value=self._state.subtitle_mode,
+            on_select=lambda e: self._set_field("subtitle_mode", e.control.value),
+            dense=True, expand=True, border_radius=RADIUS_SM,
+        )
+
+        # --- Subtitle format ---
+        self._subtitle_fmt_dd = ft.Dropdown(
+            options=[ft.dropdown.Option(key=k, text=lbl) for k, lbl in SUBTITLE_FORMATS],
+            value=self._state.subtitle_format,
+            on_select=lambda e: self._set_field("subtitle_format", e.control.value),
+            dense=True, expand=True, border_radius=RADIUS_SM,
+        )
+
+        # --- GPU ---
+        self._gpu_switch = ft.Switch(
+            value=self._state.use_gpu, label="",
+            on_change=lambda e: self._set_field("use_gpu", e.control.value),
+            active_color="#5b8af5" if dark else "#3a5fc4",
+        )
+
+        # --- Log ---
+        log_lv = ft.ListView(expand=True, auto_scroll=True, spacing=1, padding=ft.Padding.all(8))
+        self._log_list = log_lv
+        bg_log = "#0d1117" if dark else "#f8f9fc"
+        bd_log = "#252a38" if dark else "#dce0ea"
+        self._log_section = ft.Container(
+            content=log_lv, bgcolor=bg_log,
+            border=ft.Border.all(1, bd_log),
+            border_radius=RADIUS_SM, height=220,
+            clip_behavior=ft.ClipBehavior.HARD_EDGE,
+            visible=False,
+        )
+
+        # --- Progress ---
+        fill = "#5b8af5" if dark else "#3a5fc4"
+        bg_p = "#1e2230" if dark else "#e4e8f0"
+        self._progress_bar = ft.ProgressBar(
+            value=0, color=fill, bgcolor=bg_p, height=8,
+            border_radius=ft.BorderRadius.all(4), expand=True,
+        )
+        self._etr_label = ft.Text("", size=11, color=pal.text_secondary, text_align=ft.TextAlign.CENTER)
+        self._progress_col = ft.Column([
+            ft.Row([self._progress_bar], spacing=0),
+            self._etr_label,
+        ], spacing=SPACE_SM, horizontal_alignment=ft.CrossAxisAlignment.CENTER, visible=False)
+
+        # --- Buttons ---
+        self._start_btn = build_primary_button(
+            "Start Conversion",
+            icon="play_arrow",
+            on_click=self._on_start,
+            page=p,
+        )
+        self._cancel_btn = build_secondary_button(
+            "Cancel", icon="stop",
+            on_click=self._on_cancel, page=p,
+        )
+        self._cancel_btn.visible = False
+
+        # --- Finish row ---
+        self._finish_col = ft.Column([
+            ft.Row([
+                build_secondary_button("Open File", icon="open_in_new",
+                                       on_click=self._on_open_file, page=p),
+                build_secondary_button("Go to Folder", icon="folder_open",
+                                       on_click=self._on_go_folder, page=p),
+                build_secondary_button("New Conversion", icon="refresh",
+                                       on_click=self._on_reset, page=p),
+            ], wrap=True, spacing=SPACE_SM, run_spacing=SPACE_SM),
+        ], visible=False)
+
+        # --- Controls column ---
+        self._controls_col = ft.Column([
+            build_section_header("Voice & Speed", icon="record_voice_over", page=p),
+            labelled_row("Voice", self._voice_dd, page=p),
+            labelled_row("Speed", ft.Row([self._speed_slider, self._speed_label], expand=True, spacing=SPACE_SM), page=p),
+            ft.Divider(height=1, color=pal.divider),
+            build_section_header("Output", icon="audio_file", page=p),
+            labelled_row("Format", self._format_dd, page=p),
+            labelled_row("Subtitles", self._subtitle_dd, page=p),
+            labelled_row("Subtitle Format", self._subtitle_fmt_dd, page=p),
+            ft.Divider(height=1, color=pal.divider),
+            build_section_header("Processing", icon="memory", page=p),
+            labelled_row("GPU Acceleration", self._gpu_switch, page=p),
+        ], spacing=SPACE_MD)
+
+        outer = ft.Column([
+            self._drop_zone_container,
+            ft.Container(height=SPACE_MD),
+            build_card(self._controls_col, page=p),
+            ft.Container(height=SPACE_SM),
+            self._log_section,
+            self._progress_col,
+            ft.Row([self._start_btn, self._cancel_btn], spacing=SPACE_SM, wrap=True),
+            self._finish_col,
+        ], spacing=SPACE_MD, expand=True, scroll=ft.ScrollMode.AUTO)
+
+        return outer
+
+    # ------------------------------------------------------------------
+    # Drop-zone management
+    # ------------------------------------------------------------------
+
+    def _refresh_drop_zone(self, *, accent: bool = False, error: bool = False, err_msg: str = "") -> None:
+        """Rebuild the drop-zone widget and update its container."""
+        p = self._page
+        s = self._state
+        fname = None; fsize = None; fchars = None
+        if s.selected_file and os.path.exists(s.selected_file):
+            disp = s.displayed_file_path or s.selected_file
+            fname = os.path.basename(disp)
+            try:
+                fsize = human_readable_size(os.path.getsize(s.selected_file))
+            except Exception:
+                fsize = ""
+            if s.char_count:
+                fchars = format_number(s.char_count)
+
+        label = err_msg if error else "Drag & drop your file here or click to browse"
+        sub = "Supports .txt · .epub · .pdf · .md · .srt · .ass · .vtt"
+
+        dz = build_drop_zone(
+            on_pick=self._open_file_picker,
+            label=label, sub_label=sub,
+            accent=accent, error=error,
+            filename=fname, file_size=fsize, char_count=fchars,
+            page=p,
+        )
+        if self._drop_zone_container is not None:
+            self._drop_zone_container.content = dz
+        self._drop_zone_ref = dz
+
+    # ------------------------------------------------------------------
+    # File picking
+    # ------------------------------------------------------------------
+
+    def _open_file_picker(self) -> None:
+        """Open the native file picker dialog."""
+        self._page.run_task(self._pick_files_async)
+
+    async def _pick_files_async(self) -> None:
+        """Run the file picker using Flet's async service API."""
+        picker = self._file_picker
+        if picker is None:
+            picker = ft.FilePicker()
+            self._file_picker = picker
+
+        try:
+            files = await picker.pick_files(
+                dialog_title="Select Input File",
+                file_type=ft.FilePickerFileType.CUSTOM,
+                allowed_extensions=["txt", "epub", "pdf", "md", "markdown", "srt", "ass", "vtt"],
+                allow_multiple=False,
+            )
+        except Exception as ex:
+            self._refresh_drop_zone(error=True, err_msg="Could not open file picker.")
+            show_snack(self._page, f"File picker error: {ex}", error=True)
+            self._page.update()
+            return
+        if not files:
+            return
+        file_path = files[0].path
+        if not file_path or not os.path.exists(file_path):
+            return
+        self._load_file(file_path)
+
+    def _load_file(self, file_path: str) -> None:
+        """Validate and load a file into the session state."""
+        from pathlib import Path as _Path
+        ext = _Path(file_path).suffix.lower()
+        if ext not in SUPPORTED_EXTENSIONS:
+            self._state.reset_file_state()
+            self._refresh_drop_zone(error=True, err_msg=f"Unsupported file type: {ext}")
+            self._page.update()
+            return
+
+        ftype = detect_file_type(file_path)
+        s = self._state
+
+        if ftype in ("epub", "pdf", "markdown"):
+            # For book types: extract text to temp cache
+            self._handle_book_file(file_path, ftype)
+        else:
+            # Plain text / subtitle files
+            s.selected_file = file_path
+            s.selected_file_type = ftype
+            s.displayed_file_path = file_path
+            try:
+                with open(file_path, "r", encoding="utf-8", errors="ignore") as f:
+                    text = f.read()
+                s.char_count = calculate_text_length(clean_text(text))
+            except Exception:
+                s.char_count = 0
+            self._refresh_drop_zone(accent=True)
+            self._update_subtitle_availability()
+            self._page.update()
+
+    def _handle_book_file(self, book_path: str, ftype: str) -> None:
+        """Extract text from epub/pdf/markdown and store as temp txt."""
+        import threading as _t
+        s = self._state
+
+        def _extract():
+            try:
+                from abogen.text_extractor import extract_from_path
+                chapters = extract_from_path(book_path, file_type=ftype)
+                combined = "\n\n".join(ch.text for ch in chapters if ch.text.strip())
+                cache_dir = get_user_cache_path()
+                base = os.path.splitext(os.path.basename(book_path))[0]
+                fd, tmp = tempfile.mkstemp(prefix=f"{base}_", suffix=".txt", dir=cache_dir)
+                os.close(fd)
+                with open(tmp, "w", encoding="utf-8") as f:
+                    f.write(combined)
+
+                s.selected_file = tmp
+                s.selected_file_type = ftype
+                s.selected_book_path = book_path
+                s.displayed_file_path = book_path
+                s.char_count = calculate_text_length(clean_text(combined))
+                s.selected_chapters = [f"ch_{i}" for i in range(len(chapters))]
+
+                self._refresh_drop_zone(accent=True)
+                self._update_subtitle_availability()
+                self._page.update()
+            except Exception as ex:
+                s.reset_file_state()
+                self._refresh_drop_zone(error=True, err_msg=f"Could not parse file: {ex}")
+                self._page.update()
+
+        _t.Thread(target=_extract, daemon=True).start()
+
+    # ------------------------------------------------------------------
+    # Control event handlers
+    # ------------------------------------------------------------------
+
+    def _set_field(self, attr: str, value) -> None:
+        setattr(self._state, attr, value)
+        self._state.persist_config()
+
+    def _on_voice_changed(self, e: ft.ControlEvent) -> None:
+        v = e.control.value or "af_heart"
+        self._state.selected_voice = v
+        self._state.selected_lang = voice_lang_code(v)
+        self._state.persist_config()
+        self._update_subtitle_availability()
+        self._page.update()
+
+    def _on_speed_changed(self, e: ft.ControlEvent) -> None:
+        val = round(float(e.control.value), 2)
+        self._state.speed = val
+        if self._speed_label:
+            self._speed_label.value = f"{val:.2f}"
+        self._state.persist_config()
+        self._page.update()
+
+    def _update_subtitle_availability(self) -> None:
+        """Enable or disable subtitle controls based on selected language."""
+        lang = self._state.selected_lang
+        enabled = lang in SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION
+        if self._subtitle_dd:
+            self._subtitle_dd.disabled = not enabled
+        if self._subtitle_fmt_dd:
+            self._subtitle_fmt_dd.disabled = not enabled
+
+    # ------------------------------------------------------------------
+    # Conversion control
+    # ------------------------------------------------------------------
+
+    def _on_start(self, _: ft.ControlEvent) -> None:
+        """Validate inputs and kick off conversion."""
+        s = self._state
+        if not s.selected_file or not os.path.exists(s.selected_file):
+            self._refresh_drop_zone(error=True, err_msg="Please select an input file first.")
+            self._page.update()
+            return
+
+        # Transition UI to converting state
+        self._set_converting_ui(True)
+
+        self._bridge.start(
+            input_file=s.selected_file,
+            voice=s.get_voice_formula(),
+            lang_code=s.selected_lang,
+            speed=s.speed,
+            output_format=s.selected_format,
+            subtitle_mode=s.subtitle_mode,
+            subtitle_format=s.subtitle_format,
+            use_gpu=s.use_gpu,
+            save_option=s.save_option,
+            output_folder=s.selected_output_folder,
+            replace_single_newlines=s.replace_single_newlines,
+            char_count=s.char_count,
+            save_chapters_separately=s.save_chapters_separately or False,
+            merge_chapters_at_end=True if s.merge_chapters_at_end is None else s.merge_chapters_at_end,
+            separate_chapters_format=s.separate_chapters_format,
+            silence_between_chapters=s.silence_duration,
+            max_subtitle_words=s.max_subtitle_words,
+            chapter_intro_delay=s.chapter_intro_delay,
+            read_title_intro=s.read_title_intro,
+            read_closing_outro=s.read_closing_outro,
+            auto_prefix_chapter_titles=s.auto_prefix_chapter_titles,
+            normalize_chapter_opening_caps=s.normalize_chapter_opening_caps,
+            tts_provider=s.tts_provider,
+            supertonic_total_steps=s.supertonic_total_steps,
+            chunk_level=s.chunk_level,
+            generate_epub3=s.generate_epub3,
+            word_substitutions_enabled=s.word_substitutions_enabled,
+            word_substitutions_list=s.word_substitutions_list,
+            case_sensitive_substitutions=s.case_sensitive_substitutions,
+            replace_all_caps=s.replace_all_caps,
+            replace_numerals=s.replace_numerals,
+            fix_nonstandard_punctuation=s.fix_nonstandard_punctuation,
+        )
+
+    def _on_cancel(self, _: ft.ControlEvent) -> None:
+        self._bridge.cancel()
+
+    def _set_converting_ui(self, converting: bool) -> None:
+        """Toggle UI between idle and converting states."""
+        if self._start_btn:
+            self._start_btn.visible = not converting
+        if self._cancel_btn:
+            self._cancel_btn.visible = converting
+        if self._controls_col:
+            self._controls_col.visible = not converting
+        if self._log_section:
+            self._log_section.visible = converting
+            if self._log_list:
+                self._log_list.controls.clear()
+        if self._progress_col:
+            self._progress_col.visible = converting
+            if self._progress_bar:
+                self._progress_bar.value = 0
+            if self._etr_label:
+                self._etr_label.value = "Estimating…"
+        if self._finish_col:
+            self._finish_col.visible = False
+        self._page.update()
+
+    # ------------------------------------------------------------------
+    # State callbacks (called from background thread via page.run_task)
+    # ------------------------------------------------------------------
+
+    def _on_log(self, message: str, level: str) -> None:
+        if self._log_list is None:
+            return
+        entry = log_entry(message, level, self._page)
+        self._log_list.controls.append(entry)
+        # Cap log lines
+        if len(self._log_list.controls) > 2000:
+            self._log_list.controls = self._log_list.controls[-1800:]
+        try:
+            self._page.update()
+        except Exception:
+            pass
+
+    def _on_progress(self, fraction: float, etr: Optional[float]) -> None:
+        if self._progress_bar:
+            self._progress_bar.value = min(fraction, 0.99)
+        if self._etr_label:
+            self._etr_label.value = format_etr(etr)
+        try:
+            self._page.update()
+        except Exception:
+            pass
+
+    def _on_finished(self, message: str, output_path: Optional[str]) -> None:
+        if self._progress_bar:
+            self._progress_bar.value = 1.0
+        if self._cancel_btn:
+            self._cancel_btn.visible = False
+
+        if message == "Cancelled":
+            # Restore idle state
+            self._set_converting_ui(False)
+            show_snack(self._page, "Conversion cancelled.", error=True)
+            return
+
+        if "failed" in message.lower() or "error" in message.lower():
+            self._log_on_log(message, "error")
+            self._set_converting_ui(False)
+            show_snack(self._page, f"Error: {message}", error=True)
+            return
+
+        # Success
+        if self._log_section:
+            self._log_section.visible = True
+        if self._progress_col:
+            self._progress_col.visible = False
+        if self._controls_col:
+            self._controls_col.visible = False
+        if self._finish_col:
+            self._finish_col.visible = True
+        if self._start_btn:
+            self._start_btn.visible = False
+        show_snack(self._page, "Conversion completed!")
+        try:
+            self._page.update()
+        except Exception:
+            pass
+
+    def _log_on_log(self, message: str, level: str) -> None:
+        self._on_log(message, level)
+
+    # ------------------------------------------------------------------
+    # Finish actions
+    # ------------------------------------------------------------------
+
+    def _on_open_file(self, _: ft.ControlEvent) -> None:
+        path = self._state.last_output_path
+        if path and os.path.exists(path):
+            import subprocess, platform
+            try:
+                if platform.system() == "Darwin":
+                    subprocess.Popen(["open", path])
+                elif platform.system() == "Windows":
+                    os.startfile(path)
+                else:
+                    subprocess.Popen(["xdg-open", path])
+            except Exception as ex:
+                show_snack(self._page, f"Cannot open file: {ex}", error=True)
+        else:
+            show_snack(self._page, "Output file not found.", error=True)
+
+    def _on_go_folder(self, _: ft.ControlEvent) -> None:
+        path = self._state.last_output_path
+        folder = os.path.dirname(path) if path and os.path.isfile(path) else path
+        if folder and os.path.isdir(folder):
+            import subprocess, platform
+            try:
+                if platform.system() == "Darwin":
+                    subprocess.Popen(["open", folder])
+                elif platform.system() == "Windows":
+                    subprocess.Popen(["explorer", folder])
+                else:
+                    subprocess.Popen(["xdg-open", folder])
+            except Exception as ex:
+                show_snack(self._page, f"Cannot open folder: {ex}", error=True)
+        else:
+            show_snack(self._page, "Output folder not found.", error=True)
+
+    def _on_reset(self, _: ft.ControlEvent) -> None:
+        self._state.reset_file_state()
+        self._state.reset_conversion_state()
+        self._refresh_drop_zone()
+        self._set_converting_ui(False)
+        if self._finish_col:
+            self._finish_col.visible = False
+        if self._controls_col:
+            self._controls_col.visible = True
+        if self._start_btn:
+            self._start_btn.visible = True
+        self._page.update()

abogen/frontend/views/queue_view.py

@@ -0,0 +1,154 @@
+"""
+Queue management view.
+
+Displays the current conversion queue, allowing the user to reorder,
+remove, and inspect queued items before starting batch processing.
+"""
+from __future__ import annotations
+from typing import Optional
+
+import flet as ft
+
+from ..state import AppState, ConversionJob
+from ..utils.theme import get_palette, RADIUS_SM, SPACE_SM, SPACE_MD, SPACE_LG
+from ..utils.helpers import safe_basename, output_format_label, format_number
+from ..components import (
+    build_card, build_section_header, build_primary_button,
+    build_secondary_button, show_snack, build_divider,
+    resolve_icon,
+)
+
+
+class QueueView:
+    """Queue manager view."""
+
+    def __init__(self, page: ft.Page, state: AppState) -> None:
+        self._page = page
+        self._state = state
+        self._list_col: Optional[ft.Column] = None
+
+    def build(self) -> ft.Column:
+        p = self._page
+        s = self._state
+        pal = get_palette(p)
+        dark = p.theme_mode == ft.ThemeMode.DARK
+
+        self._list_col = ft.Column(spacing=SPACE_SM)
+        self._refresh_list()
+
+        header = build_section_header("Conversion Queue",
+                                      icon="list_alt", page=p)
+
+        action_row = ft.Row([
+            build_primary_button(
+                "Start Queue",
+                icon="play_arrow",
+                on_click=self._on_start_queue,
+                page=p,
+                disabled=not s.queued_items,
+            ),
+            build_secondary_button(
+                "Clear All",
+                icon="delete_sweep",
+                on_click=self._on_clear_queue,
+                page=p,
+            ),
+        ], spacing=SPACE_SM, wrap=True)
+
+        queue_card = build_card(ft.Column([
+            header,
+            ft.Divider(height=1, color=pal.divider),
+            self._list_col,
+            ft.Container(height=SPACE_SM),
+            action_row,
+        ], spacing=SPACE_MD), page=p)
+
+        return ft.Column([queue_card], scroll=ft.ScrollMode.AUTO, expand=True)
+
+    # ------------------------------------------------------------------
+
+    def _refresh_list(self) -> None:
+        if self._list_col is None:
+            return
+        self._list_col.controls.clear()
+        s = self._state
+        pal = get_palette(self._page)
+        dark = self._page.theme_mode == ft.ThemeMode.DARK
+
+        if not s.queued_items:
+            self._list_col.controls.append(
+                ft.Text("No items in the queue.", size=13,
+                        color=pal.text_secondary,
+                        text_align=ft.TextAlign.CENTER)
+            )
+            return
+
+        for idx, job in enumerate(s.queued_items):
+            tile = self._build_job_tile(idx, job, dark, pal)
+            self._list_col.controls.append(tile)
+
+        try:
+            self._page.update()
+        except Exception:
+            pass
+
+    def _build_job_tile(self, idx: int, job: ConversionJob, dark: bool, pal) -> ft.Container:
+        """Build a single queue-item tile."""
+        bg = pal.bg_elevated
+        border_clr = pal.border
+        accent = "#5b8af5" if dark else "#3a5fc4"
+        text_primary = pal.text_primary
+        text_secondary = pal.text_secondary
+
+        def _remove(_):
+            self._state.queued_items.pop(idx)
+            self._refresh_list()
+
+        name = safe_basename(job.display_name or job.file_path)
+        details = (
+            f"Voice: {job.voice}  ·  Format: {output_format_label(job.output_format)}"
+            f"  ·  Speed: {job.speed:.2f}x  ·  Chars: {format_number(job.char_count)}"
+        )
+
+        return ft.Container(
+            content=ft.Row([
+                ft.Container(
+                    content=ft.Text(str(idx + 1), size=12, weight=ft.FontWeight.W_700,
+                                    color=accent),
+                    width=32,
+                ),
+                ft.Column([
+                    ft.Text(name, size=13, weight=ft.FontWeight.W_600, color=text_primary,
+                            no_wrap=True, overflow=ft.TextOverflow.ELLIPSIS),
+                    ft.Text(details, size=11, color=text_secondary),
+                ], expand=True, tight=True, spacing=2),
+                ft.IconButton(
+                    icon=resolve_icon("delete_outline"),
+                    icon_color=pal.error if hasattr(pal, "error") else "#e84e3c",
+                    icon_size=18,
+                    tooltip="Remove",
+                    on_click=_remove,
+                ),
+            ], vertical_alignment=ft.CrossAxisAlignment.CENTER, spacing=SPACE_SM),
+            bgcolor=bg,
+            border=ft.Border.all(1, border_clr),
+            border_radius=RADIUS_SM,
+            padding=ft.Padding.symmetric(horizontal=SPACE_MD, vertical=SPACE_SM),
+        )
+
+    # ------------------------------------------------------------------
+
+    def _on_start_queue(self, _: ft.ControlEvent) -> None:
+        if not self._state.queued_items:
+            show_snack(self._page, "Queue is empty.", error=True)
+            return
+        # Navigate to dashboard and trigger queue start
+        # This is wired in main.py via the nav controller
+        self._page.pubsub.send_all("start_queue")
+
+    def _on_clear_queue(self, _: ft.ControlEvent) -> None:
+        if not self._state.queued_items:
+            return
+        self._state.queued_items.clear()
+        self._refresh_list()
+        show_snack(self._page, "Queue cleared.")

abogen/frontend/views/settings.py

@@ -0,0 +1,305 @@
+"""
+Settings view – a categorised, scrollable settings page.
+
+Groups settings into collapsible cards:
+  - Output (format, save location, chapters)
+  - Text processing (newlines, caps, substitutions, numerals)
+  - Subtitle options
+  - TTS pipeline (provider, GPU, chunking)
+  - Integrations (Audiobookshelf, Calibre OPDS)
+"""
+from __future__ import annotations
+from typing import Optional
+
+import flet as ft
+
+from ..state import AppState
+from ..utils.theme import get_palette, RADIUS_MD, RADIUS_SM, SPACE_SM, SPACE_MD, SPACE_LG
+from ..utils.helpers import output_format_label, subtitle_format_label, SUPPORTED_EXTENSIONS
+from ..components import (
+    build_card, build_section_header, labelled_row, show_snack, build_divider,
+    build_primary_button,
+)
+from abogen.constants import SUBTITLE_FORMATS
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+def _dd(options, value, on_change, **kw):
+    """Compact dropdown factory."""
+    return ft.Dropdown(
+        options=[ft.dropdown.Option(key=k, text=v) for k, v in options],
+        value=value, on_select=on_change, dense=True,
+        border_radius=RADIUS_SM, expand=True, **kw
+    )
+
+
+def _sw(value, on_change, label=""):
+    return ft.Switch(value=value, on_change=on_change, label=label)
+
+
+class SettingsView:
+    """The full settings panel."""
+
+    def __init__(self, page: ft.Page, state: AppState) -> None:
+        self._page = page
+        self._state = state
+
+    def build(self) -> ft.Column:
+        p = self._page
+        s = self._state
+        pal = get_palette(p)
+
+        # ── Output card ──────────────────────────────────────────────
+        format_dd = _dd(
+            [(k, output_format_label(k)) for k in ("wav", "flac", "mp3", "opus", "m4b")],
+            s.selected_format,
+            lambda e: self._save("selected_format", e.control.value),
+        )
+        save_dd = _dd(
+            [
+                ("Save next to input file", "Save next to input file"),
+                ("Save to Desktop", "Save to Desktop"),
+                ("Choose output folder", "Choose output folder"),
+            ],
+            s.save_option,
+            lambda e: self._save("save_option", e.control.value),
+        )
+        chapters_sw = _sw(s.save_chapters_separately or False,
+                          lambda e: self._save("save_chapters_separately", e.control.value))
+        merge_sw = _sw(True if s.merge_chapters_at_end is None else s.merge_chapters_at_end,
+                       lambda e: self._save("merge_chapters_at_end", e.control.value))
+        sep_fmt_dd = _dd(
+            [(k, output_format_label(k)) for k in ("wav", "flac", "mp3", "opus")],
+            s.separate_chapters_format,
+            lambda e: self._save("separate_chapters_format", e.control.value),
+        )
+        epub3_sw = _sw(s.generate_epub3, lambda e: self._save("generate_epub3", e.control.value))
+
+        output_card = build_card(ft.Column([
+            build_section_header("Output", icon="audio_file", page=p),
+            labelled_row("Audio Format", format_dd, page=p),
+            labelled_row("Save Location", save_dd, page=p),
+            build_divider(p),
+            labelled_row("Save Chapters Separately", chapters_sw, page=p),
+            labelled_row("Merge at End", merge_sw, page=p),
+            labelled_row("Chapter Format", sep_fmt_dd, page=p),
+            labelled_row("Generate EPUB3", epub3_sw, page=p),
+        ], spacing=SPACE_MD), page=p)
+
+        # ── Text processing card ─────────────────────────────────────
+        newlines_sw = _sw(s.replace_single_newlines,
+                          lambda e: self._save("replace_single_newlines", e.control.value))
+        caps_sw = _sw(s.replace_all_caps, lambda e: self._save("replace_all_caps", e.control.value))
+        norm_sw = _sw(s.normalize_chapter_opening_caps,
+                      lambda e: self._save("normalize_chapter_opening_caps", e.control.value))
+        numerals_sw = _sw(s.replace_numerals, lambda e: self._save("replace_numerals", e.control.value))
+        punct_sw = _sw(s.fix_nonstandard_punctuation,
+                       lambda e: self._save("fix_nonstandard_punctuation", e.control.value))
+        wordsub_sw = _sw(s.word_substitutions_enabled,
+                         lambda e: self._save("word_substitutions_enabled", e.control.value))
+        wordsub_tf = ft.TextField(
+            value=s.word_substitutions_list,
+            multiline=True, min_lines=3, max_lines=6,
+            hint_text="word|replacement  (one per line)",
+            on_change=lambda e: self._save("word_substitutions_list", e.control.value),
+            expand=True, border_radius=RADIUS_SM, text_size=12,
+        )
+        case_sw = _sw(s.case_sensitive_substitutions,
+                      lambda e: self._save("case_sensitive_substitutions", e.control.value))
+        spacy_sw = _sw(s.use_spacy_segmentation,
+                       lambda e: self._save("use_spacy_segmentation", e.control.value))
+        chunk_dd = _dd(
+            [("paragraph", "Paragraph"), ("sentence", "Sentence")],
+            s.chunk_level,
+            lambda e: self._save("chunk_level", e.control.value),
+        )
+        title_intro_sw = _sw(s.read_title_intro, lambda e: self._save("read_title_intro", e.control.value))
+        outro_sw = _sw(s.read_closing_outro, lambda e: self._save("read_closing_outro", e.control.value))
+        prefix_sw = _sw(s.auto_prefix_chapter_titles,
+                        lambda e: self._save("auto_prefix_chapter_titles", e.control.value))
+
+        text_card = build_card(ft.Column([
+            build_section_header("Text Processing", icon="text_fields", page=p),
+            labelled_row("Replace Single Newlines", newlines_sw,
+                         tooltip="Replace single newlines with spaces before processing.", page=p),
+            labelled_row("Replace ALL CAPS Words", caps_sw, page=p),
+            labelled_row("Normalize Opening CAPS", norm_sw, page=p),
+            labelled_row("Replace Numerals (spoken)", numerals_sw, page=p),
+            labelled_row("Fix Non-standard Punctuation", punct_sw, page=p),
+            build_divider(p),
+            labelled_row("Word Substitutions", wordsub_sw, page=p),
+            labelled_row("Case Sensitive", case_sw, page=p),
+            ft.Text("Substitution rules  (word|replacement, one per line):",
+                    size=12, color=pal.text_secondary),
+            wordsub_tf,
+            build_divider(p),
+            build_section_header("Chapter Options", icon="library_books", page=p),
+            labelled_row("Announce Book Title (intro)", title_intro_sw, page=p),
+            labelled_row("Announce Book Title (outro)", outro_sw, page=p),
+            labelled_row("Auto-prefix Chapter Titles", prefix_sw, page=p),
+            labelled_row("Chunk Level", chunk_dd, page=p),
+            labelled_row("Use spaCy Segmentation", spacy_sw, page=p),
+        ], spacing=SPACE_MD), page=p)
+
+        # ── Subtitle card ─────────────────────────────────────────────
+        sub_modes = ["Disabled", "Line", "Sentence", "Sentence + Comma",
+                     "Sentence + Highlighting"] + [f"{i} word{'s' if i > 1 else ''}" for i in range(1, 11)]
+        sub_mode_dd = _dd(
+            [(m, m) for m in sub_modes],
+            s.subtitle_mode,
+            lambda e: self._save("subtitle_mode", e.control.value),
+        )
+        sub_fmt_dd = _dd(
+            [(k, lbl) for k, lbl in SUBTITLE_FORMATS],
+            s.subtitle_format,
+            lambda e: self._save("subtitle_format", e.control.value),
+        )
+
+        def _mk_mw_slider():
+            lbl = ft.Text(str(s.max_subtitle_words), size=12, width=36)
+            sl = ft.Slider(
+                min=1, max=200, value=s.max_subtitle_words, divisions=199, label="{value}",
+                expand=True,
+                on_change=lambda e: (self._save("max_subtitle_words", int(e.control.value)),
+                                     setattr(lbl, "value", str(int(e.control.value))),
+                                     self._page.update()),
+            )
+            return ft.Row([sl, lbl], expand=True, spacing=SPACE_SM)
+
+        sub_speed_dd = _dd(
+            [("tts", "TTS duration"), ("silence", "Silence detection")],
+            s.subtitle_speed_method,
+            lambda e: self._save("subtitle_speed_method", e.control.value),
+        )
+        silent_gaps_sw = _sw(s.use_silent_gaps,
+                             lambda e: self._save("use_silent_gaps", e.control.value))
+
+        subtitle_card = build_card(ft.Column([
+            build_section_header("Subtitles", icon="subtitles", page=p),
+            labelled_row("Mode", sub_mode_dd, page=p),
+            labelled_row("Format", sub_fmt_dd, page=p),
+            labelled_row("Max Words / Block", _mk_mw_slider(), page=p),
+            labelled_row("Speed Method", sub_speed_dd, page=p),
+            labelled_row("Silent Gaps", silent_gaps_sw, page=p),
+        ], spacing=SPACE_MD), page=p)
+
+        # ── Pipeline card ─────────────────────────────────────────────
+        provider_dd = _dd(
+            [("kokoro", "Kokoro (default)"), ("supertonic", "Supertonic")],
+            s.tts_provider,
+            lambda e: self._save("tts_provider", e.control.value),
+        )
+        gpu_sw = _sw(s.use_gpu, lambda e: self._save("use_gpu", e.control.value),
+                     label="GPU acceleration (if available)")
+
+        def _mk_steps_slider():
+            lbl = ft.Text(str(s.supertonic_total_steps), size=12, width=28)
+            sl = ft.Slider(
+                min=2, max=15, value=s.supertonic_total_steps, divisions=13,
+                label="{value}", expand=True,
+                on_change=lambda e: (self._save("supertonic_total_steps", int(e.control.value)),
+                                     setattr(lbl, "value", str(int(e.control.value))),
+                                     self._page.update()),
+            )
+            return ft.Row([sl, lbl], expand=True, spacing=SPACE_SM)
+
+        thresh_tf = ft.TextField(
+            value=str(s.speaker_analysis_threshold), width=80,
+            keyboard_type=ft.KeyboardType.NUMBER, border_radius=RADIUS_SM,
+            on_change=lambda e: self._save_int("speaker_analysis_threshold", e.control.value, 1, 25),
+        )
+        silence_tf = ft.TextField(
+            value=str(s.silence_duration), width=80,
+            keyboard_type=ft.KeyboardType.NUMBER, border_radius=RADIUS_SM,
+            on_change=lambda e: self._save_float("silence_duration", e.control.value, 0.0),
+        )
+        intro_tf = ft.TextField(
+            value=str(s.chapter_intro_delay), width=80,
+            keyboard_type=ft.KeyboardType.NUMBER, border_radius=RADIUS_SM,
+            on_change=lambda e: self._save_float("chapter_intro_delay", e.control.value, 0.0),
+        )
+
+        pipeline_card = build_card(ft.Column([
+            build_section_header("TTS Pipeline", icon="settings", page=p),
+            labelled_row("Provider", provider_dd, page=p),
+            labelled_row("GPU Acceleration", gpu_sw, page=p),
+            labelled_row("Supertonic Steps", _mk_steps_slider(), page=p),
+            build_divider(p),
+            labelled_row("Speaker Analysis Threshold", thresh_tf, page=p),
+            labelled_row("Silence Between Chapters (s)", silence_tf, page=p),
+            labelled_row("Chapter Intro Delay (s)", intro_tf, page=p),
+        ], spacing=SPACE_MD), page=p)
+
+        # ── Integration card (Audiobookshelf) ─────────────────────────
+        abs_enabled_sw = _sw(s.audiobookshelf_enabled,
+                             lambda e: self._save("audiobookshelf_enabled", e.control.value))
+        abs_url_tf = ft.TextField(value=s.audiobookshelf_base_url, hint_text="http://abs-server:13378",
+                                  expand=True, border_radius=RADIUS_SM, text_size=12,
+                                  on_change=lambda e: self._save("audiobookshelf_base_url", e.control.value))
+        abs_token_tf = ft.TextField(value=s.audiobookshelf_api_token, password=True,
+                                    can_reveal_password=True, expand=True,
+                                    border_radius=RADIUS_SM, text_size=12,
+                                    on_change=lambda e: self._save("audiobookshelf_api_token", e.control.value))
+        abs_lib_tf = ft.TextField(value=s.audiobookshelf_library_id, hint_text="Library ID",
+                                  expand=True, border_radius=RADIUS_SM, text_size=12,
+                                  on_change=lambda e: self._save("audiobookshelf_library_id", e.control.value))
+        abs_auto_sw = _sw(s.audiobookshelf_auto_send,
+                          lambda e: self._save("audiobookshelf_auto_send", e.control.value))
+
+        integ_card = build_card(ft.Column([
+            build_section_header("Audiobookshelf Integration",
+                                 icon="cloud_upload", page=p),
+            labelled_row("Enabled", abs_enabled_sw, page=p),
+            labelled_row("Server URL", abs_url_tf, page=p),
+            labelled_row("API Token", abs_token_tf, page=p),
+            labelled_row("Library ID", abs_lib_tf, page=p),
+            labelled_row("Auto-upload on finish", abs_auto_sw, page=p),
+        ], spacing=SPACE_MD), page=p)
+
+        save_btn = build_primary_button(
+            "Save Settings", icon="save",
+            on_click=self._on_save, page=p,
+        )
+
+        return ft.Column([
+            output_card,
+            ft.Container(height=SPACE_MD),
+            text_card,
+            ft.Container(height=SPACE_MD),
+            subtitle_card,
+            ft.Container(height=SPACE_MD),
+            pipeline_card,
+            ft.Container(height=SPACE_MD),
+            integ_card,
+            ft.Container(height=SPACE_LG),
+            save_btn,
+            ft.Container(height=SPACE_LG),
+        ], spacing=0, scroll=ft.ScrollMode.AUTO, expand=True)
+
+    # ------------------------------------------------------------------
+    # Helpers
+    # ------------------------------------------------------------------
+
+    def _save(self, attr: str, value) -> None:
+        setattr(self._state, attr, value)
+
+    def _save_int(self, attr: str, raw: str, lo: int, hi: int) -> None:
+        try:
+            v = max(lo, min(hi, int(raw)))
+            setattr(self._state, attr, v)
+        except ValueError:
+            pass
+
+    def _save_float(self, attr: str, raw: str, lo: float) -> None:
+        try:
+            v = max(lo, float(raw))
+            setattr(self._state, attr, v)
+        except ValueError:
+            pass
+
+    def _on_save(self, _: ft.ControlEvent) -> None:
+        self._state.persist_config()
+        show_snack(self._page, "Settings saved.")

abogen/hf_tracker.py

@@ -19,7 +19,7 @@ def tracked_hf_hub_download(*args, **kwargs):
     try:
         local_kwargs = dict(kwargs)
         local_kwargs["local_files_only"] = True
-        return hf_hub_download(*args, **local_kwargs)
+        hf_hub_download(*args, **local_kwargs)
     except Exception:
         repo_id = kwargs.get("repo_id", "<unknown repo>")
         filename = kwargs.get("filename", "<unknown file>")

abogen/infrastructure/exporters.py

@@ -1,447 +0,0 @@
-from __future__ import annotations
-
-import json
-import logging
-import tempfile
-from dataclasses import dataclass
-from pathlib import Path
-from typing import Any, Dict, List, Optional, Mapping, Sequence
-
-import static_ffmpeg
-
-from abogen.domain.metadata_helpers import (
-    normalize_metadata_casefold,
-    split_people_field,
-    split_simple_list,
-    first_nonempty,
-    extract_year,
-    normalize_series_sequence,
-    build_audiobookshelf_metadata as _build_abs_metadata,
-    load_audiobookshelf_chapters as _load_abs_chapters,
-    _SERIES_SEQUENCE_TAG_KEYS,
-)
-from abogen.epub3.exporter import build_epub3_package
-from abogen.integrations.audiobookshelf import (
-    AudiobookshelfClient,
-    AudiobookshelfConfig,
-    AudiobookshelfUploadError,
-)
-from abogen.utils import create_process
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class ExportConfig:
-    """Configuration for export operations."""
-    ffmpeg_path: str = "ffmpeg"
-    verify_ssl: bool = True
-
-
-class ExportService:
-    """Unified service for audiobook exports (M4B, FFMETADATA, EPUB3, Audiobookshelf)."""
-    
-    def __init__(self, config: Optional[ExportConfig] = None):
-        self.config = config or ExportConfig()
-        static_ffmpeg.add_paths()
-    
-    # ----------------------------------------------------------------------
-    # FFMETADATA
-    # ----------------------------------------------------------------------
-    
-    def render_ffmetadata(
-        self,
-        metadata: Dict[str, Any],
-        chapters: List[Dict[str, Any]],
-    ) -> str:
-        """Render FFMETADATA content."""
-        lines = [";FFMETADATA1"]
-        
-        for key, value in (metadata or {}).items():
-            if value is None:
-                continue
-            key_str = str(key).strip()
-            if not key_str:
-                continue
-            lines.append(f"{key_str}={self._escape_ffmetadata_value(value)}")
-        
-        for chapter in chapters or []:
-            start = chapter.get("start")
-            end = chapter.get("end")
-            if start is None or end is None:
-                continue
-            try:
-                start_ms = max(0, int(round(float(start) * 1000)))
-                end_ms = int(round(float(end) * 1000))
-            except (TypeError, ValueError):
-                continue
-            if end_ms <= start_ms:
-                end_ms = start_ms + 1
-            lines.append("[CHAPTER]")
-            lines.append("TIMEBASE=1/1000")
-            lines.append(f"START={start_ms}")
-            lines.append(f"END={end_ms}")
-            title = chapter.get("title")
-            if title:
-                lines.append(f"title={self._escape_ffmetadata_value(title)}")
-            voice = chapter.get("voice")
-            if voice:
-                lines.append(f"voice={self._escape_ffmetadata_value(voice)}")
-        
-        return "\n".join(lines) + "\n"
-    
-    @staticmethod
-    def _escape_ffmetadata_value(value: Any) -> str:
-        escaped = str(value).replace("\\", "\\\\").replace("\n", "\\n")
-        escaped = escaped.replace("=", "\\=").replace(";", "\\;").replace("#", "\\#")
-        return escaped
-    
-    def write_ffmetadata_file(
-        self,
-        audio_path: Path,
-        metadata: Dict[str, Any],
-        chapters: List[Dict[str, Any]],
-    ) -> Optional[Path]:
-        """Write FFMETADATA file to temp location."""
-        content = self.render_ffmetadata(metadata, chapters)
-        if content.strip() == ";FFMETADATA1":
-            return None
-        
-        directory = audio_path.parent if audio_path.parent.exists() else Path(tempfile.gettempdir())
-        with tempfile.NamedTemporaryFile(
-            mode="w",
-            encoding="utf-8",
-            suffix=".ffmeta",
-            delete=False,
-            dir=str(directory),
-        ) as handle:
-            handle.write(content)
-            return Path(handle.name)
-    
-    # ----------------------------------------------------------------------
-    # M4B Export
-    # ----------------------------------------------------------------------
-    
-    def embed_m4b_metadata(
-        self,
-        audio_path: Path,
-        metadata: Dict[str, Any],
-        chapters: List[Dict[str, Any]],
-        cover_path: Optional[Path] = None,
-        cover_mime: Optional[str] = None,
-        log_callback: Optional[callable] = None,
-    ) -> None:
-        """Embed metadata and chapters into M4B file using FFmpeg + Mutagen."""
-        ffmetadata_path = self.write_ffmetadata_file(audio_path, metadata, chapters)
-        
-        metadata_args = self._metadata_to_ffmpeg_args(metadata)
-        
-        cmd = ["ffmpeg", "-y", "-i", str(audio_path)]
-        
-        if ffmetadata_path:
-            cmd.extend(["-f", "ffmetadata", "-i", str(ffmetadata_path)])
-        
-        if cover_path and cover_path.exists():
-            cmd.extend(["-i", str(cover_path)])
-            cmd.extend(["-map", "0:a"])
-            cmd.extend(["-map", "1:v:0", "-c:v:0", "mjpeg", "-disposition:v:0", "attached_pic"])
-            if cover_mime:
-                cmd.extend(["-metadata:s:v:0", f"mimetype={cover_mime}"])
-            cmd.extend(["-metadata:s:v:0", "title=Cover Art"])
-        else:
-            cmd.extend(["-map", "0:a"])
-        
-        cmd.extend(["-c:a", "copy"])
-        
-        if ffmetadata_path:
-            cmd.extend(["-map_metadata", "1", "-map_chapters", "1"])
-        else:
-            cmd.extend(["-map_metadata", "0"])
-        
-        if metadata_args:
-            cmd.extend(metadata_args)
-        
-        cmd.extend(["-movflags", "+faststart+use_metadata_tags"])
-        
-        temp_output = audio_path.with_suffix(audio_path.suffix + ".tmp")
-        if audio_path.suffix.lower() in {".m4b", ".mp4", ".m4a"}:
-            cmd.extend(["-f", "mp4"])
-        cmd.append(str(temp_output))
-        
-        if log_callback:
-            log_callback("Embedding metadata into M4B output")
-        
-        process = create_process(cmd, text=True)
-        return_code = process.wait()
-        
-        if ffmetadata_path and ffmetadata_path.exists():
-            try:
-                ffmetadata_path.unlink()
-            except OSError:
-                pass
-        
-        if return_code != 0:
-            if temp_output.exists():
-                temp_output.unlink(missing_ok=True)
-            raise RuntimeError(f"ffmpeg failed to embed metadata (exit code {return_code})")
-        
-        temp_output.replace(audio_path)
-        
-        if log_callback:
-            log_callback("Embedded metadata and chapters into M4B output", "info")
-        
-        # Apply chapters via Mutagen for better compatibility
-        self._apply_m4b_chapters_mutagen(audio_path, chapters, log_callback)
-    
-    @staticmethod
-    def _metadata_to_ffmpeg_args(metadata: Dict[str, Any]) -> List[str]:
-        args = []
-        for key, value in (metadata or {}).items():
-            if value in (None, ""):
-                continue
-            key_str = str(key).strip()
-            if not key_str:
-                continue
-            normalized_key = key_str.lower()
-            if normalized_key == "year":
-                ffmpeg_key = "date"
-            else:
-                ffmpeg_key = key_str
-            args.extend(["-metadata", f"{ffmpeg_key}={value}"])
-        return args
-    
-    def _apply_m4b_chapters_mutagen(
-        self,
-        audio_path: Path,
-        chapters: List[Dict[str, Any]],
-        log_callback: Optional[callable] = None,
-    ) -> bool:
-        """Apply chapter atoms using Mutagen."""
-        if not chapters:
-            return False
-        
-        try:
-            from fractions import Fraction
-            from mutagen.mp4 import MP4, MP4Chapter
-        except ImportError:
-            if log_callback:
-                log_callback("Unable to write MP4 chapter atoms because mutagen is not installed.", "warning")
-            return False
-        
-        try:
-            mp4 = MP4(str(audio_path))
-        except Exception as exc:
-            if log_callback:
-                log_callback(f"Failed to open m4b for chapter embedding: {exc}", "warning")
-            return False
-        
-        chapter_objects = []
-        for index, entry in enumerate(sorted(chapters, key=lambda item: float(item.get("start") or 0.0))):
-            start_raw = entry.get("start")
-            if start_raw is None:
-                continue
-            try:
-                start_seconds = max(0.0, float(start_raw))
-            except (TypeError, ValueError):
-                continue
-            
-            title_value = entry.get("title")
-            title_text = str(title_value) if title_value else f"Chapter {index + 1}"
-            
-            start_fraction = Fraction(int(round(start_seconds * 1000)), 1000)
-            chapter_atom = MP4Chapter(start_fraction, title_text)
-            
-            end_raw = entry.get("end")
-            if end_raw is not None:
-                try:
-                    end_seconds = float(end_raw)
-                except (TypeError, ValueError):
-                    end_seconds = None
-                if end_seconds is not None and end_seconds > start_seconds:
-                    chapter_atom.end = Fraction(int(round(end_seconds * 1000)), 1000)
-            
-            chapter_objects.append(chapter_atom)
-        
-        if not chapter_objects:
-            return False
-        
-        try:
-            mp4.chapters = chapter_objects
-            mp4.save()
-        except Exception as exc:
-            if log_callback:
-                log_callback(f"Failed to persist MP4 chapter atoms: {exc}", "warning")
-            return False
-        
-        if log_callback:
-            log_callback(f"Applied {len(chapter_objects)} chapter markers via mutagen", "info")
-        return True
-    
-    # ----------------------------------------------------------------------
-    # EPUB3 Export
-    # ----------------------------------------------------------------------
-    
-    def export_epub3(
-        self,
-        output_path: Path,
-        book_id: str,
-        extraction: Any,  # ExtractionResult
-        metadata_tags: Dict[str, Any],
-        chapter_markers: Sequence[Dict[str, Any]],
-        chunk_markers: Sequence[Dict[str, Any]],
-        chunks: Iterable[Dict[str, Any]],
-        audio_path: Path,
-        speaker_mode: str = "single",
-        cover_path: Optional[Path] = None,
-        cover_mime: Optional[str] = None,
-    ) -> Path:
-        """Export EPUB3 with media overlays."""
-        return build_epub3_package(
-            output_path=output_path,
-            book_id=book_id,
-            extraction=extraction,
-            metadata_tags=metadata_tags,
-            chapter_markers=chapter_markers,
-            chunk_markers=chunk_markers,
-            chunks=chunks,
-            audio_path=audio_path,
-            speaker_mode=speaker_mode,
-            cover_image_path=cover_path,
-            cover_image_mime=cover_mime,
-        )
-    
-    # ----------------------------------------------------------------------
-    # Audiobookshelf Integration
-    # ----------------------------------------------------------------------
-    
-    def build_audiobookshelf_metadata(self, job: Any) -> Dict[str, Any]:
-        """Build Audiobookshelf metadata from job."""
-        filename = Path(getattr(job, "original_filename", "") or "").stem or "Audiobook"
-        return _build_abs_metadata(
-            getattr(job, "metadata_tags", {}),
-            language=getattr(job, "language", "") or "",
-            filename=filename,
-        )
-
-    def load_audiobookshelf_chapters(self, job: Any) -> Optional[List[Dict[str, Any]]]:
-        """Load chapters from job artifacts for Audiobookshelf."""
-        metadata_ref = job.result.artifacts.get("metadata") if getattr(job, "result", None) else None
-        if not metadata_ref:
-            return None
-        metadata_path = metadata_ref if isinstance(metadata_ref, Path) else Path(str(metadata_ref))
-        return _load_abs_chapters(metadata_path)
-    
-    def upload_audiobookshelf(
-        self,
-        job: Any,
-        audio_path: Path,
-        subtitle_paths: List[Path],
-        chapters: List[Dict[str, Any]],
-        metadata: Dict[str, Any],
-        cover_path: Optional[Path] = None,
-        config: Optional[AudiobookshelfConfig] = None,
-        log_callback: Optional[callable] = None,
-    ) -> None:
-        """Upload to Audiobookshelf."""
-        if config is None:
-            cfg = getattr(job, "_abs_config", None)
-            if cfg is None:
-                from abogen.utils import load_config
-                global_cfg = load_config() or {}
-                abs_cfg = global_cfg.get("audiobookshelf")
-                if isinstance(abs_cfg, Mapping):
-                    config = AudiobookshelfConfig(
-                        base_url=str(abs_cfg.get("base_url") or "").strip(),
-                        api_token=str(abs_cfg.get("api_token") or "").strip(),
-                        library_id=str(abs_cfg.get("library_id") or "").strip(),
-                        collection_id=(str(abs_cfg.get("collection_id") or "").strip() or None),
-                        folder_id=str(abs_cfg.get("folder_id") or "").strip(),
-                        verify_ssl=self._coerce_bool(abs_cfg.get("verify_ssl"), True),
-                        send_cover=self._coerce_bool(abs_cfg.get("send_cover"), True),
-                        send_chapters=self._coerce_bool(abs_cfg.get("send_chapters"), True),
-                        send_subtitles=self._coerce_bool(abs_cfg.get("send_subtitles"), False),
-                        timeout=float(abs_cfg.get("timeout", 3600.0)),
-                    )
-                else:
-                    if log_callback:
-                        log_callback("Audiobookshelf upload skipped: not configured", "warning")
-                    return
-
-        if not config.base_url or not config.api_token or not config.library_id:
-            if log_callback:
-                log_callback("Audiobookshelf upload skipped: configure base URL, API token, and library ID first", "warning")
-            return
-        if not config.folder_id:
-            if log_callback:
-                log_callback("Audiobookshelf upload skipped: enter folder name or ID in settings", "warning")
-            return
-
-        if not audio_path.exists():
-            if log_callback:
-                log_callback("Audiobookshelf upload skipped: audio output not found", "warning")
-            return
-        
-        existing_subtitles = [p for p in subtitle_paths if p.exists()] if config.send_subtitles else None
-        chapters_to_send = chapters if config.send_chapters else None
-        
-        client = AudiobookshelfClient(config)
-        
-        display_title = metadata.get("title") or audio_path.stem
-        try:
-            existing_items = client.find_existing_items(display_title, folder_id=config.folder_id)
-        except AudiobookshelfUploadError as exc:
-            if log_callback:
-                log_callback(f"Audiobookshelf lookup failed: {exc}", "error")
-            return
-        
-        if existing_items:
-            if log_callback:
-                log_callback(f"Removing existing Audiobookshelf item(s) for '{display_title}' before upload.", "info")
-            try:
-                client.delete_items(existing_items)
-            except Exception as exc:
-                if log_callback:
-                    log_callback(f"Failed to remove existing item(s): {exc}", "warning")
-        
-        cover_to_send = cover_path
-        if config.send_cover and cover_to_send:
-            if isinstance(cover_to_send, str):
-                cover_to_send = Path(cover_to_send)
-            if not cover_to_send.exists():
-                cover_to_send = None
-        
-        client.upload_audiobook(
-            audio_path,
-            metadata=metadata,
-            cover_path=cover_to_send,
-            chapters=chapters_to_send,
-            subtitles=existing_subtitles,
-        )
-        
-        if log_callback:
-            log_callback("Audiobookshelf upload queued.", "info")
-    
-    # ----------------------------------------------------------------------
-    # Helpers
-    # ----------------------------------------------------------------------
-    
-    @staticmethod
-    def _coerce_bool(value: Any, default: bool = True) -> bool:
-        if isinstance(value, bool):
-            return value
-        if isinstance(value, str):
-            lowered = value.strip().lower()
-            if lowered in {"true", "1", "yes", "on"}:
-                return True
-            if lowered in {"false", "0", "no", "off"}:
-                return False
-            return default
-        if value is None:
-            return default
-        return bool(value)
-
-
-__all__ = [
-    "ExportConfig",
-    "ExportService",
-]

abogen/infrastructure/subtitle_writer.py

@@ -1,357 +0,0 @@
-from __future__ import annotations
-
-from abc import ABC, abstractmethod
-from dataclasses import dataclass
-from enum import Enum
-from pathlib import Path
-from typing import List, Optional, TextIO
-
-from abogen.domain.enums import SubtitleFormat, SubtitleMode
-from abogen.subtitle_utils import clean_subtitle_text
-
-
-class SubtitleAlignment(Enum):
-    LEFT = "left"
-    CENTER = "center"
-    NARROW = "narrow"
-    CENTER_NARROW = "center_narrow"
-
-
-@dataclass
-class SubtitleConfig:
-    """Configuration for subtitle writer."""
-    format: SubtitleFormat
-    mode: SubtitleMode
-    alignment: SubtitleAlignment = SubtitleAlignment.LEFT
-    max_words: int = 50
-    highlight_color: str = "&H00FFFF00"  # ASS highlight color
-
-
-class SubtitleWriter(ABC):
-    """Abstract base class for subtitle writers."""
-    
-    def __init__(self, path: Path, config: SubtitleConfig):
-        self.path = path
-        self.config = config
-        self._file: Optional[TextIO] = None
-        self._index = 0
-        self._opened = False
-    
-    def open(self) -> None:
-        """Open the subtitle file and write header."""
-        if self._opened:
-            return
-        self._file = open(self.path, "w", encoding="utf-8", errors="replace")
-        self._write_header()
-        self._opened = True
-    
-    @abstractmethod
-    def _write_header(self) -> None:
-        pass
-    
-    def write_entry(
-        self,
-        start: float,
-        end: float,
-        text: str,
-        voice: Optional[str] = None,
-    ) -> None:
-        """Write a subtitle entry."""
-        if not self._opened:
-            self.open()
-        
-        text = clean_subtitle_text(text)
-        if not text:
-            return
-        
-        self._index += 1
-        self._write_entry(self._index, start, end, text, voice)
-    
-    @abstractmethod
-    def _write_entry(
-        self,
-        index: int,
-        start: float,
-        end: float,
-        text: str,
-        voice: Optional[str],
-    ) -> None:
-        pass
-    
-    def close(self) -> None:
-        """Close the subtitle file."""
-        if self._file:
-            self._file.close()
-            self._file = None
-            self._opened = False
-    
-    def __enter__(self) -> "SubtitleWriter":
-        self.open()
-        return self
-    
-    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
-        self.close()
-
-
-class SrtWriter(SubtitleWriter):
-    """SRT subtitle writer."""
-    
-    def _write_header(self) -> None:
-        pass  # SRT has no header
-    
-    def _write_entry(
-        self,
-        index: int,
-        start: float,
-        end: float,
-        text: str,
-        voice: Optional[str],
-    ) -> None:
-        start_str = self._format_time(start)
-        end_str = self._format_time(end)
-        
-        if voice:
-            text = f"[{voice}] {text}"
-        
-        self._file.write(f"{index}\n")
-        self._file.write(f"{start_str} --> {end_str}\n")
-        self._file.write(f"{text}\n\n")
-    
-    @staticmethod
-    def _format_time(seconds: float) -> str:
-        hours = int(seconds // 3600)
-        minutes = int((seconds % 3600) // 60)
-        secs = int(seconds % 60)
-        millis = int((seconds - int(seconds)) * 1000)
-        return f"{hours:02d}:{minutes:02d}:{secs:02d},{millis:03d}"
-
-
-class VttWriter(SubtitleWriter):
-    """WebVTT subtitle writer."""
-    
-    def _write_header(self) -> None:
-        self._file.write("WEBVTT\n\n")
-    
-    def _write_entry(
-        self,
-        index: int,
-        start: float,
-        end: float,
-        text: str,
-        voice: Optional[str],
-    ) -> None:
-        start_str = self._format_time(start)
-        end_str = self._format_time(end)
-        
-        if voice:
-            text = f"[{voice}] {text}"
-        
-        self._file.write(f"{index}\n")
-        self._file.write(f"{start_str} --> {end_str}\n")
-        self._file.write(f"{text}\n\n")
-    
-    @staticmethod
-    def _format_time(seconds: float) -> str:
-        hours = int(seconds // 3600)
-        minutes = int((seconds % 3600) // 60)
-        secs = seconds % 60
-        return f"{hours:02d}:{minutes:02d}:{secs:06.3f}".replace(".", ".")
-
-
-class AssWriter(SubtitleWriter):
-    """ASS subtitle writer with karaoke highlighting support."""
-    
-    def __init__(self, path: Path, config: SubtitleConfig):
-        super().__init__(path, config)
-        self._is_centered = config.alignment in (SubtitleAlignment.CENTER, SubtitleAlignment.CENTER_NARROW)
-        self._is_narrow = config.alignment in (SubtitleAlignment.NARROW, SubtitleAlignment.CENTER_NARROW)
-    
-    def _write_header(self) -> None:
-        margin = "90" if self._is_narrow else "10"
-        alignment = "5" if self._is_centered else "2"
-        
-        self._file.write("[Script Info]\n")
-        self._file.write("Title: Generated by Abogen\n")
-        self._file.write("ScriptType: v4.00+\n\n")
-        
-        # Styles
-        self._file.write("[V4+ Styles]\n")
-        self._file.write(
-            "Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, "
-            "OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, "
-            "ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, "
-            "Alignment, MarginL, MarginR, MarginV, Encoding\n"
-        )
-        
-        if self.config.mode == SubtitleMode.SENTENCE_HIGHLIGHT:
-            # Karaoke style with highlighting
-            self._file.write(
-                f"Style: Default,Arial,24,&H00FFFFFF,&H00808080,&H00000000,&H00404040,"
-                f"0,0,0,0,100,100,0,0,3,2,0,{alignment},{margin},{margin},10,1\n"
-            )
-            self._file.write(
-                f"Style: Highlight,Arial,24,&H0000FFFF,&H00808080,&H00000000,&H00404040,"
-                f"0,0,0,0,100,100,0,0,3,2,0,{alignment},{margin},{margin},10,1\n\n"
-            )
-        else:
-            self._file.write(
-                f"Style: Default,Arial,24,&H00FFFFFF,&H00808080,&H00000000,&H00404040,"
-                f"0,0,0,0,100,100,0,0,3,2,0,{alignment},{margin},{margin},10,1\n\n"
-            )
-        
-        self._file.write("[Events]\n")
-        self._file.write(
-            "Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text\n"
-        )
-    
-    def _write_entry(
-        self,
-        index: int,
-        start: float,
-        end: float,
-        text: str,
-        voice: Optional[str],
-    ) -> None:
-        start_str = self._format_time(start)
-        end_str = self._format_time(end)
-        
-        if voice:
-            text = f"[{voice}] {text}"
-        
-        style = "Default"
-        if self.config.mode == SubtitleMode.SENTENCE_HIGHLIGHT:
-            # Add karaoke tags for highlighting
-            text = self._add_karaoke_tags(text)
-            style = "Highlight"
-        
-        alignment_tag = r"{\an5}" if self._is_centered else ""
-        self._file.write(
-            f"Dialogue: 0,{start_str},{end_str},{style},,0,0,0,,{alignment_tag}{text}\n"
-        )
-    
-    def _add_karaoke_tags(self, text: str) -> str:
-        """Add karaoke highlighting tags to text."""
-        # Simple word-level karaoke timing
-        words = text.split()
-        if not words:
-            return text
-        
-        # This is a simplified version - real karaoke needs per-word timing
-        # For now, just return the text with the highlight color
-        return r"{\k100}" + r"{\k100}".join(words) + r"{\k0}"
-    
-    @staticmethod
-    def _format_time(seconds: float) -> str:
-        hours = int(seconds // 3600)
-        minutes = int((seconds % 3600) // 60)
-        secs = seconds % 60
-        return f"{hours}:{minutes:02d}:{secs:05.2f}"
-
-
-def create_subtitle_writer(
-    path: Path,
-    format: str,
-    mode: str,
-    alignment: str = "left",
-    max_words: int = 50,
-) -> SubtitleWriter:
-    """Factory function to create subtitle writer."""
-    fmt = SubtitleFormat(format.lower())
-    mode = SubtitleMode(mode)
-    align = SubtitleAlignment(alignment.lower())
-
-    config = SubtitleConfig(
-        format=fmt,
-        mode=mode,
-        alignment=align,
-        max_words=max_words,
-    )
-
-    if fmt == SubtitleFormat.SRT:
-        return SrtWriter(path, config)
-    elif fmt == SubtitleFormat.VTT:
-        return VttWriter(path, config)
-    elif fmt == SubtitleFormat.ASS:
-        return AssWriter(path, config)
-    else:
-        raise ValueError(f"Unsupported subtitle format: {format}")
-
-
-def resolve_subtitle_format(
-    subtitle_format: str | None,
-    subtitle_mode: str,
-) -> tuple[str, str]:
-    """Resolve a subtitle_format setting string to (file_extension, alignment).
-
-    Handles the PyQt convention where format strings encode alignment
-    (e.g. ``"ass_centered_narrow"`` → extension ``"ass"``, alignment
-    ``"center_narrow"``).
-
-    Also enforces that ``"Sentence + Highlighting"`` mode requires ASS.
-
-    Returns:
-        Tuple of (file_extension, alignment) suitable for
-        :func:`create_subtitle_writer`.
-    """
-    fmt = (subtitle_format or "srt").lower()
-
-    if subtitle_mode == "Sentence + Highlighting" and fmt == "srt":
-        fmt = "ass"
-
-    if "ass" in fmt:
-        extension = "ass"
-        if "centered_narrow" in fmt:
-            alignment = "center_narrow"
-        elif "centered" in fmt:
-            alignment = "center"
-        elif "narrow" in fmt:
-            alignment = "narrow"
-        else:
-            alignment = "left"
-    else:
-        extension = fmt if fmt in ("srt", "vtt") else "srt"
-        alignment = "left"
-
-    return extension, alignment
-
-
-def make_subtitle_writer(
-    audio_path: Path,
-    subtitle_format: str | None,
-    subtitle_mode: str,
-    max_words: int = 50,
-) -> SubtitleWriter | None:
-    """Convenience: resolve format and create a writer, or return None if disabled.
-
-    Returns ``None`` when ``subtitle_mode`` is ``"Disabled"`` or the
-    format is unsupported.
-    """
-    if subtitle_mode == "Disabled":
-        return None
-
-    extension, alignment = resolve_subtitle_format(subtitle_format, subtitle_mode)
-    try:
-        return create_subtitle_writer(
-            audio_path.with_suffix(f".{extension}"),
-            extension,
-            subtitle_mode,
-            alignment=alignment,
-            max_words=max_words,
-        )
-    except (ValueError, KeyError):
-        return None
-
-
-__all__ = [
-    "SubtitleFormat",
-    "SubtitleMode",
-    "SubtitleAlignment",
-    "SubtitleConfig",
-    "SubtitleWriter",
-    "SrtWriter",
-    "VttWriter",
-    "AssWriter",
-    "create_subtitle_writer",
-    "resolve_subtitle_format",
-    "make_subtitle_writer",
-]

abogen/integrations/audiobookshelf.py

@@ -2,7 +2,9 @@ from __future__ import annotations
 
 import json
 import logging
+import math
 import mimetypes
+import re
 from contextlib import ExitStack
 from dataclasses import dataclass
 from pathlib import Path
@@ -10,8 +12,6 @@ from typing import Any, Dict, Iterable, List, Mapping, Optional, Sequence, Tuple
 
 import httpx
 
-from abogen.domain.metadata_helpers import normalize_series_sequence
-
 logger = logging.getLogger(__name__)
 
 
@@ -641,7 +641,40 @@ class AudiobookshelfClient:
         for key in preferred_keys:
             if key not in metadata:
                 continue
-            normalized = normalize_series_sequence(metadata.get(key))
+            normalized = AudiobookshelfClient._normalize_series_sequence(metadata.get(key))
             if normalized:
                 return normalized
         return ""
+
+    @staticmethod
+    def _normalize_series_sequence(raw: Any) -> str:
+        if raw is None:
+            return ""
+
+        if isinstance(raw, (int, float)):
+            if isinstance(raw, float) and (math.isnan(raw) or math.isinf(raw)):
+                return ""
+            text = str(raw)
+        else:
+            text = str(raw).strip()
+
+        if not text:
+            return ""
+
+        candidate = text.replace(",", ".")
+        match = re.search(r"\d+(?:\.\d+)?", candidate)
+        if not match:
+            return ""
+
+        normalized = match.group(0)
+        if "." in normalized:
+            normalized = normalized.rstrip("0").rstrip(".")
+            if not normalized:
+                normalized = "0"
+            return normalized
+
+        try:
+            return str(int(normalized))
+        except ValueError:
+            cleaned = normalized.lstrip("0")
+            return cleaned or "0"

abogen/main.py

@@ -2,14 +2,13 @@
 
 from __future__ import annotations
 
+import atexit
 import os
 import platform
+import signal
+import sys
 
-# Initialise global shutdown handling (atexit, signals, Qt) as early as possible.
-from abogen import shutdown  # noqa: F401
-shutdown.register_shutdown()
-
-from abogen.utils import load_config
+from abogen.utils import load_config, prevent_sleep_end
 from abogen.webui.app import main as _run_web_ui
 
 # Configure Hugging Face Hub behaviour (mirrors legacy GUI defaults).
@@ -28,6 +27,17 @@ os.environ.setdefault("MIOPEN_CONV_PRECISE_ROCM_TUNING", "0")
 if platform.system() == "Darwin" and platform.processor() == "arm":
     os.environ.setdefault("PYTORCH_ENABLE_MPS_FALLBACK", "1")
 
+atexit.register(prevent_sleep_end)
+
+
+def _cleanup_sleep(signum, _frame):
+    prevent_sleep_end()
+    sys.exit(0)
+
+
+signal.signal(signal.SIGINT, _cleanup_sleep)
+signal.signal(signal.SIGTERM, _cleanup_sleep)
+
 
 def main() -> None:
     """Launch the Flask-based web UI."""

abogen/predownload_gui.py

@@ -21,8 +21,7 @@ from PyQt6.QtWidgets import (
 )
 from PyQt6.QtCore import QThread, pyqtSignal
 
-from abogen.constants import COLORS
-from abogen.tts_plugin.utils import get_voices
+from abogen.constants import COLORS, VOICES_INTERNAL
 from abogen.spacy_utils import SPACY_MODELS
 import abogen.hf_tracker
 
@@ -115,7 +114,7 @@ class PreDownloadWorker(QThread):
             self._voices_success = False
             return
 
-        voice_list = get_voices("kokoro")
+        voice_list = VOICES_INTERNAL
         for idx, voice in enumerate(voice_list, start=1):
             if self._cancelled:
                 self._voices_success = False
@@ -463,14 +462,14 @@ class PreDownloadDialog(QDialog):
         try:
             from huggingface_hub import try_to_load_from_cache
 
-            for voice in get_voices("kokoro"):
+            for voice in VOICES_INTERNAL:
                 if not try_to_load_from_cache(
                     repo_id="hexgrad/Kokoro-82M", filename=f"voices/{voice}.pt"
                 ):
                     missing.append(voice)
         except Exception:
             # If HF missing, report all as missing
-            return False, list(get_voices("kokoro"))
+            return False, list(VOICES_INTERNAL)
         return (len(missing) == 0), missing
 
     def _check_kokoro_model(self) -> bool:

abogen/pyqt/book_handler.py

@@ -29,12 +29,6 @@ from abogen.utils import (
     get_resource_path,
 )
 from abogen.book_parser import get_book_parser
-from abogen.domain.metadata_extraction import (
-    extract_book_metadata_epub,
-    extract_book_metadata_pdf,
-    extract_book_metadata_markdown,
-    format_metadata_tags,
-)
 
 from abogen.subtitle_utils import (
     clean_text,
@@ -954,14 +948,169 @@ class HandlerDialog(QDialog):
         self.previewEdit.setHtml(html_content)
 
     def _extract_book_metadata(self):
+        metadata = {
+            "title": None,
+            "authors": [],
+            "description": None,
+            "cover_image": None,
+            "publisher": None,
+            "publication_year": None,
+        }
+
         if self.parser.file_type == "epub":
-            return extract_book_metadata_epub(self.book)
+            try:
+                title_items = self.book.get_metadata("DC", "title")
+                if title_items and len(title_items) > 0:
+                    metadata["title"] = title_items[0][0]
+            except Exception as e:
+                logging.warning(f"Error extracting title metadata: {e}")
+
+            try:
+                author_items = self.book.get_metadata("DC", "creator")
+                if author_items:
+                    metadata["authors"] = [
+                        author[0] for author in author_items if len(author) > 0
+                    ]
+            except Exception as e:
+                logging.warning(f"Error extracting author metadata: {e}")
+
+            try:
+                desc_items = self.book.get_metadata("DC", "description")
+                if desc_items and len(desc_items) > 0:
+                    metadata["description"] = desc_items[0][0]
+            except Exception as e:
+                logging.warning(f"Error extracting description metadata: {e}")
+
+            try:
+                publisher_items = self.book.get_metadata("DC", "publisher")
+                if publisher_items and len(publisher_items) > 0:
+                    metadata["publisher"] = publisher_items[0][0]
+            except Exception as e:
+                logging.warning(f"Error extracting publisher metadata: {e}")
+
+            # Try to extract publication year
+            try:
+                date_items = self.book.get_metadata("DC", "date")
+                if date_items and len(date_items) > 0:
+                    date_str = date_items[0][0]
+                    # Try to extract just the year from the date string
+                    year_match = re.search(r"\b(19|20)\d{2}\b", date_str)
+                    if year_match:
+                        metadata["publication_year"] = year_match.group(0)
+                    else:
+                        metadata["publication_year"] = date_str
+            except Exception as e:
+                logging.warning(f"Error extracting publication date metadata: {e}")
+
+            for item in self.book.get_items_of_type(ebooklib.ITEM_COVER):
+                metadata["cover_image"] = item.get_content()
+                break
+
+            if not metadata["cover_image"]:
+                for item in self.book.get_items_of_type(ebooklib.ITEM_IMAGE):
+                    if "cover" in item.get_name().lower():
+                        metadata["cover_image"] = item.get_content()
+                        break
         elif self.parser.file_type == "markdown":
-            return extract_book_metadata_markdown(
-                self.markdown_text, self.markdown_toc
-            )
+            # Extract metadata from markdown frontmatter or first heading
+            if self.markdown_text:
+                # Try to extract YAML frontmatter
+                frontmatter_match = re.match(
+                    r"^---\s*\n(.*?)\n---\s*\n", self.markdown_text, re.DOTALL
+                )
+                if frontmatter_match:
+                    try:
+                        frontmatter = frontmatter_match.group(1)
+                        # Simple YAML-like parsing for common fields
+                        title_match = re.search(
+                            r"^title:\s*(.+)$",
+                            frontmatter,
+                            re.MULTILINE | re.IGNORECASE,
+                        )
+                        if title_match:
+                            metadata["title"] = (
+                                title_match.group(1).strip().strip("\"'")
+                            )
+
+                        author_match = re.search(
+                            r"^author:\s*(.+)$",
+                            frontmatter,
+                            re.MULTILINE | re.IGNORECASE,
+                        )
+                        if author_match:
+                            metadata["authors"] = [
+                                author_match.group(1).strip().strip("\"'")
+                            ]
+
+                        desc_match = re.search(
+                            r"^description:\s*(.+)$",
+                            frontmatter,
+                            re.MULTILINE | re.IGNORECASE,
+                        )
+                        if desc_match:
+                            metadata["description"] = (
+                                desc_match.group(1).strip().strip("\"'")
+                            )
+
+                        date_match = re.search(
+                            r"^date:\s*(.+)$", frontmatter, re.MULTILINE | re.IGNORECASE
+                        )
+                        if date_match:
+                            date_str = date_match.group(1).strip().strip("\"'")
+                            year_match = re.search(r"\b(19|20)\d{2}\b", date_str)
+                            if year_match:
+                                metadata["publication_year"] = year_match.group(0)
+                    except Exception as e:
+                        logging.warning(f"Error parsing markdown frontmatter: {e}")
+
+                # Fallback: use first H1 header as title if no frontmatter title
+                if not metadata["title"] and self.markdown_toc:
+                    # Find the first level 1 header
+                    first_h1 = next(
+                        (h for h in self.markdown_toc if h["level"] == 1), None
+                    )
+                    if first_h1:
+                        metadata["title"] = first_h1["name"]
         else:
-            return extract_book_metadata_pdf(self.pdf_doc)
+            pdf_info = self.pdf_doc.metadata
+            if pdf_info:
+                metadata["title"] = pdf_info.get("title", None)
+
+                author = pdf_info.get("author", None)
+                if author:
+                    metadata["authors"] = [author]
+
+                metadata["description"] = pdf_info.get("subject", None)
+
+                keywords = pdf_info.get("keywords", None)
+                if keywords:
+                    if metadata["description"]:
+                        metadata["description"] += f"\n\nKeywords: {keywords}"
+                    else:
+                        metadata["description"] = f"Keywords: {keywords}"
+
+                metadata["publisher"] = pdf_info.get("creator", None)
+
+                # Try to extract publication date from PDF metadata
+                if "creationDate" in pdf_info:
+                    date_str = pdf_info["creationDate"]
+                    year_match = re.search(r"D:(\d{4})", date_str)
+                    if year_match:
+                        metadata["publication_year"] = year_match.group(1)
+                elif "modDate" in pdf_info:
+                    date_str = pdf_info["modDate"]
+                    year_match = re.search(r"D:(\d{4})", date_str)
+                    if year_match:
+                        metadata["publication_year"] = year_match.group(1)
+
+            if len(self.pdf_doc) > 0:
+                try:
+                    pix = self.pdf_doc[0].get_pixmap(matrix=fitz.Matrix(2, 2))
+                    metadata["cover_image"] = pix.tobytes("png")
+                except Exception:
+                    pass
+
+        return metadata
 
     def get_selected_text(self):
         # If a background loader thread is running, wait for it to finish to
@@ -987,21 +1136,59 @@ class HandlerDialog(QDialog):
 
     def _format_metadata_tags(self):
         """Format metadata tags for insertion at the beginning of the text"""
+        import datetime
         from abogen.utils import get_user_cache_path
 
+        metadata = self.book_metadata
         filename = os.path.splitext(os.path.basename(self.book_path))[0]
-        chapter_count = len(self.checked_chapters)
-        cache_dir = get_user_cache_path()
+        current_year = str(datetime.datetime.now().year)
 
-        return format_metadata_tags(
-            self.book_metadata,
-            filename,
-            chapter_count,
-            self.parser.file_type,
-            cover_bytes=self.book_metadata.get("cover_image"),
-            cache_dir=cache_dir,
+        # Get values with fallbacks
+        title = metadata.get("title") or filename
+        authors = metadata.get("authors") or ["Unknown"]
+        authors_text = ", ".join(authors)
+        album_artist = authors_text or "Unknown"
+        year = (
+            metadata.get("publication_year") or current_year
+        )  # Use publication year if available
+
+        # Count chapters/pages
+        total_chapters = len(self.checked_chapters)
+        chapter_text = (
+            f"{total_chapters} {'Chapters' if self.parser.file_type == 'epub' else 'Pages'}"
         )
 
+        # Handle cover image
+        cover_tag = ""
+        if metadata.get("cover_image"):
+            try:
+                import uuid
+
+                cache_dir = get_user_cache_path()
+                cover_path = os.path.join(cache_dir, f"cover_{uuid.uuid4()}.jpg")
+                cover_path = os.path.normpath(cover_path)
+                with open(cover_path, "wb") as f:
+                    f.write(metadata["cover_image"])
+                cover_tag = f"<<METADATA_COVER_PATH:{cover_path}>>"
+            except Exception as e:
+                logging.warning(f"Failed to save cover image: {e}")
+
+        # Format metadata tags
+        metadata_tags = [
+            f"<<METADATA_TITLE:{title}>>",
+            f"<<METADATA_ARTIST:{authors_text}>>",
+            f"<<METADATA_ALBUM:{title} ({chapter_text})>>",
+            f"<<METADATA_YEAR:{year}>>",
+            f"<<METADATA_ALBUM_ARTIST:{album_artist}>>",
+            f"<<METADATA_COMPOSER:Narrator>>",
+            f"<<METADATA_GENRE:Audiobook>>",
+        ]
+
+        if cover_tag:
+            metadata_tags.append(cover_tag)
+
+        return "\n".join(metadata_tags)
+
     def _get_markdown_selected_text(self):
         """Get selected text from markdown chapters"""
         all_checked_identifiers = set()

abogen/pyqt/conversion_adapter.py

@@ -1,192 +0,0 @@
-"""PyQt adapter: ConversionThread -> ConversionRequest.
-
-Converts a PyQt ConversionThread into a ConversionRequest that the application layer can process.
-This adapter is the bridge between the PyQt layer and the application/domain layer.
-
-The adapter is responsible for:
-- Mapping ConversionThread fields to ConversionRequest fields
-- Handling UI-specific state (signals, dialogs, cancellation)
-- Providing PipelineProvider and VoiceResolver implementations
-
-Subtitle file/timestamp special paths remain in ConversionThread.run() early return.
-"""
-
-from __future__ import annotations
-
-import os
-from pathlib import Path
-from typing import Any, Callable, Dict, List, Optional
-
-from abogen.application.conversion_request import ConversionRequest
-from abogen.application.conversion_ports import ConversionCancelled, ResolvedVoice
-
-
-def build_conversion_request_from_thread(thread: Any) -> ConversionRequest:
-    """Convert a PyQt ConversionThread into a ConversionRequest.
-
-    This is the primary function that maps thread fields to ConversionRequest.
-    All fields are copied — the request is independent of the thread.
-
-    Args:
-        thread: PyQt ConversionThread instance
-
-    Returns:
-        ConversionRequest with all thread data mapped
-    """
-    # Determine source path
-    source_path = None
-    is_direct_text = getattr(thread, "is_direct_text", False)
-    if not is_direct_text and thread.file_name:
-        source_path = Path(thread.file_name)
-
-    # Determine original filename
-    original_filename = ""
-    if getattr(thread, "from_queue", False):
-        base_path = getattr(thread, "save_base_path", None) or thread.file_name
-    else:
-        base_path = getattr(thread, "display_path", None) or thread.file_name
-
-    if base_path:
-        original_filename = os.path.basename(base_path)
-
-    # Determine output folder
-    output_folder = None
-    if thread.output_folder:
-        output_folder = Path(thread.output_folder)
-
-    return ConversionRequest(
-        # Source
-        source_path=source_path,
-        direct_text=thread.file_name if is_direct_text else None,
-        original_filename=original_filename,
-        # TTS Settings
-        language=thread.lang_code,
-        tts_provider="kokoro",  # PyQt uses Kokoro by default
-        voice=thread.voice,
-        voice_profile=getattr(thread, "voice_profile", None),
-        speed=thread.speed,
-        use_gpu=thread.use_gpu,
-        supertonic_total_steps=getattr(thread, "supertonic_total_steps", 5),
-        # Output Format
-        output_format=thread.output_format,
-        subtitle_mode=thread.subtitle_mode,
-        subtitle_format=getattr(thread, "subtitle_format", "srt"),
-        max_subtitle_words=getattr(thread, "max_subtitle_words", 50),
-        # Save Options
-        save_mode=thread.save_option,
-        output_folder=output_folder,
-        save_chapters_separately=getattr(thread, "save_chapters_separately", False),
-        merge_chapters_at_end=getattr(thread, "merge_chapters_at_end", True),
-        separate_chapters_format=getattr(thread, "separate_chapters_format", "wav"),
-        save_as_project=getattr(thread, "save_as_project", False),
-        # Timing
-        silence_between_chapters=getattr(thread, "silence_duration", 2.0),
-        chapter_intro_delay=getattr(thread, "chapter_intro_delay", 0.0),
-        # Content Processing
-        replace_single_newlines=getattr(thread, "replace_single_newlines", False),
-        read_title_intro=getattr(thread, "read_title_intro", False),
-        read_closing_outro=getattr(thread, "read_closing_outro", True),
-        auto_prefix_chapter_titles=getattr(thread, "auto_prefix_chapter_titles", True),
-        normalize_chapter_opening_caps=getattr(thread, "normalize_chapter_opening_caps", False),
-        # Pronunciation / Normalization
-        pronunciation_overrides=getattr(thread, "pronunciation_overrides", []) or [],
-        manual_overrides=getattr(thread, "manual_overrides", []) or [],
-        heteronym_overrides=getattr(thread, "heteronym_overrides", []) or [],
-        normalization_overrides=getattr(thread, "normalization_overrides", None),
-        # Chapter/Chunk Configuration
-        chapter_overrides=[],  # PyQt doesn't use chapter overrides from GUI
-        chunks=[],  # PyQt doesn't use chunks from GUI
-        chunk_level="paragraph",
-        speaker_mode="single",
-        speakers={},
-        # Metadata
-        metadata_tags=getattr(thread, "metadata_tags", {}) or {},
-        # Artifacts
-        cover_image_path=getattr(thread, "cover_image_path", None),
-        cover_image_mime=getattr(thread, "cover_image_mime", None),
-        generate_epub3=getattr(thread, "generate_epub3", False),
-    )
-
-
-class PyQtEvents:
-    """PyQt implementation of ConversionEvents protocol.
-
-    Wraps a ConversionThread to provide logging, progress, and cancellation.
-    """
-
-    def __init__(self, thread: Any):
-        self._thread = thread
-
-    def log(self, message: str, level: str = "info") -> None:
-        """Log a message via signal."""
-        self._thread.log_updated.emit((message, _level_to_color(level)))
-
-    def progress(self, pct: int, etr: str) -> None:
-        """Update progress via signal."""
-        self._thread.progress_updated.emit(pct, etr)
-
-    def check_cancelled(self) -> None:
-        """Check if conversion was cancelled.
-
-        Raises:
-            ConversionCancelled: If cancellation was requested
-        """
-        if self._thread.cancel_requested:
-            raise ConversionCancelled("Conversion cancelled by user")
-
-
-class PyQtPipelineProvider:
-    """PyQt implementation of PipelineProvider protocol.
-
-    Wraps the existing backend from ConversionThread.
-    """
-
-    def __init__(self, backend: Any):
-        self._backend = backend
-
-    def get(self, provider: str, language: str, use_gpu: bool) -> Any:
-        """Get a TTS backend instance.
-
-        For PyQt, this returns the pre-initialized backend.
-        """
-        return self._backend
-
-    def dispose_all(self) -> None:
-        """Dispose all backend resources."""
-        pass  # PyQt manages backend lifecycle in thread
-
-
-class PyQtVoiceResolver:
-    """PyQt implementation of VoiceResolver protocol.
-
-    Wraps load_voice_cached from the ConversionThread.
-    """
-
-    def __init__(self, thread: Any):
-        self._thread = thread
-
-    def resolve(self, voice_spec: str) -> ResolvedVoice:
-        """Resolve a voice spec into a loaded voice."""
-        from abogen.domain.voice_resolution import resolve_fallback_voice_spec
-
-        # Use thread's load_voice_cached method
-        loaded_voice = self._thread.load_voice_cached(voice_spec, self._thread.backend)
-
-        return ResolvedVoice(
-            provider="kokoro",
-            resolved_spec=voice_spec,
-            voice=loaded_voice,
-            speed=self._thread.speed,
-            supertonic_steps=getattr(self._thread, "supertonic_total_steps", 5),
-        )
-
-
-def _level_to_color(level: str) -> str:
-    """Map log level to PyQt color string."""
-    colors = {
-        "info": "grey",
-        "warning": "orange",
-        "error": "red",
-        "debug": "grey",
-    }
-    return colors.get(level, "grey")

abogen/pyqt/gui.py

@@ -7,7 +7,6 @@ import base64
 import re
 from abogen.pyqt.queue_manager_gui import QueueManager
 from abogen.pyqt.queued_item import QueuedItem
-
 import abogen.hf_tracker as hf_tracker
 import hashlib  # Added for cache path generation
 from PyQt6.QtWidgets import (
@@ -83,18 +82,14 @@ from abogen.constants import (
     GITHUB_URL,
     PROGRAM_DESCRIPTION,
     LANGUAGE_DESCRIPTIONS,
+    VOICES_INTERNAL,
     SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION,
     COLORS,
     SUBTITLE_FORMATS,
 )
-from abogen.tts_plugin.utils import get_voices
 import threading
 from abogen.pyqt.voice_formula_gui import VoiceFormulaDialog
 from abogen.voice_profiles import load_profiles
-from abogen.domain.settings_core import all_settings_defaults
-
-# Module-level default cache for use outside __init__
-_DEFAULTS = all_settings_defaults()
 
 # Import ctypes for Windows-specific taskbar icon
 if platform.system() == "Windows":
@@ -842,7 +837,7 @@ class WordSubstitutionsDialog(QDialog):
             self,
         )
         instructions.setStyleSheet(
-            f"padding: 10px; background-color: {COLORS['GREY_BACKGROUND']}; border-radius: 5px;"
+            "padding: 10px; background-color: #f0f0f0; border-radius: 5px;"
         )
         instructions.setWordWrap(True)
         layout.addWidget(instructions)
@@ -916,10 +911,9 @@ class abogen(QWidget):
     def __init__(self):
         super().__init__()
         self.config = load_config()
-        _d = all_settings_defaults()
-        self.apply_theme(self.config.get("theme", _d["theme"]))
+        self.apply_theme(self.config.get("theme", "system"))
         migrate_subtitle_format(self.config)
-        self.check_updates = self.config.get("check_updates", _d["check_updates"])
+        self.check_updates = self.config.get("check_updates", True)
         self.save_option = self.config.get("save_option", "Save next to input file")
         self.selected_output_folder = self.config.get("selected_output_folder", None)
         self.selected_file = self.selected_file_type = self.selected_book_path = None
@@ -927,7 +921,7 @@ class abogen(QWidget):
             None  # Add new variable to track the displayed file path
         )
         # Max log lines
-        self.log_window_max_lines = self.config.get("log_window_max_lines", _d["log_window_max_lines"])
+        self.log_window_max_lines = self.config.get("log_window_max_lines", 2000)
         self.selected_chapters = set()
         self.last_opened_book_path = None  # Track the last opened book path
         self.last_output_path = None
@@ -942,28 +936,40 @@ class abogen(QWidget):
             self.selected_voice = None
             self.selected_lang = None
         else:
-            self.selected_voice = self.config.get("selected_voice", _d["selected_voice"])
+            self.selected_voice = self.config.get("selected_voice", "af_heart")
             self.selected_lang = self.selected_voice[0] if self.selected_voice else None
         self.is_converting = False
-        self.subtitle_mode = self.config.get("subtitle_mode", _d["subtitle_mode"])
-        self.max_subtitle_words = self.config.get("max_subtitle_words", _d["max_subtitle_words"])
-        self.silence_duration = self.config.get("silence_duration", _d.get("silence_between_chapters", 2.0))
-        self.selected_format = self.config.get("selected_format", _d["selected_format"])
-        self.separate_chapters_format = self.config.get("separate_chapters_format", _d["separate_chapters_format"])
-        self.use_gpu = self.config.get("use_gpu", _d["use_gpu"])
-        self.replace_single_newlines = self.config.get("replace_single_newlines", _d.get("replace_single_newlines", True))
-        self.use_silent_gaps = self.config.get("use_silent_gaps", _d["use_silent_gaps"])
-        self.subtitle_speed_method = self.config.get("subtitle_speed_method", _d["subtitle_speed_method"])
-        self.use_spacy_segmentation = self.config.get("use_spacy_segmentation", _d["use_spacy_segmentation"])
-        self.read_title_intro = self.config.get("read_title_intro", _d.get("read_title_intro", False))
-        self.read_closing_outro = self.config.get("read_closing_outro", _d.get("read_closing_outro", True))
+        self.subtitle_mode = self.config.get("subtitle_mode", "Sentence")
+        self.max_subtitle_words = self.config.get(
+            "max_subtitle_words", 50
+        )  # Default max words per subtitle
+        self.silence_duration = self.config.get(
+            "silence_duration", 2.0
+        )  # Default silence duration
+        self.selected_format = self.config.get("selected_format", "wav")
+        self.separate_chapters_format = self.config.get(
+            "separate_chapters_format", "wav"
+        )  # Format for individual chapter files
+        self.use_gpu = self.config.get(
+            "use_gpu", True  # Load GPU setting with default True
+        )
+        self.replace_single_newlines = self.config.get("replace_single_newlines", True)
+        self.use_silent_gaps = self.config.get("use_silent_gaps", True)
+        self.subtitle_speed_method = self.config.get("subtitle_speed_method", "tts")
+        self.use_spacy_segmentation = self.config.get("use_spacy_segmentation", True)
         # Word substitution settings
-        self.word_substitutions_enabled = self.config.get("word_substitutions_enabled", _d["word_substitutions_enabled"])
-        self.word_substitutions_list = self.config.get("word_substitutions_list", _d["word_substitutions_list"])
-        self.case_sensitive_substitutions = self.config.get("case_sensitive_substitutions", _d["case_sensitive_substitutions"])
-        self.replace_all_caps = self.config.get("replace_all_caps", _d["replace_all_caps"])
-        self.replace_numerals = self.config.get("replace_numerals", _d["replace_numerals"])
-        self.fix_nonstandard_punctuation = self.config.get("fix_nonstandard_punctuation", _d["fix_nonstandard_punctuation"])
+        self.word_substitutions_enabled = self.config.get(
+            "word_substitutions_enabled", False
+        )
+        self.word_substitutions_list = self.config.get("word_substitutions_list", "")
+        self.case_sensitive_substitutions = self.config.get(
+            "case_sensitive_substitutions", False
+        )
+        self.replace_all_caps = self.config.get("replace_all_caps", False)
+        self.replace_numerals = self.config.get("replace_numerals", False)
+        self.fix_nonstandard_punctuation = self.config.get(
+            "fix_nonstandard_punctuation", False
+        )
         self._pending_close_event = None
         self.gpu_ok = False  # Initialize GPU availability status
 
@@ -991,7 +997,7 @@ class abogen(QWidget):
         self.current_queue_index = 0
 
         self.initUI()
-        self.speed_slider.setValue(int(self.config.get("speed", _d["speed"]) * 100))
+        self.speed_slider.setValue(int(self.config.get("speed", 1.00) * 100))
         self.update_speed_label()
         # Set initial selection: prefer profile, else voice
         idx = -1
@@ -1867,7 +1873,7 @@ class abogen(QWidget):
         for pname in load_profiles().keys():
             self.voice_combo.addItem(profile_icon, pname, f"profile:{pname}")
         # re-add voices
-        for v in get_voices("kokoro"):
+        for v in VOICES_INTERNAL:
             icon = QIcon()
             flag_path = get_resource_path("abogen.assets.flags", f"{v[0]}.png")
             if flag_path and os.path.exists(flag_path):
@@ -2154,7 +2160,7 @@ class abogen(QWidget):
             )
 
             # CHECK GLOBAL OVERRIDE SETTING
-            if not self.config.get("queue_override_settings", _DEFAULTS["queue_override_settings"]):
+            if not self.config.get("queue_override_settings", False):
                 self.selected_lang = queued_item.lang_code
                 self.speed_slider.setValue(int(queued_item.speed * 100))
                 
@@ -2228,10 +2234,11 @@ class abogen(QWidget):
             self.current_queue_index = 0  # Reset for next time
 
     def get_voice_formula(self) -> str:
-        from abogen.voice_formulas import pairs_to_formula
-
         if self.mixed_voice_state:
-            return pairs_to_formula(self.mixed_voice_state) or ""
+            formula_components = [
+                f"{name}*{weight}" for name, weight in self.mixed_voice_state
+            ]
+            return " + ".join(filter(None, formula_components))
         else:
             return self.selected_voice
 
@@ -2309,9 +2316,9 @@ class abogen(QWidget):
             file_size_str = "Unknown"
 
         # pipeline_loaded_callback remains unchanged
-        def pipeline_loaded_callback(backend, error):
+        def pipeline_loaded_callback(np_module, kpipeline_class, error):
             if error:
-                self.update_log((f"Error loading TTS backend: {error}", "red"))
+                self.update_log((f"Error loading numpy or KPipeline: {error}", "red"))
                 prevent_sleep_end()
                 return
 
@@ -2334,7 +2341,8 @@ class abogen(QWidget):
                 self.selected_output_folder,
                 subtitle_mode=actual_subtitle_mode,
                 output_format=self.selected_format,
-                backend=backend,
+                np_module=np_module,
+                kpipeline_class=kpipeline_class,
                 start_time=self.start_time,
                 total_char_count=self.char_count,
                 use_gpu=self.gpu_ok,
@@ -2395,9 +2403,6 @@ class abogen(QWidget):
                 self.conversion_thread.merge_chapters_at_end = getattr(
                     self, "merge_chapters_at_end", True
                 )
-            # Pass intro/outro settings
-            self.conversion_thread.read_title_intro = self.read_title_intro
-            self.conversion_thread.read_closing_outro = self.read_closing_outro
             self.conversion_thread.progress_updated.connect(self.update_progress)
             self.conversion_thread.log_updated.connect(self.update_log)
             self.conversion_thread.conversion_finished.connect(
@@ -2421,11 +2426,7 @@ class abogen(QWidget):
             self.gpu_ok = gpu_ok
             self.update_log((gpu_msg, gpu_ok))
             self.update_log("Loading modules...")
-
-            lang_code = self.selected_lang or "a"
-            load_thread = LoadPipelineThread(
-                pipeline_loaded_callback, lang_code=lang_code, use_gpu=gpu_ok
-            )
+            load_thread = LoadPipelineThread(pipeline_loaded_callback)
             load_thread.start()
 
         threading.Thread(target=gpu_and_load, daemon=True).start()
@@ -2436,7 +2437,7 @@ class abogen(QWidget):
             return
 
         # Check if override was active (this determines which settings were ACTUALLY used)
-        override_active = self.config.get("queue_override_settings", _DEFAULTS["queue_override_settings"])
+        override_active = self.config.get("queue_override_settings", False)
 
         # If override is ON, capture the global settings that were used for processing
         if override_active:
@@ -2862,18 +2863,18 @@ class abogen(QWidget):
             )
             self.loading_movie.start()
 
-        lang = self.selected_lang or "a"
-        load_thread = LoadPipelineThread(
-            self._on_pipeline_loaded_for_preview, lang_code=lang, use_gpu=self.gpu_ok
-        )
+        def pipeline_loaded_callback(np_module, kpipeline_class, error):
+            self._on_pipeline_loaded_for_preview(np_module, kpipeline_class, error)
+
+        load_thread = LoadPipelineThread(pipeline_loaded_callback)
         load_thread.start()
 
-    def _on_pipeline_loaded_for_preview(self, backend, error):
+    def _on_pipeline_loaded_for_preview(self, np_module, kpipeline_class, error):
         # stop loading animation and restore icon on error
         if error:
             self.loading_movie.stop()
             self._show_error_message_box(
-                "Loading Error", f"Error loading TTS backend: {error}"
+                "Loading Error", f"Error loading numpy or KPipeline: {error}"
             )
             self.btn_preview.setIcon(self.play_icon)
             self.btn_preview.setEnabled(True)
@@ -2911,7 +2912,7 @@ class abogen(QWidget):
         gpu_msg, gpu_ok = get_gpu_acceleration(self.use_gpu)
 
         self.preview_thread = VoicePreviewThread(
-            backend, lang, voice, speed, gpu_ok
+            np_module, kpipeline_class, lang, voice, speed, gpu_ok
         )
         self.preview_thread.finished.connect(self._play_preview_audio)
         self.preview_thread.error.connect(self._preview_error)
@@ -3214,16 +3215,12 @@ class abogen(QWidget):
             )
             box.setDefaultButton(QMessageBox.StandardButton.No)
             if box.exec() == QMessageBox.StandardButton.Yes:
-                from abogen import shutdown
-                shutdown.request_shutdown()
                 self.cleanup_conversion_thread()
                 self.cleanup_preview_threads()
                 event.accept()
             else:
                 event.ignore()
         else:
-            from abogen import shutdown
-            shutdown.request_shutdown()
             self.cleanup_conversion_thread()
             self.cleanup_preview_threads()
             event.accept()
@@ -3412,7 +3409,7 @@ class abogen(QWidget):
         app.installEventFilter(app._dark_titlebar_event_filter)
 
         # Save config if changed
-        if self.config.get("theme", _DEFAULTS["theme"]) != theme:
+        if self.config.get("theme", "system") != theme:
             self.config["theme"] = theme
             save_config(self.config)
 
@@ -3434,7 +3431,7 @@ class abogen(QWidget):
         ]
 
         # Get current theme from config, default to "system"
-        current_theme = self.config.get("theme", _DEFAULTS["theme"])
+        current_theme = self.config.get("theme", "system")
         for value, text in theme_options:
             theme_action = QAction(text, self)
             theme_action.setCheckable(True)
@@ -3565,27 +3562,6 @@ class abogen(QWidget):
         # Add separator
         menu.addSeparator()
 
-        # Add title intro option
-        self.title_intro_action = QAction("Read title intro before first chapter", self)
-        self.title_intro_action.setCheckable(True)
-        self.title_intro_action.setChecked(self.read_title_intro)
-        self.title_intro_action.triggered.connect(
-            lambda checked: self.toggle_read_title_intro(checked)
-        )
-        menu.addAction(self.title_intro_action)
-
-        # Add closing outro option
-        self.closing_outro_action = QAction("Read closing outro after last chapter", self)
-        self.closing_outro_action.setCheckable(True)
-        self.closing_outro_action.setChecked(self.read_closing_outro)
-        self.closing_outro_action.triggered.connect(
-            lambda checked: self.toggle_read_closing_outro(checked)
-        )
-        menu.addAction(self.closing_outro_action)
-
-        # Add separator
-        menu.addSeparator()
-
         # Add "Pre-download models and voices for offline use" option
         predownload_action = QAction(
             "Pre-download models and voices for offline use", self
@@ -3597,7 +3573,7 @@ class abogen(QWidget):
         disable_kokoro_action = QAction("Disable Kokoro's internet access", self)
         disable_kokoro_action.setCheckable(True)
         disable_kokoro_action.setChecked(
-            self.config.get("disable_kokoro_internet", _DEFAULTS["disable_kokoro_internet"])
+            self.config.get("disable_kokoro_internet", False)
         )
         disable_kokoro_action.triggered.connect(
             lambda checked: self.toggle_kokoro_internet_access(checked)
@@ -3607,7 +3583,7 @@ class abogen(QWidget):
         # Add check for updates option
         check_updates_action = QAction("Check for updates at startup", self)
         check_updates_action.setCheckable(True)
-        check_updates_action.setChecked(self.config.get("check_updates", _DEFAULTS["check_updates"]))
+        check_updates_action.setChecked(self.config.get("check_updates", True))
         check_updates_action.triggered.connect(self.toggle_check_updates)
         menu.addAction(check_updates_action)
 
@@ -3662,16 +3638,6 @@ class abogen(QWidget):
         self.config["use_spacy_segmentation"] = enabled
         save_config(self.config)
 
-    def toggle_read_title_intro(self, enabled):
-        self.read_title_intro = enabled
-        self.config["read_title_intro"] = enabled
-        save_config(self.config)
-
-    def toggle_read_closing_outro(self, enabled):
-        self.read_closing_outro = enabled
-        self.config["read_closing_outro"] = enabled
-        save_config(self.config)
-
     def restart_app(self):
 
         import sys
@@ -4243,7 +4209,7 @@ Categories=AudioVideo;Audio;Utility;
         """Open a dialog to set the maximum words per subtitle"""
         from PyQt6.QtWidgets import QInputDialog
 
-        current_value = self.config.get("max_subtitle_words", _DEFAULTS["max_subtitle_words"])
+        current_value = self.config.get("max_subtitle_words", 50)
 
         value, ok = QInputDialog.getInt(
             self,
@@ -4271,7 +4237,7 @@ Categories=AudioVideo;Audio;Utility;
     def set_silence_between_chapters(self):
         """Open a dialog to set the silence duration between chapters"""
 
-        current_value = self.config.get("silence_duration", _DEFAULTS.get("silence_between_chapters", 2.0))
+        current_value = self.config.get("silence_duration", 2.0)
 
         dlg = QInputDialog(self)
         dlg.setWindowTitle("Silence Duration (seconds)")

abogen/pyqt/main.py

@@ -1,10 +1,10 @@
 import os
 import sys
 import platform
+import atexit
+import signal
+from abogen.utils import get_resource_path, load_config, prevent_sleep_end
 
-# Initialise global shutdown handling (atexit, signals, Qt) as early as possible.
-from abogen import shutdown  # noqa: F401
-shutdown.register_shutdown()
 
 # Fix PyTorch DLL loading issue ([WinError 1114]) on Windows before importing PyQt6
 if platform.system() == "Windows":
@@ -46,8 +46,6 @@ except ImportError:
     print("PyQt6 not installed.")
 
 
-from abogen.utils import get_resource_path
-
 # Pre-load "libxcb-cursor" on Linux (fixes #101)
 if platform.system() == "Linux":
     arch = platform.machine().lower()
@@ -96,7 +94,6 @@ os.environ["HF_HUB_DISABLE_TELEMETRY"] = "1"  # Disable Hugging Face telemetry
 os.environ["HF_HUB_ETAG_TIMEOUT"] = "10"  # Metadata request timeout (seconds)
 os.environ["HF_HUB_DOWNLOAD_TIMEOUT"] = "10"  # File download timeout (seconds)
 os.environ["HF_HUB_DISABLE_SYMLINKS_WARNING"] = "1"  # Disable symlinks warning
-from abogen.utils import load_config
 if load_config().get("disable_kokoro_internet", False):
     print("INFO: Kokoro's internet access is disabled.")
     os.environ["HF_HUB_OFFLINE"] = "1"  # Disable Hugging Face Hub internet access
@@ -108,6 +105,25 @@ from abogen.constants import PROGRAM_NAME, VERSION
 os.environ["MIOPEN_FIND_MODE"] = "FAST"
 os.environ["MIOPEN_CONV_PRECISE_ROCM_TUNING"] = "0"
 
+# Reset sleep states
+atexit.register(prevent_sleep_end)
+
+
+# Also handle signals (Ctrl+C, kill, etc.)
+def _cleanup_sleep(signum, frame):
+    prevent_sleep_end()
+    sys.exit(0)
+
+
+signal.signal(signal.SIGINT, _cleanup_sleep)
+signal.signal(signal.SIGTERM, _cleanup_sleep)
+
+# Ensure sys.stdout and sys.stderr are valid in GUI mode
+if sys.stdout is None:
+    sys.stdout = open(os.devnull, "w")
+if sys.stderr is None:
+    sys.stderr = open(os.devnull, "w")
+
 # Enable MPS GPU acceleration on Mac Apple Silicon
 if platform.system() == "Darwin" and platform.processor() == "arm":
     os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"
@@ -120,8 +136,6 @@ def qt_message_handler(mode, context, message):
         return  # Suppress this specific message
     if "setGrabPopup called with a parent, QtWaylandClient" in message:
         return
-    if "Failed to register with host portal" in message:
-        return
 
     if mode == QtMsgType.QtWarningMsg:
         print(f"Qt Warning: {message}")
@@ -170,4 +184,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
+    main()

abogen/pyqt/predownload_gui.py

@@ -21,8 +21,7 @@ from PyQt6.QtWidgets import (
 )
 from PyQt6.QtCore import QThread, pyqtSignal
 
-from abogen.constants import COLORS
-from abogen.tts_plugin.utils import get_voices
+from abogen.constants import COLORS, VOICES_INTERNAL
 from abogen.spacy_utils import SPACY_MODELS
 import abogen.hf_tracker
 
@@ -115,7 +114,7 @@ class PreDownloadWorker(QThread):
             self._voices_success = False
             return
 
-        voice_list = get_voices("kokoro")
+        voice_list = VOICES_INTERNAL
         for idx, voice in enumerate(voice_list, start=1):
             if self._cancelled:
                 self._voices_success = False
@@ -463,14 +462,14 @@ class PreDownloadDialog(QDialog):
         try:
             from huggingface_hub import try_to_load_from_cache
 
-            for voice in get_voices("kokoro"):
+            for voice in VOICES_INTERNAL:
                 if not try_to_load_from_cache(
                     repo_id="hexgrad/Kokoro-82M", filename=f"voices/{voice}.pt"
                 ):
                     missing.append(voice)
         except Exception:
             # If HF missing, report all as missing
-            return False, list(get_voices("kokoro"))
+            return False, list(VOICES_INTERNAL)
         return (len(missing) == 0), missing
 
     def _check_kokoro_model(self) -> bool:

abogen/pyqt/voice_formula_gui.py

@@ -28,11 +28,11 @@ from PyQt6.QtWidgets import (
 from PyQt6.QtCore import Qt, QTimer, QPoint, QRect, QSize
 from PyQt6.QtGui import QPixmap, QIcon, QAction
 from abogen.constants import (
+    VOICES_INTERNAL,
     SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION,
     LANGUAGE_DESCRIPTIONS,
     COLORS,
 )
-from abogen.tts_plugin.utils import get_voices
 import re
 import platform
 from abogen.utils import get_resource_path
@@ -179,7 +179,7 @@ class VoiceMixer(QWidget):
         layout.addWidget(QLabel(name), alignment=Qt.AlignmentFlag.AlignCenter)
 
         # Voice name label with gender icon
-        is_female = self.voice_name in get_voices("kokoro") and self.voice_name[1] == "f"
+        is_female = self.voice_name in VOICES_INTERNAL and self.voice_name[1] == "f"
 
         # Icons layout (flag and gender)
         icons_layout = QHBoxLayout()
@@ -772,7 +772,7 @@ class VoiceFormulaDialog(QDialog):
 
     def add_voices(self, initial_state):
         first_enabled_voice = None
-        for voice in get_voices("kokoro"):
+        for voice in VOICES_INTERNAL:
             language_code = voice[0]  # First character is the language code
             matching_voice = next(
                 (item for item in initial_state if item[0] == voice), None

abogen/shutdown.py

@@ -1,160 +0,0 @@
-"""Graceful shutdown - single module, no over-engineering."""
-from __future__ import annotations
-
-import atexit
-import gc
-import signal
-import sys
-from typing import Callable
-
-_CLEANUP_FUNCS: list[Callable[[], None]] = []
-_EXECUTED = False
-
-
-def register_cleanup(fn: Callable[[], None]) -> None:
-    """Register a cleanup function to run on shutdown."""
-    _CLEANUP_FUNCS.append(fn)
-
-
-def _run_cleanups() -> None:
-    global _EXECUTED
-    if _EXECUTED:
-        return
-    _EXECUTED = True
-    for fn in _CLEANUP_FUNCS:
-        try:
-            fn()
-        except Exception:
-            pass
-
-
-# ---- Register built-in cleanup functions ----
-
-# 1. Restore sleep prevention
-def _restore_sleep() -> None:
-    try:
-        from abogen.utils import prevent_sleep_end
-        prevent_sleep_end()
-    except Exception:
-        pass
-
-register_cleanup(_restore_sleep)
-
-# 2. Shutdown web UI ConversionService
-def _shutdown_conversion_service() -> None:
-    try:
-        from abogen.webui.service import get_service
-        svc = get_service()
-        if svc is not None:
-            svc.shutdown()
-    except Exception:
-        pass
-
-register_cleanup(_shutdown_conversion_service)
-
-# 3. Clear TTS pipelines and GPU memory
-def _cleanup_tts_pipelines() -> None:
-    # Clear web UI pipeline cache
-    try:
-        from abogen.webui.conversion_runner import _PIPELINES
-        _PIPELINES.clear()
-    except Exception:
-        pass
-
-    # Clear PyQt conversion thread voice cache
-    try:
-        from abogen.pyqt.conversion import ConversionThread
-        if hasattr(ConversionThread, "voice_cache"):
-            ConversionThread.voice_cache.clear()
-    except Exception:
-        pass
-
-    gc.collect()
-
-    # Release CUDA cache
-    try:
-        import torch
-        if torch.cuda.is_available():
-            torch.cuda.empty_cache()
-            torch.cuda.ipc_collect()
-    except Exception:
-        pass
-
-register_cleanup(_cleanup_tts_pipelines)
-
-# 4. Clear global voice cache
-def _clear_voice_cache() -> None:
-    try:
-        from abogen.voice_cache import clear_voice_cache
-        clear_voice_cache()
-    except Exception:
-        pass
-
-register_cleanup(_clear_voice_cache)
-
-# 5. Terminate child processes (ffmpeg, etc.)
-def _terminate_subprocesses() -> None:
-    try:
-        import psutil
-    except Exception:
-        return
-
-    try:
-        current = psutil.Process()
-        for child in current.children(recursive=True):
-            try:
-                child.terminate()
-            except Exception:
-                pass
-        gone, alive = psutil.wait_procs(current.children(recursive=True), timeout=3)
-        for proc in alive:
-            try:
-                proc.kill()
-            except Exception:
-                pass
-    except Exception:
-        pass
-
-register_cleanup(_terminate_subprocesses)
-
-
-def register_shutdown() -> None:
-    """Install process-wide shutdown hooks (atexit, signals, Qt)."""
-    if register_shutdown._registered:
-        return
-    register_shutdown._registered = True
-
-    atexit.register(_run_cleanups)
-
-    # POSIX signals
-    for sig in (signal.SIGINT, signal.SIGTERM):
-        try:
-            signal.signal(sig, _on_signal)
-        except Exception:
-            pass
-
-    # Qt hook
-    try:
-        from PyQt6.QtWidgets import QApplication
-
-        app = QApplication.instance()
-        if app is not None:
-            app.aboutToQuit.connect(_run_cleanups)
-    except Exception:
-        pass
-
-
-register_shutdown._registered = False
-
-
-def _on_signal(signum: int, _frame) -> None:
-    _run_cleanups()
-    sys.exit(0)
-
-
-def request_shutdown() -> None:
-    """Programmatically trigger cleanup (e.g., from GUI closeEvent)."""
-    _run_cleanups()
-
-
-__all__ = ["register_shutdown", "request_shutdown", "register_cleanup"]

abogen/spacy_utils.py

@@ -2,36 +2,21 @@
 Lazy-loaded spaCy utilities for sentence segmentation.
 """
 
-from abogen.domain.enums import Language
-
 # Cached spaCy module and models (lazy loaded)
 _spacy = None
 _nlp_cache = {}
 
 # Language code to spaCy model mapping
 SPACY_MODELS = {
-    Language.EN_US: "en_core_web_sm",
-    Language.EN_GB: "en_core_web_sm",
-    Language.ES: "es_core_news_sm",
-    Language.FR: "fr_core_news_sm",
-    Language.IT: "it_core_news_sm",
-    Language.PT_BR: "pt_core_news_sm",
-    Language.ZH: "zh_core_web_sm",
-    Language.JA: "ja_core_news_sm",
-    Language.HI: "xx_sent_ud_sm",
-}
-
-# Kokoro single-letter codes -> Language enum (inverse of pipeline_factory._KOKORO_LANG_MAP)
-_KOKORO_TO_LANGUAGE = {
-    "a": Language.EN_US,
-    "b": Language.EN_GB,
-    "e": Language.ES,
-    "f": Language.FR,
-    "h": Language.HI,
-    "i": Language.IT,
-    "j": Language.JA,
-    "p": Language.PT_BR,
-    "z": Language.ZH,
+    "a": "en_core_web_sm",  # American English
+    "b": "en_core_web_sm",  # British English
+    "e": "es_core_news_sm",  # Spanish
+    "f": "fr_core_news_sm",  # French
+    "i": "it_core_news_sm",  # Italian
+    "p": "pt_core_news_sm",  # Brazilian Portuguese
+    "z": "zh_core_web_sm",  # Mandarin Chinese
+    "j": "ja_core_news_sm",  # Japanese
+    "h": "xx_sent_ud_sm",  # Hindi (multi-language model)
 }
 
 
@@ -51,9 +36,10 @@ def _load_spacy():
 def get_spacy_model(lang_code, log_callback=None):
     """
     Get or load a spaCy model for the given language code.
+    Downloads the model automatically if not available.
 
     Args:
-        lang_code: Language code or Language enum (e.g., "a", "en-US", Language.EN_US)
+        lang_code: Language code (a, b, e, f, etc.)
         log_callback: Optional function to log messages
 
     Returns:
@@ -72,17 +58,6 @@ def get_spacy_model(lang_code, log_callback=None):
         else:
             print(msg)
 
-    # Normalize to Language enum
-    if not isinstance(lang_code, Language):
-        if isinstance(lang_code, str) and lang_code in _KOKORO_TO_LANGUAGE:
-            lang_code = _KOKORO_TO_LANGUAGE[lang_code]
-        else:
-            try:
-                lang_code = Language.from_str(lang_code)
-            except ValueError:
-                log(f"\nspaCy: Unknown language '{lang_code}'...")
-                return None
-
     # Check if model is cached
     if lang_code in _nlp_cache:
         return _nlp_cache[lang_code]

abogen/subtitle_utils.py

@@ -466,7 +466,7 @@ def sanitize_name_for_os(name, is_folder=True):
 
 
 def validate_voice_name(voice_name):
-    """Validate voice name against available voices (case-insensitive).
+    """Validate voice name against VOICES_INTERNAL list (case-insensitive).
     Handles both single voices and formulas like 'af_heart*0.5 + am_echo*0.5'.
 
     Args:
@@ -477,10 +477,10 @@ def validate_voice_name(voice_name):
             - is_valid: True if all voices in the name/formula are valid
             - invalid_voice_name: The first invalid voice found, or None if all valid
     """
-    from abogen.tts_plugin.utils import get_voices
+    from abogen.constants import VOICES_INTERNAL
 
     # Create case-insensitive lookup set (done once per call)
-    voice_lookup_lower = {v.lower() for v in get_voices("kokoro")}
+    voice_lookup_lower = {v.lower() for v in VOICES_INTERNAL}
     voice_name = voice_name.strip()
 
     # Check if it's a formula (contains *)
@@ -505,7 +505,7 @@ def split_text_by_voice_markers(text, default_voice):
     """Split text by voice markers, returning list of (voice, text) tuples.
 
     IMPORTANT: Returns the last voice used so it can persist across chapters.
-    Voice names are normalized to lowercase to match canonical voice names.
+    Voice names are normalized to lowercase to match VOICES_INTERNAL.
 
     Args:
         text: Text potentially containing <<VOICE:name>> markers
@@ -518,7 +518,7 @@ def split_text_by_voice_markers(text, default_voice):
             - valid_count: Number of valid voice markers processed
             - invalid_count: Number of invalid voice markers skipped
     """
-    from abogen.tts_plugin.utils import get_voices
+    from abogen.constants import VOICES_INTERNAL
 
     voice_splits = list(_VOICE_MARKER_SEARCH_PATTERN.finditer(text))
 
@@ -560,7 +560,7 @@ def split_text_by_voice_markers(text, default_voice):
                         # Find the canonical (lowercase) voice name
                         voice_part_lower = voice_part.strip().lower()
                         canonical_voice = next(
-                            (v for v in get_voices("kokoro") if v.lower() == voice_part_lower),
+                            (v for v in VOICES_INTERNAL if v.lower() == voice_part_lower),
                             voice_part.strip()
                         )
                         normalized_parts.append(f"{canonical_voice}*{weight.strip()}")
@@ -569,7 +569,7 @@ def split_text_by_voice_markers(text, default_voice):
                 # Find the canonical (lowercase) voice name
                 voice_name_lower = voice_name.lower()
                 current_voice = next(
-                    (v for v in get_voices("kokoro") if v.lower() == voice_name_lower),
+                    (v for v in VOICES_INTERNAL if v.lower() == voice_name_lower),
                     voice_name
                 )
             valid_markers += 1

abogen/tts_plugin/__init__.py

@@ -1,170 +0,0 @@
-"""TTS Plugin Architecture - Public API.
-
-This package defines the frozen Plugin API for the TTS Plugin Architecture.
-All public interfaces are fully defined but contain no business logic.
-
-Public modules:
-- types: Core domain value objects (AudioFormat, Duration, VoiceSelection, etc.)
-- errors: Error hierarchy (EngineError and subtypes)
-- manifest: Plugin manifest types (PluginManifest, EngineManifest, etc.)
-- engine: Engine and EngineSession protocols
-- capabilities: Optional capability interfaces (VoiceLister, PreviewGenerator, etc.)
-- host_context: HostContext dataclass
-- plugin: Plugin contract (create_engine function signature)
-- loader: Plugin discovery and loading
-- plugin_manager: Plugin management and engine creation
-- utils: Direct utility functions (get_voices, create_pipeline, etc.)
-
-Usage:
-    from abogen.tts_plugin import (
-        # Types
-        AudioFormat,
-        Duration,
-        VoiceSelection,
-        ParameterValues,
-        SynthesisRequest,
-        SynthesizedAudio,
-        EngineConfig,
-        # Errors
-        EngineError,
-        ModelNotFoundError,
-        ModelLoadError,
-        NetworkError,
-        InvalidInputError,
-        ConfigurationError,
-        CancelledError,
-        InternalError,
-        # Manifest
-        PluginManifest,
-        EngineManifest,
-        VoiceSourceManifest,
-        VoiceManifest,
-        ParameterManifest,
-        AudioFormatManifest,
-        EnumOption,
-        RequirementManifest,
-        GpuRequirement,
-        ModelManifest,
-        # Engine
-        Engine,
-        EngineSession,
-        # Capabilities
-        VoiceLister,
-        PreviewGenerator,
-        StreamingSynthesizer,
-        CancelableSession,
-        # Host Context
-        HostContext,
-        HttpClient,
-        # Plugin Manager
-        get_plugin_manager,
-        reset_plugin_manager,
-        # Utils
-        get_voices,
-        get_default_voice,
-        is_plugin_registered,
-        resolve_voice_to_plugin,
-        create_pipeline,
-    )
-"""
-
-from abogen.tts_plugin.capabilities import (
-    CancelableSession,
-    PreviewGenerator,
-    StreamingSynthesizer,
-    VoiceLister,
-)
-from abogen.tts_plugin.engine import Engine, EngineSession
-from abogen.tts_plugin.errors import (
-    CancelledError,
-    ConfigurationError,
-    EngineError,
-    InternalError,
-    InvalidInputError,
-    ModelLoadError,
-    ModelNotFoundError,
-    NetworkError,
-)
-from abogen.tts_plugin.host_context import HttpClient, HostContext
-from abogen.tts_plugin.manifest import (
-    AudioFormatManifest,
-    EngineManifest,
-    EnumOption,
-    GpuRequirement,
-    ModelManifest,
-    ParameterManifest,
-    PluginManifest,
-    RequirementManifest,
-    VoiceManifest,
-    VoiceSourceManifest,
-)
-from abogen.tts_plugin.types import (
-    AudioFormat,
-    Duration,
-    EngineConfig,
-    ParameterValues,
-    SynthesisRequest,
-    SynthesizedAudio,
-    VoiceSelection,
-)
-
-# Plugin Manager and Utils
-from abogen.tts_plugin.plugin_manager import get_plugin_manager, reset_plugin_manager
-from abogen.tts_plugin.utils import (
-    create_pipeline,
-    get_default_voice,
-    get_voices,
-    is_plugin_registered,
-    resolve_voice_to_plugin,
-)
-
-__all__ = [
-    # Types
-    "AudioFormat",
-    "Duration",
-    "VoiceSelection",
-    "ParameterValues",
-    "SynthesisRequest",
-    "SynthesizedAudio",
-    "EngineConfig",
-    # Errors
-    "EngineError",
-    "ModelNotFoundError",
-    "ModelLoadError",
-    "NetworkError",
-    "InvalidInputError",
-    "ConfigurationError",
-    "CancelledError",
-    "InternalError",
-    # Manifest
-    "PluginManifest",
-    "EngineManifest",
-    "VoiceSourceManifest",
-    "VoiceManifest",
-    "ParameterManifest",
-    "AudioFormatManifest",
-    "EnumOption",
-    "RequirementManifest",
-    "GpuRequirement",
-    "ModelManifest",
-    # Engine
-    "Engine",
-    "EngineSession",
-    # Capabilities
-    "VoiceLister",
-    "PreviewGenerator",
-    "StreamingSynthesizer",
-    "CancelableSession",
-    # Host Context
-    "HostContext",
-    "HttpClient",
-    # Plugin Manager
-    "get_plugin_manager",
-    "reset_plugin_manager",
-    # Utils
-    "get_voices",
-    "get_default_voice",
-    "is_plugin_registered",
-    "resolve_voice_to_plugin",
-    "create_pipeline",
-]

abogen/tts_plugin/capabilities.py

@@ -1,103 +0,0 @@
-"""Capability interfaces for the TTS Plugin Architecture.
-
-This module defines optional capability interfaces that engines can implement.
-Capabilities are additive; implementing new capabilities doesn't break old plugins.
-"""
-
-from __future__ import annotations
-
-from typing import Iterator, Protocol, runtime_checkable
-
-from abogen.tts_plugin.manifest import VoiceManifest
-from abogen.tts_plugin.types import SynthesisRequest, SynthesizedAudio, VoiceSelection
-
-
-@runtime_checkable
-class VoiceLister(Protocol):
-    """Protocol for listing available voices.
-
-    Engines that support voice listing should implement this interface.
-    """
-
-    def listVoices(self, sourceId: str) -> list[VoiceManifest]:
-        """List available voices for a given source.
-
-        Args:
-            sourceId: The voice source identifier.
-
-        Returns:
-            List of VoiceManifest describing available voices.
-
-        Raises:
-            EngineError: On failure.
-        """
-        ...
-
-
-@runtime_checkable
-class PreviewGenerator(Protocol):
-    """Protocol for generating voice previews.
-
-    Engines that support voice preview should implement this interface.
-    """
-
-    def generatePreview(self, voice: VoiceSelection, text: str) -> SynthesizedAudio:
-        """Generate a preview audio for a voice.
-
-        Args:
-            voice: Voice selection for the preview.
-            text: Text to use for the preview.
-
-        Returns:
-            SynthesizedAudio with the preview audio data.
-
-        Raises:
-            EngineError: On failure.
-        """
-        ...
-
-
-@runtime_checkable
-class StreamingSynthesizer(Protocol):
-    """Protocol for streaming synthesis.
-
-    Optional capability of EngineSession, not Engine.
-    Engines that support streaming synthesis should implement this interface.
-    """
-
-    def synthesizeStream(self, request: SynthesisRequest) -> Iterator[bytes]:
-        """Synthesize audio in streaming mode.
-
-        Args:
-            request: The synthesis request.
-
-        Yields:
-            Audio chunks as they become available.
-
-        Raises:
-            CancelledError: If cancel() is called during iteration.
-            EngineError: On synthesis failure.
-        """
-        ...
-        # This is a generator function; implementation will use yield
-        yield b""  # pragma: no cover
-
-
-@runtime_checkable
-class CancelableSession(Protocol):
-    """Protocol for cancellation support.
-
-    Optional capability for engines that support cancellation.
-    cancel() causes synthesize() to raise CancelledError.
-    """
-
-    def cancel(self) -> None:
-        """Cancel in-progress synthesis.
-
-        After cancellation, synthesize() raises CancelledError.
-        The session remains usable after cancellation.
-
-        Raises:
-            EngineError: If called after dispose().
-        """
-        ...

abogen/tts_plugin/engine.py

@@ -1,95 +0,0 @@
-"""Engine interfaces for the TTS Plugin Architecture.
-
-This module defines the core Engine and EngineSession protocols.
-These are the primary interfaces that plugin implementations must satisfy.
-"""
-
-from __future__ import annotations
-
-from typing import Protocol, runtime_checkable
-
-from abogen.tts_plugin.types import SynthesisRequest, SynthesizedAudio
-
-
-@runtime_checkable
-class EngineSession(Protocol):
-    """Protocol for a session that owns mutable execution state.
-
-    An EngineSession is created by Engine.createSession() and owns
-    mutable execution state isolated from other concurrent work.
-    It is NOT thread-safe.
-
-    Lifecycle:
-        1. Created by Engine.createSession()
-        2. Used for synthesis via synthesize()
-        3. Disposed via dispose()
-
-    After dispose(), all methods except dispose() raise EngineError.
-    """
-
-    def synthesize(self, request: SynthesisRequest) -> SynthesizedAudio:
-        """Synthesize audio from text.
-
-        Args:
-            request: The synthesis request containing text, voice, parameters, and format.
-
-        Returns:
-            SynthesizedAudio with the synthesized audio data.
-
-        Raises:
-            EngineError: On synthesis failure. Session remains usable after error.
-            EngineError: If called after dispose().
-        """
-        ...
-
-    def dispose(self) -> None:
-        """Release session resources.
-
-        This method is idempotent and safe to call multiple times.
-        It never raises exceptions (catches and logs internally).
-        After dispose(), all methods except dispose() raise EngineError.
-        """
-        ...
-
-
-@runtime_checkable
-class Engine(Protocol):
-    """Protocol for a TTS engine that creates sessions.
-
-    An Engine is a factory for EngineSession instances. It is stateless
-    and thread-safe for createSession().
-
-    Lifecycle:
-        1. Created via create_engine() (plugin contract)
-        2. Sessions created via createSession()
-        3. Disposed via dispose()
-
-    Thread Safety:
-        - createSession() is thread-safe and can be called from any thread.
-        - dispose() must be called after all sessions are disposed.
-        - Disposing engine while sessions are alive violates API contract.
-    """
-
-    def createSession(self) -> EngineSession:
-        """Create a new session for synthesis.
-
-        Returns:
-            A new EngineSession instance. Ownership transfers to caller.
-
-        Raises:
-            EngineError: On failure. No partially initialized session is returned.
-        """
-        ...
-
-    def dispose(self) -> None:
-        """Release engine resources.
-
-        Caller must ensure all sessions created by this engine are disposed
-        before calling dispose(). Disposing an engine while any session is
-        still alive violates the API contract; behavior is undefined.
-
-        This method is idempotent and safe to call multiple times.
-        It never raises exceptions (catches and logs internally).
-        After dispose(), all methods except dispose() raise EngineError.
-        """
-        ...

abogen/tts_plugin/errors.py

@@ -1,62 +0,0 @@
-"""Error hierarchy for the TTS Plugin Architecture.
-
-This module defines typed exceptions that engines raise.
-Engines should never raise raw exceptions; they must use EngineError or its subtypes.
-"""
-
-from __future__ import annotations
-
-
-class EngineError(Exception):
-    """Base exception for all engine errors.
-
-    All engine operations that can fail should raise EngineError or one of its subtypes.
-    After dispose(), all methods except dispose() raise EngineError.
-    """
-
-    pass
-
-
-class ModelNotFoundError(EngineError):
-    """Raised when a required model is not found."""
-
-    pass
-
-
-class ModelLoadError(EngineError):
-    """Raised when a model fails to load."""
-
-    pass
-
-
-class NetworkError(EngineError):
-    """Raised when a network operation fails."""
-
-    pass
-
-
-class InvalidInputError(EngineError):
-    """Raised when invalid input is provided to the engine."""
-
-    pass
-
-
-class ConfigurationError(EngineError):
-    """Raised when there is a configuration error."""
-
-    pass
-
-
-class CancelledError(EngineError):
-    """Raised when an operation is cancelled.
-
-    This is raised by synthesize() when cancel() is called during synthesis.
-    """
-
-    pass
-
-
-class InternalError(EngineError):
-    """Raised when an internal engine error occurs."""
-
-    pass

abogen/tts_plugin/host_context.py

@@ -1,46 +0,0 @@
-"""Host context for the TTS Plugin Architecture.
-
-This module defines the HostContext dataclass that provides minimal
-host services to plugins. It is the only interface through which
-plugins can access host functionality.
-"""
-
-from __future__ import annotations
-
-import logging
-from dataclasses import dataclass
-from pathlib import Path
-from typing import Protocol, runtime_checkable
-
-
-@runtime_checkable
-class HttpClient(Protocol):
-    """Protocol for HTTP client provided by host.
-
-    Plugins can use this for network requests (e.g., API-based engines).
-    """
-
-    def get(self, url: str, **kwargs: object) -> object:
-        """Perform an HTTP GET request."""
-        ...
-
-    def post(self, url: str, **kwargs: object) -> object:
-        """Perform an HTTP POST request."""
-        ...
-
-
-@dataclass(frozen=True)
-class HostContext:
-    """Minimal host context provided to plugins.
-
-    Contains only essential host services. No business logic.
-
-    Attributes:
-        config_dir: Directory for API keys, preferences, and configuration.
-        logger: Logger for plugin logging.
-        http_client: HTTP client for network requests.
-    """
-
-    config_dir: Path
-    logger: logging.Logger
-    http_client: HttpClient

abogen/tts_plugin/loader.py

@@ -1,365 +0,0 @@
-"""Plugin loader infrastructure for the TTS Plugin Architecture.
-
-This module provides functionality to discover, import, validate, and load
-TTS plugins. It handles both valid and invalid plugins, providing diagnostic
-messages for errors.
-
-The loader does NOT:
-- Create Engine instances (that's the plugin's create_engine() responsibility)
-- Manage plugin lifecycle (that's the Plugin Manager's responsibility)
-- Implement any TTS engine functionality
-"""
-
-from __future__ import annotations
-
-import importlib.util
-import re
-import sys
-import types
-from dataclasses import dataclass, field
-from pathlib import Path
-from typing import Any, Callable
-
-from abogen.tts_plugin.manifest import ModelManifest, PluginManifest
-
-
-# Host API version for compatibility checking
-HOST_API_VERSION = "1.0"
-
-
-@dataclass(frozen=True)
-class PluginLoadError:
-    """Diagnostic information for a failed plugin load.
-
-    Attributes:
-        plugin_id: Plugin identifier if available, otherwise directory name.
-        path: Path to the plugin directory.
-        errors: List of error messages describing what went wrong.
-    """
-
-    plugin_id: str
-    path: Path
-    errors: tuple[str, ...] = field(default_factory=tuple)
-
-
-@dataclass(frozen=True)
-class PluginLoadResult:
-    """Result of loading a plugin.
-
-    Attributes:
-        success: Whether the plugin loaded successfully.
-        manifest: The plugin manifest if successful.
-        model_requirements: Model requirements if successful.
-        create_engine: The create_engine function if successful.
-        module: The plugin module if successful.
-        error: Error information if failed.
-    """
-
-    success: bool
-    manifest: PluginManifest | None = None
-    model_requirements: tuple[ModelManifest, ...] | None = None
-    create_engine: Callable[..., Any] | None = None
-    module: types.ModuleType | None = None
-    error: PluginLoadError | None = None
-
-
-def _parse_api_version(version: str) -> tuple[int, int] | None:
-    """Parse an api_version string into (major, minor) tuple.
-
-    Args:
-        version: Version string in format "MAJOR.MINOR".
-
-    Returns:
-        Tuple of (major, minor) or None if invalid format.
-    """
-    match = re.match(r"^(\d+)\.(\d+)$", version)
-    if match:
-        return int(match.group(1)), int(match.group(2))
-    return None
-
-
-def _check_api_version_compatibility(plugin_version: str) -> str | None:
-    """Check if plugin api_version is compatible with host.
-
-    Architecture spec:
-    - Format: semver (MAJOR.MINOR)
-    - Compatibility: Host rejects plugin if major version differs
-    - Minor version: backward compatible, Host accepts higher minor
-
-    Args:
-        plugin_version: Plugin's api_version string.
-
-    Returns:
-        Error message if incompatible, None if compatible.
-    """
-    plugin_ver = _parse_api_version(plugin_version)
-    if plugin_ver is None:
-        return f"Invalid api_version format: '{plugin_version}'. Expected format: MAJOR.MINOR"
-
-    host_ver = _parse_api_version(HOST_API_VERSION)
-    if host_ver is None:
-        return f"Invalid host api_version format: '{HOST_API_VERSION}'"
-
-    if plugin_ver[0] != host_ver[0]:
-        return (
-            f"api_version major mismatch: plugin={plugin_ver[0]}, host={host_ver[0]}. "
-            f"Major version must match for compatibility."
-        )
-
-    return None
-
-
-def _validate_manifest(module: types.ModuleType, plugin_dir: Path) -> list[str]:
-    """Validate that a plugin module has required exports.
-
-    Args:
-        module: The imported plugin module.
-        plugin_dir: Path to the plugin directory.
-
-    Returns:
-        List of error messages (empty if valid).
-    """
-    errors: list[str] = []
-
-    # Check PLUGIN_MANIFEST
-    manifest = getattr(module, "PLUGIN_MANIFEST", None)
-    if manifest is None:
-        errors.append("Missing PLUGIN_MANIFEST export")
-    elif not isinstance(manifest, PluginManifest):
-        errors.append(
-            f"PLUGIN_MANIFEST must be a PluginManifest instance, "
-            f"got {type(manifest).__name__}"
-        )
-
-    # Check MODEL_REQUIREMENTS
-    model_reqs = getattr(module, "MODEL_REQUIREMENTS", None)
-    if model_reqs is None:
-        errors.append("Missing MODEL_REQUIREMENTS export")
-    elif not isinstance(model_reqs, list):
-        errors.append(
-            f"MODEL_REQUIREMENTS must be a list, got {type(model_reqs).__name__}"
-        )
-    else:
-        for i, req in enumerate(model_reqs):
-            if not isinstance(req, ModelManifest):
-                errors.append(
-                    f"MODEL_REQUIREMENTS[{i}] must be a ModelManifest instance, "
-                    f"got {type(req).__name__}"
-                )
-
-    # Check create_engine
-    create_engine = getattr(module, "create_engine", None)
-    if create_engine is None:
-        errors.append("Missing create_engine export")
-    elif not callable(create_engine):
-        errors.append(
-            f"create_engine must be callable, got {type(create_engine).__name__}"
-        )
-
-    return errors
-
-
-def _validate_capabilities(manifest: PluginManifest) -> list[str]:
-    """Validate plugin capabilities.
-
-    Args:
-        manifest: The plugin manifest to validate.
-
-    Returns:
-        List of error messages (empty if valid).
-    """
-    errors: list[str] = []
-
-    # Known capabilities (can be extended)
-    known_capabilities = frozenset({
-        "voice_list",
-        "preview",
-        "voice_clone",
-        "voice_blend",
-        "streaming",
-        "cancel",
-    })
-
-    for cap in manifest.capabilities:
-        if cap not in known_capabilities:
-            errors.append(f"Unknown capability: '{cap}'")
-
-    return errors
-
-
-def _validate_api_version(manifest: PluginManifest) -> list[str]:
-    """Validate api_version compatibility.
-
-    Args:
-        manifest: The plugin manifest to validate.
-
-    Returns:
-        List of error messages (empty if valid).
-    """
-    errors: list[str] = []
-    error = _check_api_version_compatibility(manifest.api_version)
-    if error:
-        errors.append(error)
-    return errors
-
-
-def load_plugin_from_dir(plugin_dir: Path) -> PluginLoadResult:
-    """Load and validate a plugin from a directory.
-
-    The plugin directory must contain an __init__.py that exports:
-    - PLUGIN_MANIFEST: PluginManifest
-    - MODEL_REQUIREMENTS: list[ModelManifest]
-    - create_engine: Callable
-
-    Args:
-        plugin_dir: Path to the plugin directory.
-
-    Returns:
-        PluginLoadResult with success status and either plugin data or error info.
-    """
-    plugin_id = plugin_dir.name
-    errors: list[str] = []
-
-    # Check if directory exists
-    if not plugin_dir.exists():
-        return PluginLoadResult(
-            success=False,
-            error=PluginLoadError(
-                plugin_id=plugin_id,
-                path=plugin_dir,
-                errors=(f"Plugin directory does not exist: {plugin_dir}",),
-            ),
-        )
-
-    # Check for __init__.py
-    init_file = plugin_dir / "__init__.py"
-    if not init_file.exists():
-        return PluginLoadResult(
-            success=False,
-            error=PluginLoadError(
-                plugin_id=plugin_id,
-                path=plugin_dir,
-                errors=("Missing __init__.py in plugin directory",),
-            ),
-        )
-
-    # Import the module
-    module_name = f"abogen.tts_plugin._loaded.{plugin_id}"
-    try:
-        # Remove from cache if already imported (for testing)
-        if module_name in sys.modules:
-            del sys.modules[module_name]
-
-        spec = importlib.util.spec_from_file_location(
-            module_name, init_file, submodule_search_locations=[]
-        )
-        if spec is None or spec.loader is None:
-            return PluginLoadResult(
-                success=False,
-                error=PluginLoadError(
-                    plugin_id=plugin_id,
-                    path=plugin_dir,
-                    errors=(f"Failed to create module spec for {init_file}",),
-                ),
-            )
-
-        module = importlib.util.module_from_spec(spec)
-        sys.modules[module_name] = module
-        spec.loader.exec_module(module)
-    except Exception as e:
-        # Clean up module from sys.modules on import failure
-        if module_name in sys.modules:
-            del sys.modules[module_name]
-        return PluginLoadResult(
-            success=False,
-            error=PluginLoadError(
-                plugin_id=plugin_id,
-                path=plugin_dir,
-                errors=(f"Failed to import plugin module: {e}",),
-            ),
-        )
-
-    # Validate manifest
-    manifest_errors = _validate_manifest(module, plugin_dir)
-    errors.extend(manifest_errors)
-
-    # If manifest is valid, perform additional validation
-    manifest = getattr(module, "PLUGIN_MANIFEST", None)
-    if isinstance(manifest, PluginManifest):
-        # Validate api_version
-        api_errors = _validate_api_version(manifest)
-        errors.extend(api_errors)
-
-        # Validate capabilities
-        cap_errors = _validate_capabilities(manifest)
-        errors.extend(cap_errors)
-
-        # Use manifest id if available
-        plugin_id = manifest.id
-
-    # Check if any errors occurred
-    if errors:
-        # Clean up module from sys.modules
-        if module_name in sys.modules:
-            del sys.modules[module_name]
-
-        return PluginLoadResult(
-            success=False,
-            error=PluginLoadError(
-                plugin_id=plugin_id,
-                path=plugin_dir,
-                errors=tuple(errors),
-            ),
-        )
-
-    # Get MODEL_REQUIREMENTS
-    model_requirements = tuple(getattr(module, "MODEL_REQUIREMENTS", []))
-    create_engine = getattr(module, "create_engine", None)
-
-    return PluginLoadResult(
-        success=True,
-        manifest=manifest,
-        model_requirements=model_requirements,
-        create_engine=create_engine,
-        module=module,
-    )
-
-
-def discover_plugins(plugin_dirs: list[Path]) -> list[PluginLoadResult]:
-    """Discover and load plugins from multiple directories.
-
-    Args:
-        plugin_dirs: List of directories to scan for plugins.
-
-    Returns:
-        List of PluginLoadResult, one per plugin directory found.
-    """
-    results: list[PluginLoadResult] = []
-
-    for plugin_dir in plugin_dirs:
-        if not plugin_dir.exists():
-            continue
-
-        # Scan for subdirectories (each is a potential plugin)
-        for item in sorted(plugin_dir.iterdir()):
-            if item.is_dir() and not item.name.startswith("."):
-                result = load_plugin_from_dir(item)
-                results.append(result)
-
-    return results
-
-
-def load_plugin(
-    plugin_dir: Path,
-) -> PluginLoadResult:
-    """Load a single plugin from a directory.
-
-    This is the main entry point for loading a plugin.
-
-    Args:
-        plugin_dir: Path to the plugin directory.
-
-    Returns:
-        PluginLoadResult with success status and either plugin data or error info.
-    """
-    return load_plugin_from_dir(plugin_dir)

abogen/tts_plugin/manifest.py

@@ -1,189 +0,0 @@
-"""Plugin manifest types for the TTS Plugin Architecture.
-
-This module contains static metadata types that describe plugins.
-These types have no dependencies and are immutable.
-"""
-
-from __future__ import annotations
-
-from dataclasses import dataclass, field
-from typing import Any
-
-
-@dataclass(frozen=True)
-class AudioFormatManifest:
-    """Manifest describing an audio format.
-
-    Attributes:
-        mime: MIME type of the audio.
-        extension: File extension.
-    """
-
-    mime: str
-    extension: str
-
-
-@dataclass(frozen=True)
-class EnumOption:
-    """Manifest describing an enum option for a parameter.
-
-    Attributes:
-        value: The enum value.
-        label: Human-readable label.
-    """
-
-    value: str
-    label: str
-
-
-@dataclass(frozen=True)
-class ParameterManifest:
-    """Manifest describing a synthesis parameter.
-
-    Attributes:
-        id: Parameter identifier.
-        name: Human-readable name.
-        description: Parameter description.
-        type: Parameter type ("float", "int", "string", "boolean", "enum").
-        default: Default value.
-        min: Minimum value (optional, for numeric types).
-        max: Maximum value (optional, for numeric types).
-        step: Step size (optional, for numeric types).
-        options: Available options (optional, for enum type).
-        unit: Unit of measurement (optional).
-        group: Parameter group (optional).
-    """
-
-    id: str
-    name: str
-    description: str
-    type: str
-    default: Any
-    min: float | None = None
-    max: float | None = None
-    step: float | None = None
-    options: tuple[EnumOption, ...] = field(default_factory=tuple)
-    unit: str | None = None
-    group: str | None = None
-
-
-@dataclass(frozen=True)
-class VoiceManifest:
-    """Manifest describing a voice.
-
-    Attributes:
-        id: Voice identifier.
-        name: Human-readable name.
-        tags: Voice tags (e.g., language, style).
-    """
-
-    id: str
-    name: str
-    tags: tuple[str, ...] = field(default_factory=tuple)
-
-
-@dataclass(frozen=True)
-class VoiceSourceManifest:
-    """Manifest describing a voice source.
-
-    Attributes:
-        id: Voice source identifier.
-        name: Human-readable name.
-        type: Source type ("list", "speaker_id", "clone", "blend", "generate", "none").
-        config: Source-specific configuration.
-    """
-
-    id: str
-    name: str
-    type: str
-    config: Any = None
-
-
-@dataclass(frozen=True)
-class EngineManifest:
-    """Manifest describing engine capabilities.
-
-    Attributes:
-        voiceSources: Available voice sources.
-        parameters: Available synthesis parameters.
-        audioFormats: Supported audio formats.
-    """
-
-    voiceSources: tuple[VoiceSourceManifest, ...] = field(default_factory=tuple)
-    parameters: tuple[ParameterManifest, ...] = field(default_factory=tuple)
-    audioFormats: tuple[AudioFormatManifest, ...] = field(default_factory=tuple)
-
-
-@dataclass(frozen=True)
-class GpuRequirement:
-    """Manifest describing GPU requirements.
-
-    Attributes:
-        required: Whether GPU is required.
-        type: GPU type (e.g., "cuda", "rocm").
-        memory: Required GPU memory in GB.
-    """
-
-    required: bool = False
-    type: str | None = None
-    memory: float | None = None
-
-
-@dataclass(frozen=True)
-class RequirementManifest:
-    """Manifest describing plugin requirements.
-
-    Attributes:
-        gpu: GPU requirements (optional).
-        memory: Required RAM in GB (optional).
-        internet: Whether internet is required (optional).
-    """
-
-    gpu: GpuRequirement | None = None
-    memory: float | None = None
-    internet: bool | None = None
-
-
-@dataclass(frozen=True)
-class ModelManifest:
-    """Manifest describing a model requirement.
-
-    Attributes:
-        id: Model identifier.
-        name: Human-readable name.
-        size: Model size as string (e.g., "100MB", "2GB").
-    """
-
-    id: str
-    name: str
-    size: str
-
-
-@dataclass(frozen=True)
-class PluginManifest:
-    """Main manifest for a TTS plugin.
-
-    Attributes:
-        id: Plugin identifier (unique).
-        name: Human-readable name.
-        version: Plugin version.
-        api_version: API version (semver format: MAJOR.MINOR).
-        description: Plugin description.
-        author: Plugin author.
-        capabilities: List of capability identifiers.
-        requires: Plugin requirements.
-        engine: Engine manifest.
-        voices: Optional static voice catalog. None = not declared (use VoiceLister),
-            empty tuple = explicitly no static voices, non-empty = static catalog.
-    """
-
-    id: str
-    name: str
-    version: str
-    api_version: str
-    description: str
-    author: str
-    capabilities: tuple[str, ...] = field(default_factory=tuple)
-    requires: RequirementManifest = field(default_factory=RequirementManifest)
-    engine: EngineManifest = field(default_factory=EngineManifest)
-    voices: tuple[VoiceManifest, ...] | None = None

abogen/tts_plugin/plugin.py

@@ -1,55 +0,0 @@
-"""Plugin contract for the TTS Plugin Architecture.
-
-This module defines the plugin contract that all TTS plugins must implement.
-Each plugin must export:
-- PLUGIN_MANIFEST: PluginManifest instance
-- MODEL_REQUIREMENTS: list of ModelManifest instances
-- create_engine(): Factory function that creates an Engine
-
-The create_engine() function is the entry point for plugin activation.
-It must be atomic: succeed fully or raise and clean up.
-"""
-
-from __future__ import annotations
-
-from pathlib import Path
-from typing import Protocol, runtime_checkable
-
-from abogen.tts_plugin.engine import Engine
-from abogen.tts_plugin.host_context import HostContext
-from abogen.tts_plugin.types import EngineConfig
-
-
-@runtime_checkable
-class Plugin(Protocol):
-    """Protocol defining the plugin contract.
-
-    Every TTS plugin must implement this protocol by exporting:
-    - PLUGIN_MANIFEST: PluginManifest
-    - MODEL_REQUIREMENTS: list[ModelManifest]
-    - create_engine: Callable[[HostContext, Path | None, EngineConfig], Engine]
-    """
-
-    def create_engine(
-        self,
-        context: HostContext,
-        model_path: Path | None,
-        config: EngineConfig,
-    ) -> Engine:
-        """Create an engine instance.
-
-        This is the factory function that creates an Engine from a plugin.
-        It must be atomic: succeed fully or raise EngineError and clean up.
-
-        Args:
-            context: Host services (config dir, logger, http client).
-            model_path: Resolved model path, or None for cloud/no-model engines.
-            config: Engine initialization settings.
-
-        Returns:
-            A fully initialized Engine instance.
-
-        Raises:
-            EngineError: On failure. Cleans up partially created resources.
-        """
-        ...

abogen/tts_plugin/plugin_manager.py

@@ -1,156 +0,0 @@
-"""Plugin Manager
-
-Provides a simple interface for consumers to access TTS engines via the
-new Plugin Architecture. Discovers, loads, and manages plugins from the
-plugins directory.
-
-Usage:
-    from abogen.tts_plugin.plugin_manager import get_plugin_manager
-
-    manager = get_plugin_manager()
-    engine = manager.create_engine("kokoro", lang_code="a", device="cpu")
-    session = engine.create_session()
-    try:
-        result = session.synthesize("Hello world")
-    finally:
-        session.dispose()
-"""
-
-from typing import Any, Dict, List, Optional, Type
-
-from abogen.tts_plugin.engine import Engine, EngineSession
-from abogen.tts_plugin.manifest import PluginManifest
-from abogen.tts_plugin.types import AudioFormat
-
-
-class PluginManager:
-    """Manages TTS plugins and provides a simple interface for consumers."""
-
-    def __init__(self) -> None:
-        self._plugins: Dict[str, dict] = {}
-        self._engines: Dict[str, Engine] = {}
-        self._loaded = False
-
-    def discover(self, plugins_dir: str = "plugins") -> None:
-        """Discover and load all plugins from the given directory."""
-        import os
-        from pathlib import Path
-        from abogen.tts_plugin.loader import load_plugin_from_dir
-
-        self._plugins.clear()
-        self._engines.clear()
-
-        plugins_path = Path(plugins_dir)
-        if not plugins_path.exists():
-            if plugins_dir == "plugins":
-                plugins_path = Path(__file__).resolve().parent.parent.parent / "plugins"
-            if not plugins_path.exists():
-                self._loaded = True
-                return
-
-        for entry in plugins_path.iterdir():
-            if entry.is_dir() and (entry / "__init__.py").exists():
-                try:
-                    result = load_plugin_from_dir(entry)
-                    if result.success and result.manifest is not None:
-                        self._plugins[result.manifest.id] = {
-                            "manifest": result.manifest,
-                            "create_engine": result.create_engine,
-                            "module": result.module,
-                        }
-                except Exception as e:
-                    # Log error but continue with other plugins
-                    print(f"Warning: Failed to load plugin from {entry}: {e}")
-
-        self._loaded = True
-
-    def _ensure_loaded(self) -> None:
-        """Ensure plugins have been discovered."""
-        if not self._loaded:
-            self.discover()
-
-    def list_plugins(self) -> List[PluginManifest]:
-        """Return manifests for all loaded plugins."""
-        self._ensure_loaded()
-        return [info["manifest"] for info in self._plugins.values()]
-
-    def get_plugin(self, plugin_id: str) -> Optional[dict]:
-        """Get plugin info by ID."""
-        self._ensure_loaded()
-        return self._plugins.get(plugin_id)
-
-    def has_plugin(self, plugin_id: str) -> bool:
-        """Check if a plugin is loaded."""
-        self._ensure_loaded()
-        return plugin_id in self._plugins
-
-    def create_engine(self, plugin_id: str, **kwargs: Any) -> Engine:
-        """Create an engine instance for the given plugin.
-
-        Args:
-            plugin_id: The plugin identifier (e.g., "kokoro")
-            **kwargs: Arguments passed to the engine constructor
-
-        Returns:
-            An Engine instance
-
-        Raises:
-            KeyError: If plugin_id is not found
-            Exception: If engine creation fails
-        """
-        self._ensure_loaded()
-
-        if plugin_id not in self._plugins:
-            raise KeyError(f"Plugin not found: {plugin_id}")
-
-        plugin_info = self._plugins[plugin_id]
-        create_engine_func = plugin_info["create_engine"]
-
-        # Create engine using the plugin's factory
-        engine = create_engine_func(**kwargs)
-        return engine
-
-    def get_or_create_engine(self, plugin_id: str, **kwargs: Any) -> Engine:
-        """Get an existing engine or create a new one.
-
-        Engines are cached by plugin_id. If you need multiple instances
-        with different parameters, use create_engine() directly.
-        """
-        self._ensure_loaded()
-
-        cache_key = plugin_id
-        if cache_key in self._engines:
-            return self._engines[cache_key]
-
-        engine = self.create_engine(plugin_id, **kwargs)
-        self._engines[cache_key] = engine
-        return engine
-
-    def dispose_all(self) -> None:
-        """Dispose all cached engines."""
-        for engine in self._engines.values():
-            try:
-                engine.dispose()
-            except Exception:
-                pass  # dispose() should never raise
-        self._engines.clear()
-
-
-# Global singleton
-_manager: Optional[PluginManager] = None
-
-
-def get_plugin_manager() -> PluginManager:
-    """Get the global PluginManager instance."""
-    global _manager
-    if _manager is None:
-        _manager = PluginManager()
-    return _manager
-
-
-def reset_plugin_manager() -> None:
-    """Reset the global PluginManager (for testing)."""
-    global _manager
-    if _manager is not None:
-        _manager.dispose_all()
-    _manager = None

abogen/tts_plugin/types.py

@@ -1,111 +0,0 @@
-"""Core domain types for the TTS Plugin Architecture.
-
-This module contains immutable value objects that form the core domain.
-These types have zero dependencies and are used across the plugin system.
-"""
-
-from __future__ import annotations
-
-from dataclasses import dataclass, field
-from typing import Any, Mapping
-
-
-@dataclass(frozen=True)
-class AudioFormat:
-    """Immutable value object representing an audio format.
-
-    Attributes:
-        mime: MIME type of the audio (e.g., "audio/wav", "audio/mpeg").
-        extension: File extension (e.g., "wav", "mp3").
-    """
-
-    mime: str
-    extension: str
-
-
-@dataclass(frozen=True)
-class Duration:
-    """Immutable value object representing a time duration.
-
-    Attributes:
-        seconds: Duration in seconds.
-    """
-
-    seconds: float
-
-
-@dataclass(frozen=True)
-class VoiceSelection:
-    """Immutable value object for voice selection. Opaque to engine.
-
-    Attributes:
-        source: Voice source identifier (e.g., "builtin", "clone").
-        key: Voice key within the source.
-        payload: Optional payload for clone/blend sources.
-    """
-
-    source: str
-    key: str
-    payload: Any = None
-
-
-@dataclass(frozen=True)
-class ParameterValues:
-    """Immutable value object for synthesis parameters. Behaves like Mapping[str, Any].
-
-    Attributes:
-        values: Mapping of parameter names to their values.
-    """
-
-    values: Mapping[str, Any] = field(default_factory=dict)
-
-
-@dataclass(frozen=True)
-class SynthesisRequest:
-    """Immutable value object for a synthesis request.
-
-    Attributes:
-        text: Text to synthesize.
-        voice: Voice selection.
-        parameters: Synthesis parameters.
-        format: Desired audio output format.
-    """
-
-    text: str
-    voice: VoiceSelection
-    parameters: ParameterValues
-    format: AudioFormat
-
-
-@dataclass(frozen=True)
-class SynthesizedAudio:
-    """Immutable value object for synthesized audio result.
-
-    Attributes:
-        data: Raw audio bytes.
-        format: Audio format of the result.
-        duration: Duration of the audio.
-    """
-
-    data: bytes
-    format: AudioFormat
-    duration: Duration
-
-
-@dataclass(frozen=True)
-class EngineConfig:
-    """Immutable configuration of an Engine instance.
-
-    Contains parameters that define how a particular Engine instance is
-    created and that remain constant throughout the lifetime of that Engine.
-
-    Plugin implementations may ignore fields that are not applicable to them.
-
-    Attributes:
-        device: Device to use (e.g., "cpu", "cuda:0").
-        lang_code: Language code for the engine (e.g., "a" for Kokoro English).
-            Plugins that do not require a language code ignore this field.
-    """
-
-    device: str = "cpu"
-    lang_code: str = "a"

abogen/tts_plugin/utils.py

@@ -1,241 +0,0 @@
-"""TTS Plugin Architecture — direct utility functions.
-
-Provides helpers that replace the former compatibility adapter by
-calling the Plugin Manager directly.
-"""
-
-from __future__ import annotations
-
-from typing import Any, Iterator
-
-import numpy as np
-
-from abogen.tts_plugin.plugin_manager import get_plugin_manager
-
-
-def get_voices(plugin_id: str) -> tuple[str, ...]:
-    """Return the voice-id tuple for *plugin_id*.
-
-    Uses the official Plugin Architecture: PluginManager → Engine → VoiceLister.
-    First checks plugin manifest for static voice catalog.
-    """
-    import logging
-    import tempfile
-    from pathlib import Path
-
-    from abogen.tts_plugin.host_context import HostContext
-    from abogen.tts_plugin.types import EngineConfig
-
-    manager = get_plugin_manager()
-    if not manager.has_plugin(plugin_id):
-        return ()
-
-    # Check manifest for static voice catalog
-    plugin_info = manager.get_plugin(plugin_id)
-    if plugin_info is not None:
-        manifest = plugin_info.get("manifest")
-        if manifest is not None and manifest.voices is not None:
-            return tuple(v.id for v in manifest.voices)
-
-    ctx = HostContext(
-        config_dir=Path(tempfile.gettempdir()),
-        logger=logging.getLogger(f"abogen.utils.{plugin_id}"),
-        http_client=type("_StubHttpClient", (), {
-            "get": staticmethod(lambda url, **kw: None),
-            "post": staticmethod(lambda url, **kw: None),
-        })(),
-    )
-
-    try:
-        engine = manager.create_engine(
-            plugin_id,
-            context=ctx,
-            model_path=None,
-            config=EngineConfig(device="cpu"),
-        )
-    except Exception:
-        return ()
-
-    try:
-        from abogen.tts_plugin.capabilities import VoiceLister
-
-        if isinstance(engine, VoiceLister):
-            manifests = engine.listVoices("builtin")
-            return tuple(v.id for v in manifests)
-        return ()
-    except Exception:
-        return ()
-    finally:
-        engine.dispose()
-
-
-def get_default_voice(plugin_id: str, fallback: str = "") -> str:
-    """Return the first voice of *plugin_id*, or *fallback*."""
-    voices = get_voices(plugin_id)
-    return voices[0] if voices else fallback
-
-
-def is_plugin_registered(plugin_id: str) -> bool:
-    """Check whether *plugin_id* is loaded by the Plugin Manager."""
-    return get_plugin_manager().has_plugin(plugin_id)
-
-
-def resolve_voice_to_plugin(spec: str, fallback: str = "kokoro") -> str:
-    """Determine which plugin owns the given voice specification.
-
-    Resolution rules:
-    1. Empty spec -> fallback
-    2. Kokoro formula (contains '*' or '+') -> "kokoro"
-    3. Exact voice-id match against loaded plugins -> plugin id
-    4. Unknown voice -> fallback
-    """
-    raw = str(spec or "").strip()
-    if not raw:
-        return fallback
-
-    if "*" in raw or "+" in raw:
-        return "kokoro"
-
-    upper = raw.upper()
-    manager = get_plugin_manager()
-
-    for manifest in manager.list_plugins():
-        for voice_source in manifest.engine.voiceSources:
-            if voice_source.type == "list" and isinstance(voice_source.config, dict):
-                try:
-                    engine = manager.create_engine(manifest.id)
-                    try:
-                        if hasattr(engine, "listVoices"):
-                            voice_manifests = engine.listVoices(voice_source.id)
-                            voice_ids = [v.id.upper() for v in voice_manifests]
-                            if upper in voice_ids:
-                                return manifest.id
-                    finally:
-                        engine.dispose()
-                except Exception:
-                    continue
-
-    return fallback
-
-
-class Pipeline:
-    """Callable wrapper around Engine / EngineSession.
-
-    Presents the same interface that old callers expect::
-
-        pipeline = create_pipeline("kokoro", lang_code="a", device="cpu")
-        for segment in pipeline(text, voice="af_nova", speed=1.0):
-            audio = segment.audio
-    """
-
-    def __init__(self, engine: Any, **engine_kwargs: Any) -> None:
-        self._engine = engine
-        self._engine_kwargs = engine_kwargs
-        self._session: Any = None
-
-    def _ensure_session(self) -> Any:
-        if self._session is None:
-            self._session = self._engine.createSession()
-        return self._session
-
-    def __call__(
-        self,
-        text: str,
-        voice: str = "default",
-        speed: float = 1.0,
-        split_pattern: str | None = None,
-        **kwargs: Any,
-    ) -> Iterator[Any]:
-        from abogen.tts_plugin.types import (
-            AudioFormat,
-            ParameterValues,
-            SynthesisRequest,
-            VoiceSelection,
-        )
-
-        session = self._ensure_session()
-
-        params: dict[str, Any] = {"speed": speed}
-        if split_pattern is not None:
-            params["split_pattern"] = split_pattern
-        params.update(kwargs)
-
-        request = SynthesisRequest(
-            text=text,
-            voice=VoiceSelection(source="builtin", key=voice),
-            parameters=ParameterValues(values=params),
-            format=AudioFormat(mime="audio/wav", extension="wav"),
-        )
-
-        result = session.synthesize(request)
-        audio_array = np.frombuffer(result.data, dtype=np.float32)
-
-        from dataclasses import dataclass
-
-        @dataclass
-        class Segment:
-            graphemes: str
-            audio: np.ndarray
-
-        yield Segment(graphemes=text, audio=audio_array)
-
-    def load_single_voice(self, voice_name: str) -> Any:
-        engine_pipeline = getattr(self._engine, '_pipeline', None)
-        if engine_pipeline is not None and hasattr(engine_pipeline, 'load_single_voice'):
-            return engine_pipeline.load_single_voice(voice_name)
-        raise AttributeError(f"load_single_voice not available on {type(self._engine).__name__}")
-
-    def dispose(self) -> None:
-        if self._session is not None:
-            try:
-                self._session.dispose()
-            except Exception:
-                pass
-            self._session = None
-
-    def __del__(self) -> None:
-        self.dispose()
-
-
-def create_pipeline(
-    plugin_id: str,
-    *,
-    lang_code: str = "a",
-    device: str = "cpu",
-) -> Pipeline:
-    """Create a callable TTS pipeline via the Plugin Architecture.
-
-    Builds a proper HostContext and EngineConfig, then delegates to the
-    PluginManager to create the engine. Returns a :class:`Pipeline` whose
-    ``__call__`` interface matches the callable protocol used by consumers.
-
-    Args:
-        plugin_id: Plugin identifier (e.g., "kokoro", "supertonic").
-        lang_code: Language code for the engine.
-        device: Device to use (e.g., "cpu", "cuda:0").
-
-    Returns:
-        A callable Pipeline instance.
-    """
-    import logging
-    import tempfile
-    from pathlib import Path
-
-    from abogen.tts_plugin.host_context import HostContext
-    from abogen.tts_plugin.types import EngineConfig
-
-    manager = get_plugin_manager()
-
-    ctx = HostContext(
-        config_dir=Path(tempfile.gettempdir()),
-        logger=logging.getLogger(f"abogen.pipeline.{plugin_id}"),
-        http_client=type("_StubHttpClient", (), {
-            "get": staticmethod(lambda url, **kw: None),
-            "post": staticmethod(lambda url, **kw: None),
-        })(),
-    )
-
-    config = EngineConfig(device=device, lang_code=lang_code)
-
-    engine = manager.create_engine(plugin_id, context=ctx, model_path=None, config=config)
-    return Pipeline(engine)

abogen/tts_supertonic.py

@@ -1,25 +1,31 @@
-"""SuperTonic Pipeline — self-contained TTS pipeline for the plugin.
-
-This module provides the SuperTonicPipeline class and supporting utilities
-used by the SuperTonic plugin. It is independent of the legacy
-abogen.tts_backends module.
-"""
-
 from __future__ import annotations
 
 import ast
+from dataclasses import dataclass
 import logging
+import math
 import re
 from typing import Any, Iterable, Iterator, Optional
 
 import numpy as np
 
+
 logger = logging.getLogger(__name__)
 
 
+DEFAULT_SUPERTONIC_VOICES = ("M1", "M2", "M3", "M4", "M5", "F1", "F2", "F3", "F4", "F5")
+
+
+@dataclass
+class SupertonicSegment:
+    graphemes: str
+    audio: np.ndarray
+
+
 def _ensure_float32_mono(wav: Any) -> np.ndarray:
     arr = np.asarray(wav, dtype="float32")
     if arr.ndim == 2:
+        # (n, 1) or (1, n) or (n, channels)
         if arr.shape[0] == 1 and arr.shape[1] > 1:
             arr = arr.reshape(-1)
         else:
@@ -56,6 +62,7 @@ def _split_text(
     else:
         parts = [stripped]
 
+    # Enforce max length by hard-splitting long parts.
     result: list[str] = []
     for part in parts:
         if len(part) <= max_chunk_length:
@@ -64,6 +71,7 @@ def _split_text(
         start = 0
         while start < len(part):
             end = min(len(part), start + max_chunk_length)
+            # Try to split at whitespace.
             if end < len(part):
                 ws = part.rfind(" ", start, end)
                 if ws > start + 40:
@@ -82,6 +90,7 @@ _UNSUPPORTED_CHARS_RE = re.compile(
 
 def _parse_unsupported_characters(error: BaseException) -> list[str]:
     """Best-effort extraction of unsupported characters from SuperTonic errors."""
+
     message = " ".join(
         str(part) for part in getattr(error, "args", ()) if part is not None
     ) or str(error)
@@ -127,11 +136,16 @@ def _configure_supertonic_gpu() -> None:
 
         available = ort.get_available_providers()
 
+        # Use CUDA if available, skip TensorRT (requires extra libs not always present)
+        # TensorrtExecutionProvider may be listed as available but fail at runtime
+        # if TensorRT libraries (libnvinfer.so) are not installed
         providers = []
         if "CUDAExecutionProvider" in available:
             providers.append("CUDAExecutionProvider")
         providers.append("CPUExecutionProvider")
 
+        # Patch supertonic's config and loader before TTS import
+        # We must patch both because loader imports the value at module load time
         import supertonic.config as supertonic_config
         import supertonic.loader as supertonic_loader
 
@@ -142,16 +156,6 @@ def _configure_supertonic_gpu() -> None:
         logger.warning("Could not configure supertonic GPU providers: %s", exc)
 
 
-class SupertonicSegment:
-    """A single synthesized audio segment."""
-
-    __slots__ = ("graphemes", "audio")
-
-    def __init__(self, graphemes: str, audio: np.ndarray) -> None:
-        self.graphemes = graphemes
-        self.audio = audio
-
-
 class SupertonicPipeline:
     """Minimal adapter that mimics Kokoro's pipeline iteration interface."""
 
@@ -167,6 +171,7 @@ class SupertonicPipeline:
         self.total_steps = int(total_steps)
         self.max_chunk_length = int(max_chunk_length)
 
+        # Configure GPU providers before importing TTS
         _configure_supertonic_gpu()
 
         try:
@@ -202,6 +207,7 @@ class SupertonicPipeline:
             removed: set[str] = set()
             last_exc: Exception | None = None
 
+            # SuperTonic can raise ValueError for unsupported characters; strip and retry.
             for attempt in range(3):
                 try:
                     wav, duration = self._tts.synthesize(
@@ -225,6 +231,7 @@ class SupertonicPipeline:
                         chunk_to_speak, unsupported
                     ).strip()
 
+                    # If we didn't change anything, don't loop forever.
                     if sanitized == chunk_to_speak.strip():
                         raise
 
@@ -242,6 +249,7 @@ class SupertonicPipeline:
                             sorted(removed),
                         )
             else:
+                # Exhausted retries.
                 assert last_exc is not None
                 raise last_exc
 
@@ -250,6 +258,7 @@ class SupertonicPipeline:
 
             audio = _ensure_float32_mono(wav)
 
+            # If duration is present, infer the source sample rate and resample if needed.
             src_rate = self.sample_rate
             try:
                 dur = float(duration)

abogen/utils.py

@@ -529,20 +529,21 @@ def prevent_sleep_end():
                 _sleep_procs[system] = None
 
 
+def load_numpy_kpipeline():
+    import numpy as np
+    from kokoro import KPipeline  # type: ignore[import-not-found]
+
+    return np, KPipeline
+
+
 class LoadPipelineThread(Thread):
-    def __init__(self, callback, lang_code="a", use_gpu=True):
+    def __init__(self, callback):
         super().__init__()
         self.callback = callback
-        self.lang_code = lang_code
-        self.use_gpu = use_gpu
 
     def run(self):
         try:
-            from abogen.domain.pipeline_factory import create_pipeline_for_job
-
-            backend = create_pipeline_for_job(
-                "kokoro", language=self.lang_code, use_gpu=self.use_gpu
-            )
-            self.callback(backend, None)
+            np_module, kpipeline_class = load_numpy_kpipeline()
+            self.callback(np_module, kpipeline_class, None)
         except Exception as e:
-            self.callback(None, str(e))
+            self.callback(None, None, str(e))

abogen/voice_cache.py

@@ -17,7 +17,7 @@ if LocalEntryNotFoundError is None:  # pragma: no cover - fallback for tests
         pass
 
 
-from abogen.tts_plugin.utils import get_voices
+from abogen.constants import VOICES_INTERNAL
 
 _CACHE_LOCK = threading.Lock()
 _CACHED_VOICES: Set[str] = set()
@@ -26,9 +26,8 @@ _BOOTSTRAPPED = False
 
 
 def _normalize_targets(voices: Optional[Iterable[str]]) -> Set[str]:
-    kokoro_voices = get_voices("kokoro")
     if not voices:
-        return set(kokoro_voices)
+        return set(VOICES_INTERNAL)
     normalized: Set[str] = set()
     for voice in voices:
         if not voice:
@@ -36,7 +35,7 @@ def _normalize_targets(voices: Optional[Iterable[str]]) -> Set[str]:
         voice_id = str(voice).strip()
         if not voice_id:
             continue
-        if voice_id in kokoro_voices:
+        if voice_id in VOICES_INTERNAL:
             normalized.add(voice_id)
     return normalized
 
@@ -144,11 +143,3 @@ def _ensure_single_voice_asset(
 
     hf_hub_download(resume_download=True, **common_kwargs)
     return True
-
-
-def clear_voice_cache() -> None:
-    """Clear the in‑process voice cache (used during shutdown)."""
-    with _CACHE_LOCK:
-        _CACHED_VOICES.clear()
-    global _BOOTSTRAPPED
-    _BOOTSTRAPPED = False

abogen/voice_formulas.py

@@ -1,7 +1,7 @@
 import re
-from typing import Iterable, List, Optional, Tuple
+from typing import List, Tuple
 
-from abogen.tts_plugin.utils import get_voices
+from abogen.constants import VOICES_INTERNAL
 
 
 # Calls parsing and loads the voice to gpu or cpu
@@ -22,7 +22,6 @@ def parse_formula_terms(formula: str) -> List[Tuple[str, float]]:
         raise ValueError("Empty voice formula")
 
     terms: List[Tuple[str, float]] = []
-    kokoro_voices = get_voices("kokoro")
     for segment in formula.split("+"):
         part = segment.strip()
         if not part:
@@ -31,7 +30,7 @@ def parse_formula_terms(formula: str) -> List[Tuple[str, float]]:
             raise ValueError("Each component must be in the form voice*weight")
         voice_name, raw_weight = part.split("*", 1)
         voice_name = voice_name.strip()
-        if voice_name not in kokoro_voices:
+        if voice_name not in VOICES_INTERNAL:
             raise ValueError(f"Unknown voice: {voice_name}")
         try:
             weight = float(raw_weight.strip())
@@ -72,33 +71,6 @@ def parse_voice_formula(pipeline, formula):
     return weighted_sum
 
 
-def pairs_to_formula(pairs: Iterable[Tuple[str, float]]) -> Optional[str]:
-    """Build a voice formula string from (voice_name, weight) pairs.
-
-    Normalizes weights to sum to 1.0 and formats as "voice1*0.5+voice2*0.5".
-
-    Args:
-        pairs: Iterable of (voice_name, weight) tuples. Zero-weight entries
-            are filtered out.
-
-    Returns:
-        Formula string, or None if no valid entries.
-    """
-    voices = [(voice, float(weight)) for voice, weight in pairs if weight is not None and float(weight) > 0]
-    if not voices:
-        return None
-    total = sum(weight for _, weight in voices)
-    if total <= 0:
-        return None
-
-    def _format_value(value: float) -> str:
-        normalized = value / total if total else 0.0
-        return (f"{normalized:.4f}").rstrip("0").rstrip(".") or "0"
-
-    parts = [f"{voice}*{_format_value(weight)}" for voice, weight in voices]
-    return "+".join(parts)
-
-
 def calculate_sum_from_formula(formula):
     weights = re.findall(r"\* *([\d.]+)", formula)
     total_sum = sum(float(weight) for weight in weights)

abogen/voice_metadata.py

@@ -1,33 +0,0 @@
-from dataclasses import dataclass
-
-
-@dataclass(frozen=True)
-class VoiceMetadata:
-    """
-    Immutable metadata describing a voice from a TTS backend.
-
-    This model describes a voice independently of any backend implementation.
-    Backends populate these objects; the application consumes them.
-
-    The ``backend_id`` field is set by the backend itself (via
-    ``self.metadata.id``) — the application never hardcodes it.
-    This ensures renaming a backend does not require touching voice definitions.
-    """
-
-    id: str
-    """Unique voice identifier within the backend (e.g. ``"af_alloy"``, ``"M1"``)."""
-
-    display_name: str
-    """Human-readable display name (e.g. ``"Alloy"``, ``"Male 1"``)."""
-
-    language: str
-    """Language code — backend-specific format is acceptable (e.g. ``"a"``, ``"en"``)."""
-
-    gender: str
-    """Gender category: ``"female"``, ``"male"``, or ``"unknown"``."""
-
-    backend_id: str
-    """Identifier of the backend that owns this voice (e.g. ``"kokoro"``).
-
-    Set automatically by the backend — never hardcoded in voice definitions.
-    """

abogen/voice_profiles.py

@@ -2,7 +2,8 @@ import json
 import os
 from typing import Any, Dict, Iterable, List, Tuple
 
-from abogen.tts_plugin.utils import get_voices, is_plugin_registered
+from abogen.constants import VOICES_INTERNAL
+from abogen.tts_supertonic import DEFAULT_SUPERTONIC_VOICES
 from abogen.utils import get_user_config_path
 
 
@@ -69,8 +70,7 @@ def serialize_profiles() -> Dict[str, Dict[str, Iterable[Tuple[str, float]]]]:
 
 def _normalize_supertonic_voice(value: Any) -> str:
     raw = str(value or "").strip().upper()
-    supertonic_voices = get_voices("supertonic")
-    return raw if raw in supertonic_voices else "M1"
+    return raw if raw in DEFAULT_SUPERTONIC_VOICES else "M1"
 
 
 def _coerce_supertonic_steps(value: Any) -> int:
@@ -101,7 +101,7 @@ def normalize_profile_entry(entry: Any) -> Dict[str, Any]:
         return {}
 
     provider = str(entry.get("provider") or "kokoro").strip().lower()
-    if not is_plugin_registered(provider):
+    if provider not in {"kokoro", "supertonic"}:
         provider = "kokoro"
 
     language = str(entry.get("language") or "a").strip().lower() or "a"
@@ -135,7 +135,6 @@ def normalize_profile_entry(entry: Any) -> Dict[str, Any]:
 
 def _normalize_voice_entries(entries: Iterable) -> List[Tuple[str, float]]:
     normalized: List[Tuple[str, float]] = []
-    kokoro_voices = get_voices("kokoro")
     for item in entries or []:
         if isinstance(item, dict):
             voice = item.get("id") or item.get("voice")
@@ -144,7 +143,7 @@ def _normalize_voice_entries(entries: Iterable) -> List[Tuple[str, float]]:
             voice, weight = item[0], item[1]
         else:
             continue
-        if voice not in kokoro_voices:
+        if voice not in VOICES_INTERNAL:
             continue
         if weight is None:
             continue

abogen/webui/Dockerfile

@@ -2,6 +2,7 @@ FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu22.04
 
 ENV PYTHONDONTWRITEBYTECODE=1 \
   PYTHONUNBUFFERED=1 \
+  PIP_NO_CACHE_DIR=1 \
   VIRTUAL_ENV=/opt/venv \
   PATH=/opt/venv/bin:$PATH
 
@@ -26,22 +27,22 @@ RUN python3 -m venv "$VIRTUAL_ENV"
 WORKDIR /app
 
 COPY pyproject.toml README.md ./
-RUN pip install uv \
-  && if [ -n "$TORCH_VERSION" ]; then \
-       uv pip install --system torch=="$TORCH_VERSION" torchvision=="$TORCH_VERSION" torchaudio=="$TORCH_VERSION" --index-url "$TORCH_INDEX_URL"; \
-     else \
-       uv pip install --system torch torchvision torchaudio --index-url "$TORCH_INDEX_URL"; \
-     fi \
-  && uv pip install --system . \
-    https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl \
-  && uv pip install --system "mutagen>=1.47.0"
-
 COPY abogen ./abogen
 
+RUN pip install --upgrade pip \
+  && if [ -n "$TORCH_VERSION" ]; then \
+       pip install torch=="$TORCH_VERSION" torchvision=="$TORCH_VERSION" torchaudio=="$TORCH_VERSION" --index-url "$TORCH_INDEX_URL"; \
+     else \
+       pip install torch torchvision torchaudio --index-url "$TORCH_INDEX_URL"; \
+     fi \
+  && pip install --no-cache-dir . \
+    https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl \
+  && pip install --no-cache-dir "mutagen>=1.47.0"
+
 # Install onnxruntime-gpu for CUDA acceleration (supertonic uses ONNX Runtime)
 # Set USE_GPU=false to skip this for CPU-only deployments
 RUN if [ "$USE_GPU" = "true" ]; then \
-      uv pip install --system onnxruntime-gpu; \
+      pip install --no-cache-dir onnxruntime-gpu; \
     fi
 
 ENV ABOGEN_HOST=0.0.0.0 \

abogen/webui/app.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import atexit
 import logging
 import os
 from pathlib import Path
@@ -7,8 +8,6 @@ from typing import Any, Optional
 
 from flask import Flask
 
-from abogen import shutdown  # noqa: F401
-shutdown.register_shutdown()
 from abogen.utils import get_user_cache_path, get_user_output_path, get_user_settings_dir
 
 from .conversion_runner import run_conversion_job
@@ -84,12 +83,6 @@ def create_app(config: Optional[dict[str, Any]] = None) -> Flask:
         "UPLOAD_FOLDER": str(uploads_dir),
         "OUTPUT_FOLDER": str(outputs_dir),
         "MAX_CONTENT_LENGTH": 1024 * 1024 * 400,  # 400 MB uploads
-        # Large books can submit four form fields per chapter. Werkzeug's
-        # defaults reject those requests before the wizard route can process
-        # them, even though the encoded payload is much smaller than the upload
-        # limit above.
-        "MAX_FORM_MEMORY_SIZE": 10 * 1024 * 1024,
-        "MAX_FORM_PARTS": 10_000,
     }
     if config:
         base_config.update(config)
@@ -120,6 +113,8 @@ def create_app(config: Optional[dict[str, Any]] = None) -> Flask:
     app.register_blueprint(books_bp, url_prefix="/find-books")
     app.register_blueprint(api_bp, url_prefix="/api")
 
+    atexit.register(service.shutdown)
+
     global _access_log_filter_attached
     if not _access_log_filter_attached:
         logging.getLogger("werkzeug").addFilter(_SuppressSuccessfulAccessFilter())
@@ -137,4 +132,4 @@ def main() -> None:
 
 
 if __name__ == "__main__":  # pragma: no cover
-    main()
+    main()

abogen/webui/conversion_adapter.py

@@ -1,162 +0,0 @@
-"""WebUI adapter: Job -> ConversionRequest.
-
-Converts a WebUI Job into a ConversionRequest that the application layer can process.
-This adapter is the bridge between the WebUI layer and the application/domain layer.
-
-The adapter is responsible for:
-- Mapping Job fields to ConversionRequest fields
-- Handling UI-specific state (logs, progress, cancellation)
-- Providing PipelineProvider and VoiceResolver implementations
-
-All conversions happen through this adapter — the application layer
-never accesses Job directly.
-"""
-
-from __future__ import annotations
-
-from pathlib import Path
-from typing import Any, Callable, Dict, List, Optional
-
-from abogen.application.conversion_request import ConversionRequest
-from abogen.application.conversion_ports import ConversionCancelled, ResolvedVoice
-
-
-def build_conversion_request_from_job(job: Any) -> ConversionRequest:
-    """Convert a WebUI Job into a ConversionRequest.
-
-    This is the primary function that maps Job fields to ConversionRequest.
-    All fields are copied — the request is independent of the Job.
-
-    Args:
-        job: WebUI Job instance
-
-    Returns:
-        ConversionRequest with all Job data mapped
-    """
-    return ConversionRequest(
-        # Source
-        source_path=Path(job.stored_path) if job.stored_path else None,
-        original_filename=job.original_filename,
-        # TTS Settings
-        language=job.language,
-        tts_provider=job.tts_provider,
-        voice=job.voice,
-        voice_profile=job.voice_profile,
-        speed=job.speed,
-        use_gpu=job.use_gpu,
-        supertonic_total_steps=job.supertonic_total_steps,
-        # Output Format
-        output_format=job.output_format,
-        subtitle_mode=job.subtitle_mode,
-        subtitle_format=job.subtitle_format,
-        max_subtitle_words=job.max_subtitle_words,
-        # Save Options
-        save_mode=job.save_mode,
-        output_folder=Path(job.output_folder) if job.output_folder else None,
-        save_chapters_separately=job.save_chapters_separately,
-        merge_chapters_at_end=job.merge_chapters_at_end,
-        separate_chapters_format=job.separate_chapters_format,
-        save_as_project=job.save_as_project,
-        # Timing
-        silence_between_chapters=job.silence_between_chapters,
-        chapter_intro_delay=job.chapter_intro_delay,
-        # Content Processing
-        replace_single_newlines=job.replace_single_newlines,
-        read_title_intro=job.read_title_intro,
-        read_closing_outro=job.read_closing_outro,
-        auto_prefix_chapter_titles=job.auto_prefix_chapter_titles,
-        normalize_chapter_opening_caps=job.normalize_chapter_opening_caps,
-        # Pronunciation / Normalization
-        pronunciation_overrides=job.pronunciation_overrides or [],
-        manual_overrides=job.manual_overrides or [],
-        heteronym_overrides=job.heteronym_overrides or [],
-        normalization_overrides=job.normalization_overrides or {},
-        # Chapter/Chunk Configuration
-        chapter_overrides=job.chapters or [],
-        chunks=job.chunks or [],
-        chunk_level=job.chunk_level,
-        speaker_mode=job.speaker_mode,
-        speakers=job.speakers or {},
-        # Metadata
-        metadata_tags=job.metadata_tags or {},
-        # Artifacts
-        cover_image_path=Path(job.cover_image_path) if job.cover_image_path else None,
-        cover_image_mime=job.cover_image_mime,
-        generate_epub3=job.generate_epub3,
-    )
-
-
-class WebJobEvents:
-    """WebUI implementation of ConversionEvents protocol.
-
-    Wraps a Job to provide logging, progress, and cancellation.
-    """
-
-    def __init__(self, job: Any):
-        self._job = job
-
-    def log(self, message: str, level: str = "info") -> None:
-        """Log a message to the Job."""
-        self._job.add_log(message, level=level)
-
-    def progress(self, pct: int, etr: str) -> None:
-        """Update progress on the Job."""
-        self._job.progress = pct / 100.0
-        self._job.etr_str = etr
-
-    def check_cancelled(self) -> None:
-        """Check if the Job was cancelled.
-
-        Raises:
-            ConversionCancelled: If cancellation was requested
-        """
-        if self._job.cancel_requested:
-            raise ConversionCancelled("Job cancelled by user")
-
-
-class WebPipelineProvider:
-    """WebUI implementation of PipelineProvider protocol.
-
-    Wraps PipelinePool to provide TTS backends.
-    """
-
-    def __init__(self, pipeline_pool: Any):
-        self._pool = pipeline_pool
-
-    def get(self, provider: str, language: str, use_gpu: bool) -> Any:
-        """Get a TTS backend instance."""
-        return self._pool.get(provider, language, use_gpu)
-
-    def dispose_all(self) -> None:
-        """Dispose all backend resources."""
-        self._pool.dispose_all()
-
-
-class WebVoiceResolver:
-    """WebUI implementation of VoiceResolver protocol.
-
-    Wraps the voice resolution logic from conversion_runner.py.
-    """
-
-    def __init__(
-        self,
-        resolve_fn: Callable[[str], tuple[str, str, Any, Optional[float], Optional[int]]],
-    ):
-        """Initialize with a voice resolution function.
-
-        Args:
-            resolve_fn: Function that takes a voice_spec and returns
-                (provider, resolved_spec, voice_choice, speed, steps)
-        """
-        self._resolve_fn = resolve_fn
-
-    def resolve(self, voice_spec: str) -> ResolvedVoice:
-        """Resolve a voice spec into a loaded voice."""
-        provider, resolved_spec, voice, speed, steps = self._resolve_fn(voice_spec)
-        return ResolvedVoice(
-            provider=provider,
-            resolved_spec=resolved_spec,
-            voice=voice,
-            speed=speed or 1.0,
-            supertonic_steps=steps or 5,
-        )