extract normalize_text_for_pipeline to domain/normalization.py

fix(webui): allow large chapter forms

abogen/domain/audio_helpers.py

@@ -0,0 +1,118 @@
+"""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/chapter_overrides.py

@@ -0,0 +1,92 @@
+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

@@ -0,0 +1,204 @@
+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

@@ -0,0 +1,75 @@
+"""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/device.py

@@ -0,0 +1,31 @@
+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/file_type.py

@@ -0,0 +1,136 @@
+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/metadata_helpers.py

@@ -0,0 +1,138 @@
+from __future__ import annotations
+
+import re
+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()

abogen/domain/metadata_merge.py

@@ -0,0 +1,23 @@
+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/normalization.py

@@ -0,0 +1,30 @@
+"""Text normalization convenience helpers."""
+
+from __future__ import annotations
+
+from typing import Any, 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()
+
+
+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)

abogen/domain/output_paths.py

@@ -0,0 +1,91 @@
+"""Output path resolution utilities.
+
+Pure functions for resolving output directories, building file paths,
+and computing project folder layouts.
+"""
+
+from __future__ import annotations
+
+import re
+from datetime import datetime
+from pathlib import Path
+from typing import Any, Callable, List, Optional, Tuple
+
+from abogen.text_extractor import ExtractedChapter
+
+
+_OUTPUT_SANITIZE_RE = re.compile(r"[^\w\-_.]+")
+
+
+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_output_stem(name: str) -> 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)
+
+
+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 == "Save to Desktop" and desktop_dir:
+        return desktop_dir
+    if save_mode == "Save next to input file":
+        return stored_path.parent
+    if save_mode == "Choose output folder" and output_folder:
+        return Path(output_folder)
+    if save_mode == "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

abogen/domain/pronunciation.py

@@ -0,0 +1,261 @@
+"""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/split_pattern.py

@@ -0,0 +1,40 @@
+from __future__ import annotations
+
+"""Unified split pattern logic extracted from 3 copies."""
+import re
+
+
+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
+    """
+    # For English, always use newline splitting only
+    if language in ("a", "b"):
+        return "\n"
+
+    # Determine spacing pattern based on language
+    spacing = r"\s*" if language in ("z", "j") else r"\s+"
+
+    # For CJK languages, when subtitle mode is Disabled or Line, prefer
+    # punctuation-based splitting instead of plain newline splitting.
+    if subtitle_mode in ("Disabled", "Line") and language in ("z", "j"):
+        return rf"(?<=[{PUNCTUATION_SENTENCE}]){spacing}|\n+"
+
+    if subtitle_mode == "Line":
+        return "\n"
+    elif subtitle_mode == "Sentence":
+        return rf"(?<=[{PUNCTUATION_SENTENCE}]){spacing}|\n+"
+    elif subtitle_mode == "Sentence + Comma":
+        return rf"(?<=[{PUNCTUATION_SENTENCE_COMMA}]){spacing}|\n+"
+    else:
+        return r"\n+"

abogen/domain/title_builder.py

@@ -0,0 +1,97 @@
+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/voice_resolution.py

@@ -0,0 +1,190 @@
+"""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

@@ -0,0 +1,97 @@
+from __future__ import annotations
+
+from typing import Any, 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)

abogen/infrastructure/exporters.py

@@ -0,0 +1,673 @@
+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.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."""
+        tags = self._normalize_metadata_casefold(getattr(job, "metadata_tags", {}))
+        filename = Path(getattr(job, "original_filename", "") or "").stem or "Audiobook"
+        
+        title = self._first_nonempty(
+            tags.get("title"),
+            tags.get("book_title"),
+            tags.get("name"),
+            tags.get("album"),
+            filename,
+        )
+        authors = self._split_people_field(
+            tags.get("authors")
+            or tags.get("author")
+            or tags.get("album_artist")
+            or tags.get("artist")
+        )
+        narrators = self._split_people_field(tags.get("narrators") or tags.get("narrator"))
+        description = self._first_nonempty(
+            tags.get("description"), tags.get("summary"), tags.get("comment")
+        )
+        genres = self._split_simple_list(tags.get("genre"))
+        keywords = self._split_simple_list(tags.get("tags") or tags.get("keywords"))
+        language = self._first_nonempty(tags.get("language"), tags.get("lang")) or getattr(job, "language", "") or ""
+        series_name = self._first_nonempty(
+            tags.get("series"),
+            tags.get("series_name"),
+            tags.get("seriesname"),
+            tags.get("series_title"),
+            tags.get("seriestitle"),
+        )
+        
+        series_sequence = None
+        for key in ("series_index", "series_position", "series_sequence", "series_number", "seriesnumber", "book_number", "booknumber"):
+            raw = tags.get(key)
+            normalized = self._normalize_series_sequence(raw)
+            if normalized:
+                series_sequence = normalized
+                break
+        if not series_name:
+            series_sequence = None
+        
+        data = {
+            "title": title,
+            "subtitle": tags.get("subtitle"),
+            "authors": authors,
+            "narrators": narrators,
+            "description": description,
+            "publisher": tags.get("publisher"),
+            "genres": genres,
+            "tags": keywords,
+            "language": language,
+            "publishedYear": self._extract_year(
+                tags.get("published") or tags.get("publication_year") or tags.get("date") or tags.get("year")
+            ),
+            "seriesName": series_name,
+            "seriesSequence": series_sequence,
+            "isbn": self._first_nonempty(tags.get("isbn"), tags.get("asin")),
+        }
+        
+        published_date = self._first_nonempty(
+            tags.get("published"), tags.get("publication_date"), tags.get("date")
+        )
+        if published_date:
+            data["publishedDate"] = published_date
+        
+        rating_text = self._first_nonempty(tags.get("rating"), tags.get("my_rating"))
+        if rating_text:
+            try:
+                data["rating"] = float(str(rating_text).strip())
+            except ValueError:
+                pass
+            rating_max_text = self._first_nonempty(tags.get("rating_max"), tags.get("rating_scale"))
+            if rating_max_text:
+                try:
+                    data["ratingMax"] = float(str(rating_max_text).strip())
+                except ValueError:
+                    pass
+        
+        # Remove empty values
+        cleaned = {}
+        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(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))
+        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 = []
+        for entry in chapters:
+            if not isinstance(entry, Mapping):
+                continue
+            title = self._first_nonempty(entry.get("title"), entry.get("original_title"))
+            start = entry.get("start")
+            end = entry.get("end")
+            if title is None or not isinstance(start, (int, float)):
+                continue
+            chapter_payload = {"title": title, "start": float(start)}
+            if isinstance(end, (int, float)):
+                chapter_payload["end"] = float(end)
+            cleaned.append(chapter_payload)
+        return cleaned or None
+    
+    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:
+            # Load from job or global config
+            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 _normalize_metadata_casefold(values: Optional[Mapping[str, Any]]) -> Dict[str, Any]:
+        normalized = {}
+        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
+    
+    @staticmethod
+    def _split_people_field(raw: Any) -> List[str]:
+        if raw is None:
+            return []
+        if isinstance(raw, (list, tuple, set)):
+            results = []
+            for item in raw:
+                results.extend(ExportService._split_people_field(item))
+            return results
+        text = str(raw or "").strip()
+        if not text:
+            return []
+        import re
+        tokens = [token.strip() for token in re.split(r"[;,/&]|\band\b", text, flags=re.IGNORECASE) if token.strip()]
+        seen = set()
+        ordered = []
+        for token in tokens:
+            key = token.casefold()
+            if key in seen:
+                continue
+            seen.add(key)
+            ordered.append(token)
+        return ordered
+    
+    @staticmethod
+    def _split_simple_list(raw: Any) -> List[str]:
+        if raw is None:
+            return []
+        if isinstance(raw, (list, tuple, set)):
+            results = []
+            for item in raw:
+                results.extend(ExportService._split_simple_list(item))
+            return results
+        text = str(raw or "").strip()
+        if not text:
+            return []
+        import re
+        tokens = [token.strip() for token in re.split(r"[;,\n]", text) if token.strip()]
+        seen = set()
+        ordered = []
+        for token in tokens:
+            key = token.casefold()
+            if key in seen:
+                continue
+            seen.add(key)
+            ordered.append(token)
+        return ordered
+    
+    @staticmethod
+    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
+    
+    @staticmethod
+    def _extract_year(raw: Optional[str]) -> Optional[int]:
+        if not raw:
+            return None
+        text = str(raw).strip()
+        if not text:
+            return None
+        import re
+        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
+    
+    @staticmethod
+    def _normalize_series_sequence(raw: Any) -> Optional[str]:
+        if raw is None:
+            return None
+        if isinstance(raw, (int, float)):
+            if isinstance(raw, float) and (raw != raw or raw == float("inf") or raw == float("-inf")):
+                return None
+            text = str(raw)
+        else:
+            text = str(raw).strip()
+        if not text:
+            return None
+        candidate = text.replace(",", ".")
+        import re
+        match = re.search(r"\d+(?:\.\d+)?", 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:
+            cleaned = normalized.lstrip("0")
+            return cleaned or "0"
+    
+    @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

@@ -0,0 +1,303 @@
+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.subtitle_utils import clean_subtitle_text
+
+
+class SubtitleFormat(Enum):
+    SRT = "srt"
+    ASS = "ass"
+    VTT = "vtt"
+
+
+class SubtitleMode(Enum):
+    DISABLED = "Disabled"
+    LINE = "Line"
+    SENTENCE = "Sentence"
+    SENTENCE_COMMA = "Sentence + Comma"
+    SENTENCE_HIGHLIGHT = "Sentence + Highlighting"
+
+
+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}")
+
+
+__all__ = [
+    "SubtitleFormat",
+    "SubtitleMode",
+    "SubtitleAlignment",
+    "SubtitleConfig",
+    "SubtitleWriter",
+    "SrtWriter",
+    "VttWriter",
+    "AssWriter",
+    "create_subtitle_writer",
+]

abogen/pyqt/conversion.py

@@ -14,7 +14,6 @@ from abogen.utils import (
 )
 from abogen.constants import (
     LANGUAGE_DESCRIPTIONS,
-    SAMPLE_VOICE_TEXTS,
     COLORS,
     CHAPTER_OPTIONS_COUNTDOWN,
     SUBTITLE_FORMATS,
@@ -22,11 +21,18 @@ from abogen.constants import (
     SUPPORTED_SUBTITLE_FORMATS,
 )
 from abogen.voice_formulas import get_new_voice
+from abogen.infrastructure.subtitle_writer import _format_timestamp
+from abogen.domain.split_pattern import get_split_pattern
+from abogen.domain.output_paths import (
+    resolve_output_directory,
+    build_output_path,
+    sanitize_output_stem,
+)
+from abogen.domain.audio_helpers import build_ffmpeg_command, to_float32
 import abogen.hf_tracker as hf_tracker
 import static_ffmpeg
 import threading  # for efficient waiting
 import subprocess
-import platform
 
 # Configuration constants
 _USER_RESPONSE_TIMEOUT = (
@@ -43,10 +49,7 @@ from abogen.subtitle_utils import (
     get_sample_voice_text,
     sanitize_name_for_os,
     _CHAPTER_MARKER_SEARCH_PATTERN,
-    _VOICE_MARKER_PATTERN,
+    split_text_by_voice_markers
-    _VOICE_MARKER_SEARCH_PATTERN,
-    split_text_by_voice_markers,
-    validate_voice_name,
 )
 
 class CountdownDialog(QDialog):
@@ -216,40 +219,6 @@ class ConversionThread(QThread):
     PUNCTUATION_SENTENCE_COMMA = ".!?,।。！？、，"
     PUNCTUATION_COMMAS = ",，、"
 
-    def _get_split_pattern(self, lang_code, subtitle_mode):
-        """
-        Get the appropriate split pattern based on language and subtitle mode.
-
-        Args:
-            lang_code: Language code (a, b, e, f, etc.)
-            subtitle_mode: Subtitle mode ("Sentence", "Sentence + Comma", "Line", etc.)
-
-        Returns:
-            Split pattern string
-        """
-        # For English, always use newline splitting only
-        if lang_code in ["a", "b"]:
-            return "\n"
-
-        # Determine spacing pattern based on language
-        spacing_pattern = r"\s*" if lang_code in ["z", "j"] else r"\s+"
-
-        # For Chinese/Japanese, when subtitle mode is Disabled or Line, prefer
-        # punctuation-based splitting instead of plain newline splitting.
-        if subtitle_mode in ("Disabled", "Line") and lang_code in ["z", "j"]:
-            return r"(?<=[{}]){}|\n+".format(self.PUNCTUATION_SENTENCE, spacing_pattern)
-
-        if subtitle_mode == "Line":
-            return "\n"
-        elif subtitle_mode == "Sentence":
-            return r"(?<=[{}]){}|\n+".format(self.PUNCTUATION_SENTENCE, spacing_pattern)
-        elif subtitle_mode == "Sentence + Comma":
-            return r"(?<=[{}]){}|\n+".format(
-                self.PUNCTUATION_SENTENCE_COMMA, spacing_pattern
-            )
-        else:
-            return r"\n+"  # Default to line breaks
-
     def __init__(
         self,
         file_name,
@@ -298,7 +267,7 @@ class ConversionThread(QThread):
         self.silence_duration = 2.0  # Default value, will be overridden from GUI
         self.use_spacy_segmentation = True  # Default, will be overridden from GUI
         # Set split pattern based on language and subtitle mode
-        self.split_pattern = self._get_split_pattern(lang_code, subtitle_mode)
+        self.split_pattern = get_split_pattern(lang_code, subtitle_mode)
         self.voice_cache = {}  # Cache for loaded voices
 
     def load_voice_cached(self, voice_name, tts):
@@ -676,15 +645,17 @@ class ConversionThread(QThread):
                 base_path = self.display_path if self.display_path else self.file_name
 
             base_name = os.path.splitext(os.path.basename(base_path))[0]
-            # Sanitize base_name for folder/file creation based on OS
             sanitized_base_name = sanitize_name_for_os(base_name, is_folder=True)
 
-            if self.save_option == "Save to Desktop":
+            parent_dir = resolve_output_directory(
-                parent_dir = user_desktop_dir()
+                save_mode=self.save_option,
-            elif self.save_option == "Save next to input file":
+                stored_path=Path(base_path),
-                parent_dir = os.path.dirname(base_path)
+                output_folder=getattr(self, "output_folder", None),
-            else:
+                desktop_dir=Path(user_desktop_dir()),
-                parent_dir = self.output_folder or os.getcwd()
+                user_output_path=None,
+                user_cache_outputs=Path(os.getcwd()),
+            )
+            parent_dir = str(parent_dir)
             # Ensure the output folder exists, error if it doesn't
             if not os.path.exists(parent_dir):
                 self.log_updated.emit(
@@ -754,77 +725,40 @@ class ConversionThread(QThread):
                         format=self.output_format,
                     )
                     ffmpeg_proc = None
-                elif self.output_format == "m4b":
+                elif self.output_format in ("m4b", "opus"):
-                    # Real-time M4B generation using FFmpeg pipe
+                    # Real-time generation using FFmpeg pipe
                     static_ffmpeg.add_paths()
                     merged_out_file = None
                     ffmpeg_proc = None
                     metadata_options, cover_path = (
                         self._extract_and_add_metadata_tags_to_ffmpeg_cmd()
+                        if self.output_format == "m4b"
+                        else ([], None)
                     )
-                    # Prepare ffmpeg command for m4b output
+                    cmd = build_ffmpeg_command(
-                    cmd = [
+                        Path(merged_out_path),
-                        "ffmpeg",
+                        self.output_format,
-                        "-y",
-                        "-thread_queue_size",
-                        "32768",
-                        "-f",
-                        "f32le",
-                        "-ar",
-                        "24000",
-                        "-ac",
-                        "1",
-                        "-i",
-                        "pipe:0",
-                    ]
-                    if cover_path and os.path.exists(cover_path):
-                        cmd.extend(
-                            [
-                                "-i",
-                                cover_path,
-                                "-map",
-                                "0:a",
-                                "-map",
-                                "1",
-                                "-c:v",
-                                "copy",
-                                "-disposition:v",
-                                "attached_pic",
-                            ]
-                        )
-                    cmd.extend(
-                        [
-                            "-c:a",
-                            "aac",
-                            "-q:a",
-                            "2",
-                            "-movflags",
-                            "+faststart+use_metadata_tags",
-                        ]
                     )
-                    cmd += metadata_options
+                    # Insert thread queue size after ffmpeg header
-                    cmd.append(merged_out_path)
+                    cmd.insert(2, "-thread_queue_size")
+                    cmd.insert(3, "32768")
+                    if self.output_format == "m4b" and cover_path and os.path.exists(cover_path):
+                        # Insert cover image input before the output path
+                        output_path = cmd.pop()
+                        cmd.extend([
+                            "-i", cover_path,
+                            "-map", "0:a",
+                            "-map", "1",
+                            "-c:v", "copy",
+                            "-disposition:v", "attached_pic",
+                        ])
+                        cmd.extend(metadata_options)
+                        cmd.append(output_path)
+                    elif self.output_format == "m4b":
+                        output_path = cmd.pop()
+                        cmd.extend(metadata_options)
+                        cmd.append(output_path)
                     ffmpeg_proc = create_process(cmd, stdin=subprocess.PIPE, text=False)
-                elif self.output_format == "opus":
-                    static_ffmpeg.add_paths()
-                    cmd = [
-                        "ffmpeg",
-                        "-y",
-                        "-thread_queue_size",
-                        "32768",
-                        "-f",
-                        "f32le",
-                        "-ar",
-                        "24000",
-                        "-ac",
-                        "1",
-                        "-i",
-                        "pipe:0",
-                    ]
-                    cmd.extend(["-c:a", "libopus", "-b:a", "24000"])
-                    cmd.append(merged_out_path)
-                    ffmpeg_proc = create_process(cmd, stdin=subprocess.PIPE, text=False)
-                    merged_out_file = None
                 else:
                     self.log_updated.emit(
                         (f"Unsupported output format: {self.output_format}", "red")
@@ -1258,8 +1192,8 @@ class ConversionThread(QThread):
                                         )
                                         if "ass" in subtitle_format:
                                             for start, end, text in new_entries:
-                                                start_time = self._ass_time(start)
+                                                start_time = _format_timestamp(start, ass=True)
-                                                end_time = self._ass_time(end)
+                                                end_time = _format_timestamp(end, ass=True)
                                                 # Use karaoke effect for highlighting mode
                                                 effect = (
                                                     "karaoke"
@@ -1274,7 +1208,7 @@ class ConversionThread(QThread):
                                             for entry in new_entries:
                                                 start, end, text = entry
                                                 merged_subtitle_file.write(
-                                                    f"{merged_srt_index}\n{self._srt_time(start)} --> {self._srt_time(end)}\n{text}\n\n"
+                                                    f"{merged_srt_index}\n{_format_timestamp(start)} --> {_format_timestamp(end)}\n{text}\n\n"
                                                 )
                                                 merged_srt_index += 1
                                 # Per-chapter subtitle processing for both file and ffmpeg_proc
@@ -1292,8 +1226,8 @@ class ConversionThread(QThread):
                                         )
                                         if "ass" in subtitle_format:
                                             for start, end, text in new_chapter_entries:
-                                                start_time = self._ass_time(start)
+                                                start_time = _format_timestamp(start, ass=True)
-                                                end_time = self._ass_time(end)
+                                                end_time = _format_timestamp(end, ass=True)
                                                 # Use karaoke effect for highlighting mode
                                                 effect = (
                                                     "karaoke"
@@ -1308,7 +1242,7 @@ class ConversionThread(QThread):
                                             for entry in new_chapter_entries:
                                                 start, end, text = entry
                                                 chapter_subtitle_file.write(
-                                                    f"{chapter_srt_index}\n{self._srt_time(start)} --> {self._srt_time(end)}\n{text}\n\n"
+                                                    f"{chapter_srt_index}\n{_format_timestamp(start)} --> {_format_timestamp(end)}\n{text}\n\n"
                                                 )
                                                 chapter_srt_index += 1
                             if merge_chapters_at_end:
@@ -1597,58 +1531,27 @@ class ConversionThread(QThread):
                 )
             else:
                 static_ffmpeg.add_paths()
-                cmd = [
+                cmd = build_ffmpeg_command(
-                    "ffmpeg",
+                    Path(merged_out_path),
-                    "-y",
+                    self.output_format,
-                    "-thread_queue_size",
+                )
-                    "32768",
+                cmd.insert(2, "-thread_queue_size")
-                    "-f",
+                cmd.insert(3, "32768")
-                    "f32le",
-                    "-ar",
-                    str(rate),
-                    "-ac",
-                    "1",
-                    "-i",
-                    "pipe:0",
-                ]
                 if self.output_format == "m4b":
                     metadata_options, cover_path = (
                         self._extract_and_add_metadata_tags_to_ffmpeg_cmd()
                     )
                     if cover_path and os.path.exists(cover_path):
-                        cmd.extend(
+                        output_path = cmd.pop()
-                            [
+                        cmd.extend([
-                                "-i",
+                            "-i", cover_path,
-                                cover_path,
+                            "-map", "0:a",
-                                "-map",
+                            "-map", "1",
-                                "0:a",
+                            "-c:v", "copy",
-                                "-map",
+                            "-disposition:v", "attached_pic",
-                                "1",
+                        ])
-                                "-c:v",
+                        cmd.append(output_path)
-                                "copy",
-                                "-disposition:v",
-                                "attached_pic",
-                            ]
-                        )
-                    cmd.extend(
-                        [
-                            "-c:a",
-                            "aac",
-                            "-q:a",
-                            "2",
-                            "-movflags",
-                            "+faststart+use_metadata_tags",
-                        ]
-                    )
                     cmd.extend(metadata_options)
-                elif self.output_format == "opus":
-                    cmd.extend(["-c:a", "libopus", "-b:a", "24000"])
-                else:
-                    self.log_updated.emit(
-                        (f"Unsupported output format: {self.output_format}", "red")
-                    )
-                    return
-                cmd.append(merged_out_path)
                 ffmpeg_proc = create_process(cmd, stdin=subprocess.PIPE, text=False)
 
             # Always generate subtitles for subtitle input files
@@ -1938,11 +1841,11 @@ class ConversionThread(QThread):
                             else processed_text.replace("\n", "\\N")
                         )
                         subtitle_file.write(
-                            f"Dialogue: 0,{self._ass_time(start_time)},{self._ass_time(end_time)},Default,,{margin},{margin},0,{effect},{alignment}{ass_text}\n"
+                            f"Dialogue: 0,{_format_timestamp(start_time, ass=True)},{_format_timestamp(end_time, ass=True)},Default,,{margin},{margin},0,{effect},{alignment}{ass_text}\n"
                         )
                     else:
                         subtitle_file.write(
-                            f"{srt_index}\n{self._srt_time(start_time)} --> {self._srt_time(end_time)}\n{processed_text}\n\n"
+                            f"{srt_index}\n{_format_timestamp(start_time)} --> {_format_timestamp(end_time)}\n{processed_text}\n\n"
                         )
                         srt_index += 1
 
@@ -2104,22 +2007,6 @@ class ConversionThread(QThread):
         # Add these to ffmpeg command
         return metadata_options, cover_path
 
-    def _srt_time(self, t):
-        """Helper function to format time for SRT files"""
-        h = int(t // 3600)
-        m = int((t % 3600) // 60)
-        s = int(t % 60)
-        ms = int((t - int(t)) * 1000)
-        return f"{h:02d}:{m:02d}:{s:02d},{ms:03d}"
-
-    def _ass_time(self, t):
-        """Helper function to format time for ASS files"""
-        h = int(t // 3600)
-        m = int((t % 3600) // 60)
-        s = int(t % 60)
-        cs = int((t - int(t)) * 100)  # Centiseconds for ASS format
-        return f"{h:01d}:{m:02d}:{s:02d}.{cs:02d}"
-
     def _process_subtitle_tokens(
         self,
         tokens_with_timestamps,

abogen/pyqt/gui.py

@@ -7,6 +7,7 @@ import base64
 import re
 from abogen.pyqt.queue_manager_gui import QueueManager
 from abogen.pyqt.queued_item import QueuedItem
+from abogen.domain.device import select_device as _select_device
 import abogen.hf_tracker as hf_tracker
 import hashlib  # Added for cache path generation
 from PyQt6.QtWidgets import (
@@ -2428,10 +2429,7 @@ class abogen(QWidget):
 
             # Determine device based on GPU availability
             if gpu_ok:
-                if platform.system() == "Darwin" and platform.processor() == "arm":
+                device = _select_device()
-                    device = "mps"
-                else:
-                    device = "cuda"
             else:
                 device = "cpu"
 
@@ -2877,10 +2875,7 @@ class abogen(QWidget):
 
         # Determine device based on GPU availability
         if self.gpu_ok:
-            if platform.system() == "Darwin" and platform.processor() == "arm":
+            device = _select_device()
-                device = "mps"
-            else:
-                device = "cuda"
         else:
             device = "cpu"
 

abogen/webui/app.py

@@ -84,6 +84,12 @@ 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)

abogen/webui/routes/utils/preview.py

@@ -6,6 +6,8 @@ import soundfile as sf
 from flask import current_app, send_file
 from flask.typing import ResponseReturnValue
 
+from abogen.domain.device import select_device as _select_device
+
 
 SPLIT_PATTERN = r"\n+"
 SAMPLE_RATE = 24000
@@ -25,31 +27,6 @@ def clear_preview_pipelines() -> None:
         _preview_pipelines.clear()
 
 
-def _select_device() -> str:
-    import platform
-
-    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():
-                return "mps"
-        except Exception:
-            pass
-        return "cpu"
-
-    try:
-        if torch.cuda.is_available():
-            return "cuda"
-    except Exception:
-        pass
-    return "cpu"
-
-
 def _resolve_pipeline(language: str, use_gpu: bool) -> Tuple[Any, bool]:
     devices: List[str] = ["cpu"]
     if use_gpu:

pyproject.toml

@@ -44,7 +44,7 @@ dependencies = [
   "python-dotenv>=1.0.1",
   "static_ffmpeg>=2.13",
   "Markdown>=3.9",
-  "Flask>=3.0.3",
+  "Flask>=3.1.0",
   "numpy>=1.24.0",
   "gpustat>=1.1.1",
   "num2words>=0.5.13",

tests/test_audio_helpers.py

@@ -0,0 +1,128 @@
+"""Tests for audio helper utilities.
+
+Tests import from domain/audio_helpers.py (new module).
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+import numpy as np
+import pytest
+
+
+# ---------------------------------------------------------------------------
+# build_ffmpeg_command
+# ---------------------------------------------------------------------------
+
+
+class TestBuildFfmpegCommand:
+    """build_ffmpeg_command builds ffmpeg argument list."""
+
+    def test_base_structure(self):
+        from abogen.domain.audio_helpers import build_ffmpeg_command
+
+        cmd = build_ffmpeg_command(Path("/out/audio.wav"), "wav")
+        assert cmd[0] == "ffmpeg"
+        assert "-y" in cmd
+        assert "pipe:0" in cmd
+        assert str(Path("/out/audio.wav")) in cmd
+
+    def test_mp3_codec(self):
+        from abogen.domain.audio_helpers import build_ffmpeg_command
+
+        cmd = build_ffmpeg_command(Path("/out.mp3"), "mp3")
+        assert "libmp3lame" in cmd
+
+    def test_opus_codec(self):
+        from abogen.domain.audio_helpers import build_ffmpeg_command
+
+        cmd = build_ffmpeg_command(Path("/out.opus"), "opus")
+        assert "libopus" in cmd
+
+    def test_m4b_codec(self):
+        from abogen.domain.audio_helpers import build_ffmpeg_command
+
+        cmd = build_ffmpeg_command(Path("/out.m4b"), "m4b")
+        assert "aac" in cmd
+        assert "-q:a" in cmd
+        assert "+faststart+use_metadata_tags" in cmd
+
+    def test_wav_copy_codec(self):
+        from abogen.domain.audio_helpers import build_ffmpeg_command
+
+        cmd = build_ffmpeg_command(Path("/out.wav"), "wav")
+        assert "copy" in cmd
+
+    def test_with_metadata(self):
+        from abogen.domain.audio_helpers import build_ffmpeg_command
+
+        cmd = build_ffmpeg_command(Path("/out.mp3"), "mp3", metadata={"album": "Test"})
+        assert str(Path("/out.mp3")) in cmd
+
+
+# ---------------------------------------------------------------------------
+# to_float32
+# ---------------------------------------------------------------------------
+
+
+class TestToFloat32:
+    """to_float32 converts audio to float32 numpy array."""
+
+    def test_none_returns_empty(self):
+        from abogen.domain.audio_helpers import to_float32
+
+        result = to_float32(None)
+        assert isinstance(result, np.ndarray)
+        assert result.dtype == np.float32
+        assert len(result) == 0
+
+    def test_numpy_array(self):
+        from abogen.domain.audio_helpers import to_float32
+
+        arr = np.array([1.0, 2.0, 3.0], dtype="float64")
+        result = to_float32(arr)
+        assert result.dtype == np.float32
+        assert len(result) == 3
+
+    def test_mock_tensor(self):
+        from abogen.domain.audio_helpers import to_float32
+
+        tensor = MagicMock()
+        tensor.detach.return_value = tensor
+        tensor.cpu.return_value = tensor
+        tensor.numpy.return_value = np.array([1.0, 2.0])
+        result = to_float32(tensor)
+        assert result.dtype == np.float32
+        assert len(result) == 2
+
+    def test_list_input(self):
+        from abogen.domain.audio_helpers import to_float32
+
+        result = to_float32([1.0, 2.0])
+        assert result.dtype == np.float32
+        assert len(result) == 2
+
+
+# ---------------------------------------------------------------------------
+# apply_m4b_chapters_with_mutagen
+# ---------------------------------------------------------------------------
+
+
+class TestApplyM4bChaptersWithMutagen:
+    """apply_m4b_chapters_with_mutagen writes chapter atoms to MP4."""
+
+    def test_empty_chapters_returns_false(self):
+        from abogen.domain.audio_helpers import apply_m4b_chapters_with_mutagen
+
+        assert apply_m4b_chapters_with_mutagen(Path("/fake.m4b"), []) is False
+
+    def test_missing_mutagen_raises(self):
+        from abogen.domain.audio_helpers import apply_m4b_chapters_with_mutagen
+
+        with patch.dict("sys.modules", {"mutagen": None, "mutagen.mp4": None}):
+            with pytest.raises((ImportError, KeyError)):
+                apply_m4b_chapters_with_mutagen(
+                    Path("/fake.m4b"), [{"start": 0, "title": "Ch1"}]
+                )

tests/test_chapter_merge_normalize.py

@@ -0,0 +1,167 @@
+"""Tests for chapter_overrides, merge_metadata, normalize_for_pipeline.
+
+Tests import from domain modules (new location).
+"""
+
+from __future__ import annotations
+
+import pytest
+from abogen.text_extractor import ExtractedChapter
+
+
+# ---------------------------------------------------------------------------
+# apply_chapter_overrides
+# ---------------------------------------------------------------------------
+
+
+class TestApplyChapterOverrides:
+    """apply_chapter_overrides applies chapter overrides to extracted chapters."""
+
+    def test_empty_overrides(self):
+        from abogen.domain.chapter_overrides import apply_chapter_overrides
+
+        result, updates, diags = apply_chapter_overrides([], [])
+        assert result == []
+        assert updates == {}
+        assert diags == []
+
+    def test_basic_override_by_index(self):
+        from abogen.domain.chapter_overrides import apply_chapter_overrides
+
+        chapters = [ExtractedChapter(title="Ch1", text="original")]
+        overrides = [{"index": 0, "title": "New Title", "text": "new text"}]
+        result, updates, diags = apply_chapter_overrides(chapters, overrides)
+        assert len(result) == 1
+        assert result[0].title == "New Title"
+        assert result[0].text == "new text"
+
+    def test_override_by_source_title(self):
+        from abogen.domain.chapter_overrides import apply_chapter_overrides
+
+        chapters = [ExtractedChapter(title="Ch1", text="text1")]
+        overrides = [{"source_title": "Ch1", "title": "Renamed"}]
+        result, _, _ = apply_chapter_overrides(chapters, overrides)
+        assert result[0].title == "Renamed"
+
+    def test_disabled_override_skipped(self):
+        from abogen.domain.chapter_overrides import apply_chapter_overrides
+
+        chapters = [ExtractedChapter(title="Ch1", text="text1")]
+        overrides = [{"index": 0, "enabled": False}]
+        result, _, _ = apply_chapter_overrides(chapters, overrides)
+        assert len(result) == 0
+
+    def test_metadata_updates_collected(self):
+        from abogen.domain.chapter_overrides import apply_chapter_overrides
+
+        chapters = [ExtractedChapter(title="Ch1", text="text1")]
+        overrides = [{"index": 0, "metadata": {"album": "New Album"}}]
+        _, updates, _ = apply_chapter_overrides(chapters, overrides)
+        assert updates["album"] == "New Album"
+
+    def test_no_matching_chapter_diagnostic(self):
+        from abogen.domain.chapter_overrides import apply_chapter_overrides
+
+        overrides = [{"index": 99, "title": "X"}]
+        _, _, diags = apply_chapter_overrides([], overrides)
+        assert len(diags) == 1
+        assert "Skipped" in diags[0]
+
+    def test_non_dict_override_skipped(self):
+        from abogen.domain.chapter_overrides import apply_chapter_overrides
+
+        _, _, diags = apply_chapter_overrides([], ["bad"])
+        assert len(diags) == 1
+
+    def test_text_from_base_when_not_provided(self):
+        from abogen.domain.chapter_overrides import apply_chapter_overrides
+
+        chapters = [ExtractedChapter(title="Ch1", text="original text")]
+        overrides = [{"index": 0, "title": "New Title"}]
+        result, _, _ = apply_chapter_overrides(chapters, overrides)
+        assert result[0].text == "original text"
+
+    def test_default_title_when_no_base(self):
+        from abogen.domain.chapter_overrides import apply_chapter_overrides
+
+        overrides = [{"text": "some text"}]
+        result, _, _ = apply_chapter_overrides([], overrides)
+        assert result[0].title == "Chapter 1"
+
+
+# ---------------------------------------------------------------------------
+# merge_metadata
+# ---------------------------------------------------------------------------
+
+
+class TestMergeMetadata:
+    """merge_metadata merges extracted metadata with overrides."""
+
+    def test_both_empty(self):
+        from abogen.domain.metadata_merge import merge_metadata
+
+        assert merge_metadata({}, {}) == {}
+
+    def test_only_extracted(self):
+        from abogen.domain.metadata_merge import merge_metadata
+
+        result = merge_metadata({"album": "Book"}, {})
+        assert result == {"album": "Book"}
+
+    def test_only_overrides(self):
+        from abogen.domain.metadata_merge import merge_metadata
+
+        result = merge_metadata(None, {"album": "Override"})
+        assert result == {"album": "Override"}
+
+    def test_override_wins(self):
+        from abogen.domain.metadata_merge import merge_metadata
+
+        result = merge_metadata({"album": "Old"}, {"album": "New"})
+        assert result == {"album": "New"}
+
+    def test_none_value_deletes_key(self):
+        from abogen.domain.metadata_merge import merge_metadata
+
+        result = merge_metadata({"album": "Book"}, {"album": None})
+        assert "album" not in result
+
+    def test_none_values_in_extracted_skipped(self):
+        from abogen.domain.metadata_merge import merge_metadata
+
+        result = merge_metadata({"album": None, "artist": "X"}, {})
+        assert result == {"artist": "X"}
+
+    def test_numeric_values_stringified(self):
+        from abogen.domain.metadata_merge import merge_metadata
+
+        result = merge_metadata({"track": 1}, {})
+        assert result["track"] == "1"
+
+
+# ---------------------------------------------------------------------------
+# normalize_for_pipeline (thin wrapper)
+# ---------------------------------------------------------------------------
+
+
+class TestNormalizeForPipeline:
+    """normalize_for_pipeline normalizes text with runtime settings."""
+
+    def test_basic_normalize(self):
+        from abogen.domain.normalization import normalize_text_for_pipeline
+
+        result = normalize_text_for_pipeline("Hello   World")
+        assert isinstance(result, str)
+        assert len(result) > 0
+
+    def test_empty_string(self):
+        from abogen.domain.normalization import normalize_text_for_pipeline
+
+        result = normalize_text_for_pipeline("")
+        assert result == ""
+
+    def test_with_overrides(self):
+        from abogen.domain.normalization import normalize_text_for_pipeline
+
+        result = normalize_text_for_pipeline("test", normalization_overrides={"number_format": "words"})
+        assert isinstance(result, str)

tests/test_chapter_titles.py

@@ -0,0 +1,144 @@
+"""Tests for domain/chapter_titles.py."""
+import sys
+import os
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
+
+from abogen.domain.chapter_titles import (
+    simplify_heading_text,
+    headings_equivalent,
+    strip_duplicate_heading_line,
+    normalize_caps_word,
+    normalize_chapter_opening_caps,
+    format_spoken_chapter_title,
+)
+
+
+class TestSimplifyHeadingText:
+    def test_empty(self):
+        assert simplify_heading_text("") == ""
+
+    def test_none(self):
+        assert simplify_heading_text(None) == ""
+
+    def test_chapter_prefix_removed(self):
+        assert simplify_heading_text("Chapter 1") == "1"
+
+    def test_lowercase(self):
+        assert simplify_heading_text("Chapter 1: The Beginning") == "1thebeginning"
+
+    def test_strips_special_chars(self):
+        result = simplify_heading_text("Ch. 1")
+        assert "1" in result
+        assert "." not in result
+
+    def test_no_chapter_prefix(self):
+        result = simplify_heading_text("Part 2")
+        assert "part" in result
+
+
+class TestHeadingsEquivalent:
+    def test_exact_match(self):
+        assert headings_equivalent("Chapter 1", "Chapter 1")
+
+    def test_prefix_match(self):
+        assert headings_equivalent("Chapter 2", "Chapter 2: The Return")
+
+    def test_reverse_prefix(self):
+        assert headings_equivalent("Chapter 2: The Return", "Chapter 2")
+
+    def test_different_numbers(self):
+        assert not headings_equivalent("Chapter 1", "Chapter 2")
+
+    def test_empty(self):
+        assert not headings_equivalent("", "Chapter 1")
+
+    def test_long_containment(self):
+        assert headings_equivalent("Introduction", "Introduction to Everything")
+
+
+class TestStripDuplicateHeadingLine:
+    def test_removes_heading(self):
+        text = "Chapter 1\n\nSome text here"
+        result, removed = strip_duplicate_heading_line(text, "Chapter 1")
+        assert removed is True
+        assert "Chapter 1" not in result
+        assert "Some text here" in result
+
+    def test_no_heading(self):
+        text = "Just some text"
+        result, removed = strip_duplicate_heading_line(text, "Chapter 1")
+        assert removed is False
+        assert result == text
+
+    def test_empty_text(self):
+        result, removed = strip_duplicate_heading_line("", "Chapter 1")
+        assert removed is False
+
+    def test_strips_leading_empty_lines(self):
+        text = "Chapter 1\n\n\n\nText"
+        result, removed = strip_duplicate_heading_line(text, "Chapter 1")
+        assert removed is True
+        assert result.startswith("Text")
+
+
+class TestNormalizeCapsWord:
+    def test_acronym_kept(self):
+        assert normalize_caps_word("TTS") == "TTS"
+
+    def test_single_letter_kept(self):
+        assert normalize_caps_word("A") == "A"
+
+    def test_roman_numeral_kept(self):
+        assert normalize_caps_word("IV") == "IV"
+
+    def test_all_caps_converted(self):
+        result = normalize_caps_word("HELLO")
+        assert result == "Hello"
+
+    def test_with_hyphen(self):
+        result = normalize_caps_word("WELL-KNOWN")
+        assert result == "Well-Known"
+
+
+class TestNormalizeChapterOpeningCaps:
+    def test_all_caps_words(self):
+        text = "THIS IS A TEST"
+        result, changed = normalize_chapter_opening_caps(text)
+        assert changed is True
+        assert result == "This Is A Test"
+
+    def test_already_normal(self):
+        text = "This is normal"
+        result, changed = normalize_chapter_opening_caps(text)
+        assert changed is False
+
+    def test_empty(self):
+        result, changed = normalize_chapter_opening_caps("")
+        assert changed is False
+
+    def test_mixed(self):
+        text = "HELLO world"
+        result, changed = normalize_chapter_opening_caps(text)
+        assert changed is True
+
+
+class TestFormatSpokenChapterTitle:
+    def test_empty_no_prefix(self):
+        assert format_spoken_chapter_title("", 1, False) == ""
+
+    def test_empty_with_prefix(self):
+        assert format_spoken_chapter_title("", 1, True) == "Chapter 1"
+
+    def test_no_prefix_returns_base(self):
+        assert format_spoken_chapter_title("My Chapter", 1, False) == "My Chapter"
+
+    def test_already_has_chapter(self):
+        assert format_spoken_chapter_title("Chapter 5", 1, True) == "Chapter 5"
+
+    def test_number_prefix(self):
+        result = format_spoken_chapter_title("3. The End", 1, True)
+        assert result == "Chapter 3. The End"
+
+    def test_number_only(self):
+        result = format_spoken_chapter_title("7", 1, True)
+        assert result == "Chapter 7"

tests/test_chunk_helpers.py

@@ -3,7 +3,8 @@ from __future__ import annotations
 from types import SimpleNamespace
 
 from abogen.chunking import chunk_text
-from abogen.webui.conversion_runner import _chunk_voice_spec, _group_chunks_by_chapter
+from abogen.domain.voice_resolution import chunk_voice_spec
+from abogen.domain.chunk_utils import group_chunks_by_chapter
 
 
 def test_group_chunks_by_chapter_orders_and_groups() -> None:
@@ -13,7 +14,7 @@ def test_group_chunks_by_chapter_orders_and_groups() -> None:
         {"chapter_index": 1, "chunk_index": 0, "text": "next"},
     ]
 
-    grouped = _group_chunks_by_chapter(chunks)
+    grouped = group_chunks_by_chapter(chunks)
 
     assert [entry["text"] for entry in grouped[0]] == ["body", "tail"]
     assert grouped[1][0]["text"] == "next"
@@ -23,7 +24,7 @@ def test_chunk_voice_spec_prefers_chunk_overrides() -> None:
     job = SimpleNamespace(voice="base_voice", speakers={})
     chunk = {"voice": "override_voice", "speaker_id": "narrator"}
 
-    assert _chunk_voice_spec(job, chunk, "fallback") == "override_voice"
+    assert chunk_voice_spec(job, chunk, "fallback") == "override_voice"
 
 
 def test_chunk_voice_spec_falls_back_to_speaker_voice() -> None:
@@ -32,14 +33,14 @@ def test_chunk_voice_spec_falls_back_to_speaker_voice() -> None:
     )
     chunk = {"speaker_id": "narrator"}
 
-    assert _chunk_voice_spec(job, chunk, "fallback") == "speaker_voice"
+    assert chunk_voice_spec(job, chunk, "fallback") == "speaker_voice"
 
 
 def test_chunk_voice_spec_uses_fallback_when_no_overrides() -> None:
     job = SimpleNamespace(voice="base_voice", speakers={})
     chunk = {"speaker_id": "unknown"}
 
-    assert _chunk_voice_spec(job, chunk, "fallback") == "fallback"
+    assert chunk_voice_spec(job, chunk, "fallback") == "fallback"
 
 
 def test_chunk_text_merges_title_abbreviations() -> None:

tests/test_chunk_text_for_tts_prefers_raw.py

@@ -1,4 +1,4 @@
-from abogen.webui.conversion_runner import _chunk_text_for_tts
+from abogen.domain.chunk_utils import chunk_text_for_tts
 
 
 def test_chunk_text_for_tts_prefers_text_over_normalized_text():
@@ -9,7 +9,7 @@ def test_chunk_text_for_tts_prefers_text_over_normalized_text():
         "text": "Unfu*k",
     }
 
-    assert _chunk_text_for_tts(entry) == "Unfu*k"
+    assert chunk_text_for_tts(entry) == "Unfu*k"
 
 
 def test_chunk_text_for_tts_falls_back_to_original_text_then_normalized_text():
@@ -17,9 +17,9 @@ def test_chunk_text_for_tts_falls_back_to_original_text_then_normalized_text():
         "original_text": "Hello * world",
         "normalized_text": "Hello world",
     }
-    assert _chunk_text_for_tts(entry) == "Hello * world"
+    assert chunk_text_for_tts(entry) == "Hello * world"
 
     entry2 = {
         "normalized_text": "Only normalized",
     }
-    assert _chunk_text_for_tts(entry2) == "Only normalized"
+    assert chunk_text_for_tts(entry2) == "Only normalized"

tests/test_chunk_utils.py

@@ -0,0 +1,123 @@
+"""Tests for chunk processing utilities.
+
+Tests import from domain.chunk_utils (new location).
+"""
+
+from __future__ import annotations
+
+from types import SimpleNamespace
+from unittest.mock import patch
+
+import pytest
+
+
+# ---------------------------------------------------------------------------
+# safe_int
+# ---------------------------------------------------------------------------
+
+
+class TestSafeInt:
+    """safe_int safely converts to int with a default."""
+
+    def test_int_value(self):
+        from abogen.domain.chunk_utils import safe_int
+
+        assert safe_int(42) == 42
+
+    def test_string_number(self):
+        from abogen.domain.chunk_utils import safe_int
+
+        assert safe_int("7") == 7
+
+    def test_float_truncated(self):
+        from abogen.domain.chunk_utils import safe_int
+
+        assert safe_int(3.9) == 3
+
+    def test_none_returns_default(self):
+        from abogen.domain.chunk_utils import safe_int
+
+        assert safe_int(None) == 0
+
+    def test_garbage_returns_default(self):
+        from abogen.domain.chunk_utils import safe_int
+
+        assert safe_int("abc") == 0
+
+    def test_custom_default(self):
+        from abogen.domain.chunk_utils import safe_int
+
+        assert safe_int(None, default=-1) == -1
+
+
+# ---------------------------------------------------------------------------
+# chunk_text_for_tts (supplement existing tests)
+# ---------------------------------------------------------------------------
+
+
+class TestChunkTextForTts:
+    """chunk_text_for_tts selects the best text source."""
+
+    def test_non_mapping_returns_empty(self):
+        from abogen.domain.chunk_utils import chunk_text_for_tts
+
+        assert chunk_text_for_tts("not a dict") == ""
+
+    def test_none_returns_empty(self):
+        from abogen.domain.chunk_utils import chunk_text_for_tts
+
+        assert chunk_text_for_tts(None) == ""
+
+    def test_empty_dict_returns_empty(self):
+        from abogen.domain.chunk_utils import chunk_text_for_tts
+
+        assert chunk_text_for_tts({}) == ""
+
+    def test_whitespace_only_returns_empty(self):
+        from abogen.domain.chunk_utils import chunk_text_for_tts
+
+        assert chunk_text_for_tts({"text": "  "}) == ""
+
+
+# ---------------------------------------------------------------------------
+# record_override_usage
+# ---------------------------------------------------------------------------
+
+
+class TestRecordOverrideUsage:
+    """record_override_usage records pronunciation override usage."""
+
+    def test_noop_when_empty(self):
+        from abogen.domain.chunk_utils import record_override_usage
+
+        job = SimpleNamespace(language="en")
+        record_override_usage(job, {}, {})
+
+    def test_noop_when_all_zero(self):
+        from abogen.domain.chunk_utils import record_override_usage
+
+        job = SimpleNamespace(language="en")
+        record_override_usage(job, {"hello": 0}, {"hello": "hi"})
+
+    def test_records_usage(self):
+        from abogen.domain.chunk_utils import record_override_usage
+
+        job = SimpleNamespace(language="en", add_log=lambda *a, **kw: None)
+        with patch("abogen.domain.chunk_utils.increment_usage") as mock_inc:
+            record_override_usage(job, {"hello": 2}, {"hello": "hi"})
+            mock_inc.assert_called_once_with(language="en", token="hi", amount=2)
+
+    def test_fallback_token_from_normalized(self):
+        from abogen.domain.chunk_utils import record_override_usage
+
+        job = SimpleNamespace(language="ja", add_log=lambda *a, **kw: None)
+        with patch("abogen.domain.chunk_utils.increment_usage") as mock_inc:
+            record_override_usage(job, {"test": 1}, {})
+            mock_inc.assert_called_once_with(language="ja", token="test", amount=1)
+
+    def test_handles_exception_gracefully(self):
+        from abogen.domain.chunk_utils import record_override_usage
+
+        job = SimpleNamespace(language="en", add_log=lambda *a, **kw: None)
+        with patch("abogen.domain.chunk_utils.increment_usage", side_effect=RuntimeError("db error")):
+            record_override_usage(job, {"hello": 1}, {"hello": "hi"})

tests/test_conversion_chapter_titles.py

@@ -124,3 +124,117 @@ def test_normalize_chapter_opening_caps_keeps_mixed_case() -> None:
     normalized, changed = _normalize_chapter_opening_caps("Already Mixed Case")
     assert normalized == "Already Mixed Case"
     assert changed is False
+
+
+class TestApplyChapterTextTransforms:
+    """Tests for the combined heading-strip + opening-caps helper."""
+
+    def test_both_enabled_heading_matches(self) -> None:
+        from abogen.domain.chapter_titles import apply_chapter_text_transforms
+
+        text, heading_removed, caps_changed = apply_chapter_text_transforms(
+            "Chapter 1: The Beginning\nBody text here",
+            heading_text="Chapter 1: The Beginning",
+            raw_title="Chapter 1: The Beginning",
+            strip_heading=True,
+            normalize_caps=True,
+        )
+        assert heading_removed is True
+        assert "Body text here" in text
+        assert "Chapter 1" not in text
+
+    def test_heading_fallback_to_number(self) -> None:
+        from abogen.domain.chapter_titles import apply_chapter_text_transforms
+
+        text, heading_removed, caps_changed = apply_chapter_text_transforms(
+            "1. The Beginning\nBody text",
+            heading_text="Chapter 1: The Beginning",
+            raw_title="1: The Beginning",
+            strip_heading=True,
+            normalize_caps=False,
+        )
+        assert heading_removed is True
+        assert "Body text" in text
+
+    def test_only_heading_strip(self) -> None:
+        from abogen.domain.chapter_titles import apply_chapter_text_transforms
+
+        text, heading_removed, caps_changed = apply_chapter_text_transforms(
+            "Chapter 1: Title\nBody text",
+            heading_text="Chapter 1: Title",
+            raw_title="",
+            strip_heading=True,
+            normalize_caps=False,
+        )
+        assert heading_removed is True
+        assert caps_changed is False
+
+    def test_only_opening_caps(self) -> None:
+        from abogen.domain.chapter_titles import apply_chapter_text_transforms
+
+        text, heading_removed, caps_changed = apply_chapter_text_transforms(
+            "ALL CAPS START OF CHAPTER",
+            heading_text="Chapter 1",
+            raw_title="",
+            strip_heading=False,
+            normalize_caps=True,
+        )
+        assert heading_removed is False
+        assert caps_changed is True
+        assert text == "All Caps Start Of Chapter"
+
+    def test_both_disabled_no_change(self) -> None:
+        from abogen.domain.chapter_titles import apply_chapter_text_transforms
+
+        original = "Some text here"
+        text, heading_removed, caps_changed = apply_chapter_text_transforms(
+            original,
+            heading_text="Chapter 1",
+            raw_title="",
+            strip_heading=False,
+            normalize_caps=False,
+        )
+        assert text == original
+        assert heading_removed is False
+        assert caps_changed is False
+
+    def test_heading_not_matching(self) -> None:
+        from abogen.domain.chapter_titles import apply_chapter_text_transforms
+
+        text, heading_removed, caps_changed = apply_chapter_text_transforms(
+            "Completely different text",
+            heading_text="Chapter 1: Title",
+            raw_title="",
+            strip_heading=True,
+            normalize_caps=False,
+        )
+        assert heading_removed is False
+        assert text == "Completely different text"
+
+    def test_empty_text(self) -> None:
+        from abogen.domain.chapter_titles import apply_chapter_text_transforms
+
+        text, heading_removed, caps_changed = apply_chapter_text_transforms(
+            "",
+            heading_text="Chapter 1",
+            raw_title="",
+            strip_heading=True,
+            normalize_caps=True,
+        )
+        assert text == ""
+        assert heading_removed is False
+        assert caps_changed is False
+
+    def test_both_enabled_text_only_has_caps(self) -> None:
+        from abogen.domain.chapter_titles import apply_chapter_text_transforms
+
+        text, heading_removed, caps_changed = apply_chapter_text_transforms(
+            "NASA MISSION LOG",
+            heading_text="Chapter 1",
+            raw_title="",
+            strip_heading=True,
+            normalize_caps=True,
+        )
+        assert heading_removed is False
+        assert caps_changed is True
+        assert text == "NASA Mission Log"

tests/test_exporters.py

@@ -0,0 +1,163 @@
+"""Tests for ExportService FFmpeg metadata methods."""
+import os
+import sys
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
+
+from pathlib import Path
+from abogen.infrastructure.exporters import ExportService
+
+
+class TestEscapeFfmetadataValue:
+    def setup_method(self):
+        self.svc = ExportService()
+
+    def test_simple_string(self):
+        assert self.svc._escape_ffmetadata_value("hello") == "hello"
+
+    def test_escapes_backslash(self):
+        assert self.svc._escape_ffmetadata_value("a\\b") == "a\\\\b"
+
+    def test_escapes_newline(self):
+        assert self.svc._escape_ffmetadata_value("line1\nline2") == "line1\\nline2"
+
+    def test_escapes_equals(self):
+        assert self.svc._escape_ffmetadata_value("key=value") == "key\\=value"
+
+    def test_escapes_semicolon(self):
+        assert self.svc._escape_ffmetadata_value("a;b") == "a\\;b"
+
+    def test_escapes_hash(self):
+        assert self.svc._escape_ffmetadata_value("#comment") == "\\#comment"
+
+    def test_escapes_all_special(self):
+        result = self.svc._escape_ffmetadata_value("a\\b\nc=d;e#f")
+        assert "\\\\" in result
+        assert "\\n" in result
+        assert "\\=" in result
+        assert "\\;" in result
+        assert "\\#" in result
+
+    def test_empty_string(self):
+        assert self.svc._escape_ffmetadata_value("") == ""
+
+
+class TestRenderFfmetadata:
+    def setup_method(self):
+        self.svc = ExportService()
+
+    def test_renders_header(self):
+        result = self.svc.render_ffmetadata({"title": "My Book"}, [])
+        assert result.startswith(";FFMETADATA1\n")
+        assert "title=My Book\n" in result
+
+    def test_renders_multiple_keys(self):
+        result = self.svc.render_ffmetadata({"title": "T", "artist": "A"}, [])
+        assert "title=T\n" in result
+        assert "artist=A\n" in result
+
+    def test_skips_none_values(self):
+        result = self.svc.render_ffmetadata({"title": None}, [])
+        assert "title=" not in result
+
+    def test_renders_chapters(self):
+        chapters = [{"start": 0.0, "end": 10.0, "title": "Ch 1"}]
+        result = self.svc.render_ffmetadata({}, chapters)
+        assert "[CHAPTER]" in result
+        assert "TIMEBASE=1/1000" in result
+        assert "START=0" in result
+        assert "END=10000" in result
+        assert "title=Ch 1" in result
+
+    def test_renders_voice_in_chapter(self):
+        chapters = [{"start": 0.0, "end": 5.0, "voice": "af_heart"}]
+        result = self.svc.render_ffmetadata({}, chapters)
+        assert "voice=af_heart" in result
+
+    def test_skips_chapters_without_times(self):
+        chapters = [{"title": "No times"}]
+        result = self.svc.render_ffmetadata({}, chapters)
+        assert "[CHAPTER]" not in result
+
+    def test_end_equals_start_gets_minimum_duration(self):
+        chapters = [{"start": 5.0, "end": 5.0, "title": "Zero"}]
+        result = self.svc.render_ffmetadata({}, chapters)
+        assert "START=5000" in result
+        assert "END=5001" in result
+
+    def test_empty_metadata_and_chapters(self):
+        result = self.svc.render_ffmetadata({}, [])
+        assert result.strip() == ";FFMETADATA1"
+
+    def test_escapes_special_chars_in_title(self):
+        chapters = [{"start": 0.0, "end": 1.0, "title": "A=B;C#D"}]
+        result = self.svc.render_ffmetadata({}, chapters)
+        assert "\\=" in result
+        assert "\\;" in result
+        assert "\\#" in result
+
+    def test_negative_start_clamped_to_zero(self):
+        chapters = [{"start": -1.0, "end": 5.0, "title": "Neg"}]
+        result = self.svc.render_ffmetadata({}, chapters)
+        assert "START=0" in result
+
+
+class TestMetadataToFfmpegArgs:
+    def setup_method(self):
+        self.svc = ExportService()
+
+    def test_simple_metadata(self):
+        args = self.svc._metadata_to_ffmpeg_args({"title": "My Book"})
+        assert args == ["-metadata", "title=My Book"]
+
+    def test_year_becomes_date(self):
+        args = self.svc._metadata_to_ffmpeg_args({"year": "2024"})
+        assert args == ["-metadata", "date=2024"]
+
+    def test_skips_none_and_empty(self):
+        args = self.svc._metadata_to_ffmpeg_args({"title": None, "artist": ""})
+        assert args == []
+
+    def test_skips_empty_key(self):
+        args = self.svc._metadata_to_ffmpeg_args({"": "value"})
+        assert args == []
+
+    def test_multiple_keys(self):
+        args = self.svc._metadata_to_ffmpeg_args({"title": "T", "artist": "A"})
+        assert "-metadata" in args
+        assert "title=T" in args
+        assert "artist=A" in args
+
+    def test_empty_metadata(self):
+        assert self.svc._metadata_to_ffmpeg_args({}) == []
+
+    def test_none_metadata(self):
+        assert self.svc._metadata_to_ffmpeg_args(None) == []
+
+
+class TestWriteFfmetadataFile:
+    def setup_method(self):
+        self.svc = ExportService()
+
+    def test_writes_file(self, tmp_path):
+        audio = tmp_path / "test.mp3"
+        audio.touch()
+        meta = {"title": "My Book"}
+        chapters = [{"start": 0.0, "end": 5.0, "title": "Ch 1"}]
+        result = self.svc.write_ffmetadata_file(audio, meta, chapters)
+        assert result is not None
+        assert result.exists()
+        content = result.read_text()
+        assert ";FFMETADATA1" in content
+        assert "title=My Book" in content
+
+    def test_returns_none_for_empty(self, tmp_path):
+        audio = tmp_path / "test.mp3"
+        audio.touch()
+        result = self.svc.write_ffmetadata_file(audio, {}, [])
+        assert result is None
+
+    def test_returns_none_for_only_header(self, tmp_path):
+        audio = tmp_path / "test.mp3"
+        audio.touch()
+        result = self.svc.write_ffmetadata_file(audio, None, None)
+        assert result is None

tests/test_ffmetadata.py

@@ -1,8 +1,9 @@
 from __future__ import annotations
 
-from pathlib import Path
+from abogen.infrastructure.exporters import ExportService
 
-from abogen.webui.conversion_runner import _render_ffmetadata, _write_ffmetadata_file
+
+svc = ExportService()
 
 
 def test_render_ffmetadata_includes_chapters(tmp_path):
@@ -17,7 +18,7 @@ def test_render_ffmetadata_includes_chapters(tmp_path):
         {"start": 5.0, "end": 12.345, "title": "Chapter 2"},
     ]
 
-    rendered = _render_ffmetadata(metadata, chapters)
+    rendered = svc.render_ffmetadata(metadata, chapters)
 
     assert ";FFMETADATA1" in rendered
     assert "title=Sample Book" in rendered
@@ -30,7 +31,7 @@ def test_render_ffmetadata_includes_chapters(tmp_path):
     assert "voice=voice_a" in rendered
 
     audio_path = tmp_path / "book.m4b"
-    metadata_path = _write_ffmetadata_file(audio_path, metadata, chapters)
+    metadata_path = svc.write_ffmetadata_file(audio_path, metadata, chapters)
     assert metadata_path is not None
     assert metadata_path.exists()
 

tests/test_metadata_helpers.py

@@ -0,0 +1,133 @@
+"""Tests for domain/metadata_helpers.py."""
+import sys
+import os
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
+
+from abogen.domain.metadata_helpers import (
+    normalize_metadata_map,
+    format_author_sentence,
+    ensure_sentence,
+    normalize_series_number,
+    extract_series_metadata,
+    format_series_sentence,
+)
+
+
+class TestNormalizeMetadataMap:
+    def test_empty(self):
+        assert normalize_metadata_map({}) == {}
+
+    def test_none(self):
+        assert normalize_metadata_map(None) == {}
+
+    def test_normalizes_keys(self):
+        result = normalize_metadata_map({"Title": "My Book", "artist": "John"})
+        assert "title" in result
+        assert "artist" in result
+
+    def test_skips_none_values(self):
+        result = normalize_metadata_map({"title": None, "artist": "John"})
+        assert "title" not in result
+
+    def test_skips_empty_values(self):
+        result = normalize_metadata_map({"title": "", "artist": "John"})
+        assert "title" not in result
+
+
+class TestFormatAuthorSentence:
+    def test_none(self):
+        assert format_author_sentence(None) == ""
+
+    def test_empty(self):
+        assert format_author_sentence("") == ""
+
+    def test_unknown(self):
+        assert format_author_sentence("Unknown") == ""
+
+    def test_single(self):
+        assert format_author_sentence("John Doe") == "By John Doe"
+
+    def test_two(self):
+        assert format_author_sentence("John, Jane") == "By John and Jane"
+
+    def test_three(self):
+        assert format_author_sentence("John, Jane, Bob") == "By John, Jane, and Bob"
+
+    def test_ampersand(self):
+        assert format_author_sentence("John & Jane") == "By John and Jane"
+
+
+class TestEnsureSentence:
+    def test_empty(self):
+        assert ensure_sentence("") == ""
+
+    def test_already_sentence(self):
+        assert ensure_sentence("Hello.") == "Hello."
+
+    def test_adds_period(self):
+        assert ensure_sentence("Hello") == "Hello."
+
+    def test_exclamation(self):
+        assert ensure_sentence("Hello!") == "Hello!"
+
+
+class TestNormalizeSeriesNumber:
+    def test_empty(self):
+        assert normalize_series_number("") is None
+
+    def test_integer(self):
+        assert normalize_series_number("3") == "3"
+
+    def test_float(self):
+        assert normalize_series_number("3.5") == "3.5"
+
+    def test_float_trailing_zero(self):
+        assert normalize_series_number("3.10") == "3.1"
+
+    def test_comma_as_separator(self):
+        assert normalize_series_number("3,5") == "3.5"
+
+    def test_text_with_number(self):
+        assert normalize_series_number("Book 3") == "3"
+
+    def test_none(self):
+        assert normalize_series_number(None) is None
+
+
+class TestExtractSeriesMetadata:
+    def test_empty(self):
+        name, number = extract_series_metadata({})
+        assert name is None
+        assert number is None
+
+    def test_series_name(self):
+        name, number = extract_series_metadata({"series": "My Series"})
+        assert name == "My Series"
+        assert number is None
+
+    def test_series_number(self):
+        name, number = extract_series_metadata({"series_index": "3"})
+        assert name is None
+        assert number == "3"
+
+    def test_both(self):
+        name, number = extract_series_metadata({"series": "My Series", "series_index": "3"})
+        assert name == "My Series"
+        assert number == "3"
+
+
+class TestFormatSeriesSentence:
+    def test_empty(self):
+        assert format_series_sentence(None, None) == ""
+
+    def test_name_only(self):
+        assert format_series_sentence("My Series", None) == ""
+
+    def test_number_only(self):
+        assert format_series_sentence(None, "3") == ""
+
+    def test_both(self):
+        assert format_series_sentence("My Series", "3") == "Book 3 of the My Series"
+
+    def test_with_the(self):
+        assert format_series_sentence("The Lord of the Rings", "1") == "Book 1 of The Lord of the Rings"

tests/test_output_paths.py

@@ -1,79 +1,257 @@
+"""Tests for output path utilities.
+
+Tests import from domain/output_paths.py (new module).
+"""
+
 from __future__ import annotations
 
-import time
+import re
+from datetime import datetime
 from pathlib import Path
+from types import SimpleNamespace
 
 import pytest
 
-from abogen.webui.conversion_runner import _build_output_path, _prepare_project_layout
+
-from abogen.webui.service import Job
+# ---------------------------------------------------------------------------
+# slugify
+# ---------------------------------------------------------------------------
 
 
-def _sample_job(tmp_path: Path) -> Job:
+class TestSlugify:
-    source = tmp_path / "sample.txt"
+    """slugify converts title to filesystem-safe slug."""
-    source.write_text("example", encoding="utf-8")
+
-    return Job(
+    def test_basic_slug(self):
-        id="job-1",
+        from abogen.domain.output_paths import slugify
-        original_filename="Sample Title.txt",
+
-        stored_path=source,
+        assert slugify("Hello World", 0) == "hello_world"
-        language="en",
+
-        voice="af_alloy",
+    def test_strips_special_chars(self):
-        speed=1.0,
+        from abogen.domain.output_paths import slugify
-        use_gpu=False,
+
-        subtitle_mode="Sentence",
+        result = slugify("Chapter 1: The Beginning!", 0)
-        output_format="mp3",
+        assert result == "chapter_1_the_beginning"
-        save_mode="Use default save location",
+
-        output_folder=tmp_path,
+    def test_empty_title_uses_index(self):
-        replace_single_newlines=False,
+        from abogen.domain.output_paths import slugify
-        subtitle_format="srt",
+
-        created_at=time.time(),
+        assert slugify("", 5) == "chapter_05"
-    )
+
+    def test_truncated_at_80(self):
+        from abogen.domain.output_paths import slugify
+
+        long_title = "a" * 100
+        assert len(slugify(long_title, 0)) == 80
+
+    def test_preserves_hyphens(self):
+        from abogen.domain.output_paths import slugify
+
+        assert slugify("mid-night", 0) == "mid-night"
 
 
-def test_prepare_project_layout_uses_timestamped_folder(
+# ---------------------------------------------------------------------------
-    monkeypatch: pytest.MonkeyPatch, tmp_path: Path
+# sanitize_output_stem
-) -> None:
+# ---------------------------------------------------------------------------
-    job = _sample_job(tmp_path)
-    monkeypatch.setattr(
-        "abogen.webui.conversion_runner._output_timestamp_token",
-        lambda: "20250101-120000",
-    )
-
-    project_root, audio_dir, subtitle_dir, metadata_dir = _prepare_project_layout(
-        job, tmp_path
-    )
-
-    assert project_root.name.startswith(
-        "20250101-120000_Sample_Title"
-    ), project_root.name
-    assert audio_dir == project_root
-    assert subtitle_dir == project_root
-    assert metadata_dir is None
-
-    output_path = _build_output_path(audio_dir, job.original_filename, "mp3")
-    assert output_path == project_root / "Sample_Title.mp3"
 
 
-def test_prepare_project_layout_creates_project_subdirs(
+class TestSanitizeOutputStem:
-    monkeypatch: pytest.MonkeyPatch, tmp_path: Path
+    """sanitize_output_stem cleans filename stem."""
-) -> None:
-    job = _sample_job(tmp_path)
-    job.save_as_project = True
-    monkeypatch.setattr(
-        "abogen.webui.conversion_runner._output_timestamp_token",
-        lambda: "20250101-120500",
-    )
 
-    project_root, audio_dir, subtitle_dir, metadata_dir = _prepare_project_layout(
+    def test_basic_sanitize(self):
-        job, tmp_path
+        from abogen.domain.output_paths import sanitize_output_stem
-    )
 
-    assert audio_dir == project_root / "audio"
+        assert sanitize_output_stem("my file.mp3") == "my_file"
-    assert subtitle_dir == project_root / "subtitles"
-    assert metadata_dir == project_root / "metadata"
-    assert audio_dir.is_dir()
-    assert subtitle_dir.is_dir()
-    assert metadata_dir is not None and metadata_dir.is_dir()
 
-    output_path = _build_output_path(audio_dir, job.original_filename, "wav")
+    def test_empty_returns_default(self):
-    assert output_path == audio_dir / "Sample_Title.wav"
+        from abogen.domain.output_paths import sanitize_output_stem
+
+        assert sanitize_output_stem("") == "output"
+
+    def test_strips_underscores(self):
+        from abogen.domain.output_paths import sanitize_output_stem
+
+        assert sanitize_output_stem("__test__") == "test"
+
+
+# ---------------------------------------------------------------------------
+# output_timestamp_token
+# ---------------------------------------------------------------------------
+
+
+class TestOutputTimestampToken:
+    """output_timestamp_token returns timestamp string."""
+
+    def test_format(self):
+        from abogen.domain.output_paths import output_timestamp_token
+
+        token = output_timestamp_token()
+        assert re.match(r"\d{8}-\d{6}", token)
+
+
+# ---------------------------------------------------------------------------
+# build_output_path
+# ---------------------------------------------------------------------------
+
+
+class TestBuildOutputPath:
+    """build_output_path builds the output file path."""
+
+    def test_basic_path(self, tmp_path):
+        from abogen.domain.output_paths import build_output_path
+
+        result = build_output_path(tmp_path, "test.mp3", "mp3")
+        assert result.suffix == ".mp3"
+        assert result.parent == tmp_path
+
+    def test_stem_sanitized(self, tmp_path):
+        from abogen.domain.output_paths import build_output_path
+
+        result = build_output_path(tmp_path, "my file.txt", "wav")
+        assert "my_file" in result.name
+
+
+# ---------------------------------------------------------------------------
+# apply_newline_policy
+# ---------------------------------------------------------------------------
+
+
+class TestApplyNewlinePolicy:
+    """apply_newline_policy replaces single newlines in chapter text."""
+
+    def test_noop_when_disabled(self):
+        from abogen.domain.output_paths import apply_newline_policy
+
+        from abogen.text_extractor import ExtractedChapter
+        chapters = [ExtractedChapter(title="t", text="a\nb")]
+        apply_newline_policy(chapters, False)
+        assert chapters[0].text == "a\nb"
+
+    def test_replaces_single_newlines(self):
+        from abogen.domain.output_paths import apply_newline_policy
+
+        from abogen.text_extractor import ExtractedChapter
+        chapters = [ExtractedChapter(title="t", text="a\nb\nc")]
+        apply_newline_policy(chapters, True)
+        assert chapters[0].text == "a b c"
+
+    def test_preserves_double_newlines(self):
+        from abogen.domain.output_paths import apply_newline_policy
+
+        from abogen.text_extractor import ExtractedChapter
+        chapters = [ExtractedChapter(title="t", text="a\n\nb")]
+        apply_newline_policy(chapters, True)
+        assert chapters[0].text == "a\n\nb"
+
+
+# ---------------------------------------------------------------------------
+# resolve_output_directory
+# ---------------------------------------------------------------------------
+
+
+class TestResolveOutputDirectory:
+    """resolve_output_directory determines output dir from save_mode."""
+
+    def test_save_to_desktop(self, tmp_path):
+        from abogen.domain.output_paths import resolve_output_directory
+
+        result = resolve_output_directory(
+            save_mode="Save to Desktop",
+            stored_path=Path("/input/book.epub"),
+            output_folder=None,
+            desktop_dir=tmp_path,
+            user_output_path=None,
+            user_cache_outputs=None,
+        )
+        assert result == tmp_path
+
+    def test_save_next_to_input(self, tmp_path):
+        from abogen.domain.output_paths import resolve_output_directory
+
+        stored = tmp_path / "book.epub"
+        result = resolve_output_directory(
+            save_mode="Save next to input file",
+            stored_path=stored,
+            output_folder=None,
+            desktop_dir=None,
+            user_output_path=None,
+            user_cache_outputs=None,
+        )
+        assert result == tmp_path
+
+    def test_choose_output_folder(self, tmp_path):
+        from abogen.domain.output_paths import resolve_output_directory
+
+        custom = tmp_path / "custom"
+        result = resolve_output_directory(
+            save_mode="Choose output folder",
+            stored_path=Path("/x/y.epub"),
+            output_folder=str(custom),
+            desktop_dir=None,
+            user_output_path=None,
+            user_cache_outputs=None,
+        )
+        assert result == custom
+
+    def test_use_default_save_location(self, tmp_path):
+        from abogen.domain.output_paths import resolve_output_directory
+
+        result = resolve_output_directory(
+            save_mode="Use default save location",
+            stored_path=Path("/x/y.epub"),
+            output_folder=None,
+            desktop_dir=None,
+            user_output_path=tmp_path / "default",
+            user_cache_outputs=None,
+        )
+        assert result == tmp_path / "default"
+
+    def test_fallback_to_cache(self, tmp_path):
+        from abogen.domain.output_paths import resolve_output_directory
+
+        result = resolve_output_directory(
+            save_mode="unknown",
+            stored_path=Path("/x/y.epub"),
+            output_folder=None,
+            desktop_dir=None,
+            user_output_path=None,
+            user_cache_outputs=tmp_path / "cache",
+        )
+        assert result == tmp_path / "cache"
+
+
+# ---------------------------------------------------------------------------
+# resolve_project_layout
+# ---------------------------------------------------------------------------
+
+
+class TestResolveProjectLayout:
+    """resolve_project_layout computes project folder structure."""
+
+    def test_flat_layout(self, tmp_path):
+        from abogen.domain.output_paths import resolve_project_layout
+
+        root, audio, subs, meta = resolve_project_layout(
+            original_filename="book.epub",
+            save_as_project=False,
+            base_dir=tmp_path,
+            timestamp_fn=lambda: "20260101-000000",
+            sanitize_fn=lambda n, i: "book",
+        )
+        assert audio == root
+        assert subs == root
+        assert meta is None
+
+    def test_project_layout(self, tmp_path):
+        from abogen.domain.output_paths import resolve_project_layout
+
+        root, audio, subs, meta = resolve_project_layout(
+            original_filename="book.epub",
+            save_as_project=True,
+            base_dir=tmp_path,
+            timestamp_fn=lambda: "20260101-000000",
+            sanitize_fn=lambda n, i: "book",
+        )
+        assert root.name == "20260101-000000_book"
+        assert audio.name == "audio"
+        assert subs.name == "subtitles"
+        assert meta.name == "metadata"

tests/test_pronunciation.py

@@ -0,0 +1,334 @@
+"""Tests for abogen.domain.pronunciation — compile/apply pronunciation rules."""
+
+from __future__ import annotations
+
+import re
+import pytest
+
+
+# ---------------------------------------------------------------------------
+# We import the domain functions.  The module must be created first.
+# For now the tests are written against the expected public API so they can
+# serve as the contract during extraction.
+# ---------------------------------------------------------------------------
+
+
+class TestCompilePronunciationRules:
+    """compile_pronunciation_rules turns override dicts into regex-based rules."""
+
+    def test_empty_input(self):
+        from abogen.domain.pronunciation import compile_pronunciation_rules
+
+        assert compile_pronunciation_rules(None) == []
+        assert compile_pronunciation_rules([]) == []
+
+    def test_single_entry(self):
+        from abogen.domain.pronunciation import compile_pronunciation_rules
+
+        overrides = [{"token": "albeit", "pronunciation": "all be it"}]
+        rules = compile_pronunciation_rules(overrides)
+        assert len(rules) == 1
+        assert rules[0]["replacement"] == "all be it"
+        assert rules[0]["pattern"].search("albeit")
+
+    def test_skips_entries_without_pronunciation(self):
+        from abogen.domain.pronunciation import compile_pronunciation_rules
+
+        overrides = [{"token": "hello"}]
+        assert compile_pronunciation_rules(overrides) == []
+
+    def test_skips_entries_without_token(self):
+        from abogen.domain.pronunciation import compile_pronunciation_rules
+
+        overrides = [{"pronunciation": "foo"}]
+        assert compile_pronunciation_rules(overrides) == []
+
+    def test_deduplication_by_casefold(self):
+        from abogen.domain.pronunciation import compile_pronunciation_rules
+
+        overrides = [
+            {"token": "Albeit", "pronunciation": "all be it"},
+            {"token": "ALBEIT", "pronunciation": "all be it"},
+        ]
+        rules = compile_pronunciation_rules(overrides)
+        assert len(rules) == 1
+
+    def test_longer_token_sorted_first(self):
+        from abogen.domain.pronunciation import compile_pronunciation_rules
+
+        overrides = [
+            {"token": "ice cream", "pronunciation": "ice cream"},
+            {"token": "ice", "pronunciation": "ais"},
+        ]
+        rules = compile_pronunciation_rules(overrides)
+        assert len(rules) == 2
+        assert len(rules[0]["token"]) >= len(rules[1]["token"])
+
+    def test_normalized_fallback_to_entity_token(self):
+        from abogen.domain.pronunciation import compile_pronunciation_rules
+
+        overrides = [{"normalized": "USA", "pronunciation": "you ess ay"}]
+        rules = compile_pronunciation_rules(overrides)
+        assert len(rules) == 1
+
+    def test_pattern_is_case_insensitive(self):
+        from abogen.domain.pronunciation import compile_pronunciation_rules
+
+        overrides = [{"token": "hello", "pronunciation": "hi"}]
+        rules = compile_pronunciation_rules(overrides)
+        assert rules[0]["pattern"].search("Hello")
+        assert rules[0]["pattern"].search("HELLO")
+
+    def test_non_mapping_items_skipped(self):
+        from abogen.domain.pronunciation import compile_pronunciation_rules
+
+        overrides = ["bad", None, 42]
+        assert compile_pronunciation_rules(overrides) == []
+
+
+class TestCompileHeteronymSentenceRules:
+    """compile_heteronym_sentence_rules builds sentence-level replacements."""
+
+    def test_empty_input(self):
+        from abogen.domain.pronunciation import compile_heteronym_sentence_rules
+
+        assert compile_heteronym_sentence_rules(None) == []
+        assert compile_heteronym_sentence_rules([]) == []
+
+    def test_basic_replacement(self):
+        from abogen.domain.pronunciation import compile_heteronym_sentence_rules
+
+        overrides = [
+            {
+                "sentence": "I read the book",
+                "choice": "past",
+                "options": [
+                    {"key": "present", "replacement_sentence": "I read the book"},
+                    {"key": "past", "replacement_sentence": "I read the book"},
+                ],
+            }
+        ]
+        rules = compile_heteronym_sentence_rules(overrides)
+        assert len(rules) == 1
+        assert rules[0]["replacement"] == "I read the book"
+
+    def test_skips_without_sentence(self):
+        from abogen.domain.pronunciation import compile_heteronym_sentence_rules
+
+        overrides = [{"choice": "a", "options": []}]
+        assert compile_heteronym_sentence_rules(overrides) == []
+
+    def test_skips_without_choice(self):
+        from abogen.domain.pronunciation import compile_heteronym_sentence_rules
+
+        overrides = [{"sentence": "hello", "options": []}]
+        assert compile_heteronym_sentence_rules(overrides) == []
+
+    def test_skips_when_no_matching_option(self):
+        from abogen.domain.pronunciation import compile_heteronym_sentence_rules
+
+        overrides = [
+            {
+                "sentence": "I read the book",
+                "choice": "past",
+                "options": [{"key": "present", "replacement_sentence": "I read the book"}],
+            }
+        ]
+        assert compile_heteronym_sentence_rules(overrides) == []
+
+    def test_deduplication(self):
+        from abogen.domain.pronunciation import compile_heteronym_sentence_rules
+
+        entry = {
+            "sentence": "I read the book",
+            "choice": "past",
+            "options": [{"key": "past", "replacement_sentence": "I red the book"}],
+        }
+        rules = compile_heteronym_sentence_rules([entry, entry])
+        assert len(rules) == 1
+
+    def test_longer_sentence_sorted_first(self):
+        from abogen.domain.pronunciation import compile_heteronym_sentence_rules
+
+        overrides = [
+            {
+                "sentence": "short",
+                "choice": "a",
+                "options": [{"key": "a", "replacement_sentence": "s"}],
+            },
+            {
+                "sentence": "a longer sentence here",
+                "choice": "b",
+                "options": [{"key": "b", "replacement_sentence": "l"}],
+            },
+        ]
+        rules = compile_heteronym_sentence_rules(overrides)
+        assert len(rules[0]["pattern"].pattern) >= len(rules[1]["pattern"].pattern)
+
+
+class TestApplyPronunciationRules:
+    """apply_pronunciation_rules applies compiled token-level rules."""
+
+    def test_empty_text(self):
+        from abogen.domain.pronunciation import apply_pronunciation_rules
+
+        assert apply_pronunciation_rules("", []) == ""
+
+    def test_no_rules(self):
+        from abogen.domain.pronunciation import apply_pronunciation_rules
+
+        assert apply_pronunciation_rules("hello", []) == "hello"
+
+    def test_basic_replacement(self):
+        from abogen.domain.pronunciation import compile_pronunciation_rules, apply_pronunciation_rules
+
+        rules = compile_pronunciation_rules([{"token": "albeit", "pronunciation": "all be it"}])
+        result = apply_pronunciation_rules("albeit it was raining", rules)
+        assert result == "all be it it was raining"
+
+    def test_possessive_preserved(self):
+        from abogen.domain.pronunciation import compile_pronunciation_rules, apply_pronunciation_rules
+
+        rules = compile_pronunciation_rules([{"token": "dog", "pronunciation": "dawg"}])
+        result = apply_pronunciation_rules("the dog's bone", rules)
+        assert result == "the dawg's bone"
+
+    def test_usage_counter_increments(self):
+        from abogen.domain.pronunciation import compile_pronunciation_rules, apply_pronunciation_rules
+
+        rules = compile_pronunciation_rules([{"token": "hello", "pronunciation": "hi"}])
+        counter: dict[str, int] = {}
+        apply_pronunciation_rules("hello hello", rules, usage_counter=counter)
+        assert counter.get("hello", 0) == 2
+
+    def test_case_insensitive_match(self):
+        from abogen.domain.pronunciation import compile_pronunciation_rules, apply_pronunciation_rules
+
+        rules = compile_pronunciation_rules([{"token": "test", "pronunciation": "tst"}])
+        result = apply_pronunciation_rules("This is a Test", rules)
+        assert "tst" in result.lower()
+
+
+class TestApplyHeteronymSentenceRules:
+    """apply_heteronym_sentence_rules applies sentence-level replacements."""
+
+    def test_empty_text(self):
+        from abogen.domain.pronunciation import apply_heteronym_sentence_rules
+
+        assert apply_heteronym_sentence_rules("", []) == ""
+
+    def test_no_rules(self):
+        from abogen.domain.pronunciation import apply_heteronym_sentence_rules
+
+        assert apply_heteronym_sentence_rules("hello", []) == "hello"
+
+    def test_basic_replacement(self):
+        from abogen.domain.pronunciation import (
+            compile_heteronym_sentence_rules,
+            apply_heteronym_sentence_rules,
+        )
+
+        rules = compile_heteronym_sentence_rules(
+            [
+                {
+                    "sentence": "I read the book",
+                    "choice": "past",
+                    "options": [{"key": "past", "replacement_sentence": "I read the book"}],
+                }
+            ]
+        )
+        result = apply_heteronym_sentence_rules("I read the book.", rules)
+        assert result == "I read the book."
+
+    def test_no_match_left_unchanged(self):
+        from abogen.domain.pronunciation import (
+            compile_heteronym_sentence_rules,
+            apply_heteronym_sentence_rules,
+        )
+
+        rules = compile_heteronym_sentence_rules(
+            [
+                {
+                    "sentence": "I read the book",
+                    "choice": "past",
+                    "options": [{"key": "past", "replacement_sentence": "I red the book"}],
+                }
+            ]
+        )
+        result = apply_heteronym_sentence_rules("something else entirely", rules)
+        assert result == "something else entirely"
+
+
+class TestMergePronunciationOverrides:
+    """merge_pronunciation_overrides consolidates override sources."""
+
+    def test_empty_job(self):
+        from abogen.domain.pronunciation import merge_pronunciation_overrides
+
+        class FakeJob:
+            pronunciation_overrides = None
+            speakers = None
+            manual_overrides = None
+            language = "en"
+
+        result = merge_pronunciation_overrides(FakeJob())
+        assert result == []
+
+    def test_pronunciation_overrides_included(self):
+        from abogen.domain.pronunciation import merge_pronunciation_overrides
+
+        class FakeJob:
+            pronunciation_overrides = [
+                {"token": "hello", "pronunciation": "hi", "normalized": "hello"}
+            ]
+            speakers = None
+            manual_overrides = None
+            language = "en"
+
+        result = merge_pronunciation_overrides(FakeJob())
+        assert len(result) == 1
+        assert result[0]["token"] == "hello"
+        assert result[0]["source"] == "pronunciation"
+
+    def test_manual_overrides_win(self):
+        from abogen.domain.pronunciation import merge_pronunciation_overrides
+
+        class FakeJob:
+            pronunciation_overrides = [
+                {"token": "hello", "pronunciation": "hi old", "normalized": "hello"}
+            ]
+            speakers = None
+            manual_overrides = [
+                {"token": "hello", "pronunciation": "hi new", "normalized": "hello"}
+            ]
+            language = "en"
+
+        result = merge_pronunciation_overrides(FakeJob())
+        assert len(result) == 1
+        assert result[0]["pronunciation"] == "hi new"
+        assert result[0]["source"] == "manual"
+
+    def test_speaker_entries_included(self):
+        from abogen.domain.pronunciation import merge_pronunciation_overrides
+
+        class FakeJob:
+            pronunciation_overrides = None
+            speakers = {"narrator": {"token": "war", "pronunciation": "wɔːr"}}
+            manual_overrides = None
+            language = "en"
+
+        result = merge_pronunciation_overrides(FakeJob())
+        assert len(result) == 1
+        assert result[0]["source"] == "speaker"
+
+    def test_skips_empty_tokens(self):
+        from abogen.domain.pronunciation import merge_pronunciation_overrides
+
+        class FakeJob:
+            pronunciation_overrides = [{"token": "", "pronunciation": "foo"}]
+            speakers = None
+            manual_overrides = None
+            language = "en"
+
+        result = merge_pronunciation_overrides(FakeJob())
+        assert result == []

tests/test_select_device.py

@@ -0,0 +1,94 @@
+import sys
+from unittest.mock import patch, MagicMock
+
+
+class TestSelectDevice:
+    """Tests for domain.device.select_device."""
+
+    def test_returns_mps_on_apple_silicon_when_available(self) -> None:
+        from abogen.domain.device import select_device
+
+        mock_platform = MagicMock()
+        mock_platform.system.return_value = "Darwin"
+        mock_platform.processor.return_value = "arm"
+
+        mock_torch = MagicMock()
+        mock_torch.backends.mps.is_available.return_value = True
+        mock_torch.cuda.is_available.return_value = False
+
+        with patch("abogen.domain.device._platform", mock_platform), \
+             patch.dict(sys.modules, {"torch": mock_torch}):
+            result = select_device()
+        assert result == "mps"
+
+    def test_returns_cpu_on_apple_silicon_when_mps_unavailable(self) -> None:
+        from abogen.domain.device import select_device
+
+        mock_platform = MagicMock()
+        mock_platform.system.return_value = "Darwin"
+        mock_platform.processor.return_value = "arm"
+
+        mock_torch = MagicMock()
+        mock_torch.backends.mps.is_available.return_value = False
+        mock_torch.cuda.is_available.return_value = False
+
+        with patch("abogen.domain.device._platform", mock_platform), \
+             patch.dict(sys.modules, {"torch": mock_torch}):
+            result = select_device()
+        assert result == "cpu"
+
+    def test_returns_cuda_when_available(self) -> None:
+        from abogen.domain.device import select_device
+
+        mock_platform = MagicMock()
+        mock_platform.system.return_value = "Linux"
+        mock_platform.processor.return_value = "x86_64"
+
+        mock_torch = MagicMock()
+        mock_torch.backends.mps.is_available.return_value = False
+        mock_torch.cuda.is_available.return_value = True
+
+        with patch("abogen.domain.device._platform", mock_platform), \
+             patch.dict(sys.modules, {"torch": mock_torch}):
+            result = select_device()
+        assert result == "cuda"
+
+    def test_returns_cpu_when_cuda_unavailable(self) -> None:
+        from abogen.domain.device import select_device
+
+        mock_platform = MagicMock()
+        mock_platform.system.return_value = "Linux"
+        mock_platform.processor.return_value = "x86_64"
+
+        mock_torch = MagicMock()
+        mock_torch.backends.mps.is_available.return_value = False
+        mock_torch.cuda.is_available.return_value = False
+
+        with patch("abogen.domain.device._platform", mock_platform), \
+             patch.dict(sys.modules, {"torch": mock_torch}):
+            result = select_device()
+        assert result == "cpu"
+
+    def test_returns_cpu_when_torch_not_installed(self) -> None:
+        from abogen.domain.device import select_device
+
+        mock_platform = MagicMock()
+        mock_platform.system.return_value = "Linux"
+        mock_platform.processor.return_value = "x86_64"
+
+        with patch("abogen.domain.device._platform", mock_platform), \
+             patch.dict(sys.modules, {"torch": None}):
+            result = select_device()
+        assert result == "cpu"
+
+    def test_handles_torch_import_error(self) -> None:
+        from abogen.domain.device import select_device
+
+        mock_platform = MagicMock()
+        mock_platform.system.return_value = "Windows"
+        mock_platform.processor.return_value = "AMD64"
+
+        with patch("abogen.domain.device._platform", mock_platform), \
+             patch.dict(sys.modules, {"torch": None}):
+            result = select_device()
+        assert result == "cpu"

tests/test_split_pattern.py

@@ -0,0 +1,101 @@
+"""Tests for split pattern logic (3 identical copies in codebase)."""
+import os
+import sys
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
+
+import pytest
+
+from abogen.domain.split_pattern import get_split_pattern
+
+
+# --- English always returns \n ---
+
+class TestEnglish:
+    def test_english_sentence(self):
+        assert get_split_pattern("a", "Sentence") == "\n"
+
+    def test_english_sentence_comma(self):
+        assert get_split_pattern("a", "Sentence + Comma") == "\n"
+
+    def test_english_line(self):
+        assert get_split_pattern("a", "Line") == "\n"
+
+    def test_english_disabled(self):
+        assert get_split_pattern("a", "Disabled") == "\n"
+
+    def test_english_b(self):
+        assert get_split_pattern("b", "Sentence") == "\n"
+
+
+# --- CJK languages ---
+
+class TestCJK:
+    def test_chinese_disabled(self):
+        pattern = get_split_pattern("z", "Disabled")
+        assert pattern != "\n"
+        assert r"\n+" in pattern
+
+    def test_chinese_line(self):
+        pattern = get_split_pattern("z", "Line")
+        assert pattern != "\n"
+        assert r"\n+" in pattern
+
+    def test_chinese_sentence(self):
+        pattern = get_split_pattern("z", "Sentence")
+        assert r"\n+" in pattern
+
+    def test_chinese_sentence_comma(self):
+        pattern = get_split_pattern("z", "Sentence + Comma")
+        assert r"\n+" in pattern
+
+    def test_japanese_disabled(self):
+        pattern = get_split_pattern("j", "Disabled")
+        assert pattern != "\n"
+        assert r"\n+" in pattern
+
+    def test_japanese_sentence(self):
+        pattern = get_split_pattern("j", "Sentence")
+        assert r"\n+" in pattern
+
+
+# --- Other languages ---
+
+class TestOtherLanguages:
+    def test_spanish_sentence(self):
+        pattern = get_split_pattern("e", "Sentence")
+        assert r"\n+" in pattern
+
+    def test_spanish_line(self):
+        assert get_split_pattern("e", "Line") == "\n"
+
+    def test_spanish_disabled(self):
+        # canonical: \n+ for non-CJK Disabled
+        assert get_split_pattern("e", "Disabled") == r"\n+"
+
+    def test_french_sentence_comma(self):
+        pattern = get_split_pattern("f", "Sentence + Comma")
+        assert r"\n+" in pattern
+
+    def test_unknown_lang(self):
+        pattern = get_split_pattern("x", "Sentence")
+        assert r"\n+" in pattern
+
+
+# --- Pattern structure ---
+
+class TestPatternStructure:
+    def test_sentence_has_lookbehind(self):
+        pattern = get_split_pattern("e", "Sentence")
+        assert r"(?<=" in pattern
+
+    def test_sentence_comma_has_comma_chars(self):
+        pattern = get_split_pattern("e", "Sentence + Comma")
+        assert "," in pattern
+
+    def test_cjk_spacing_uses_star(self):
+        pattern = get_split_pattern("z", "Sentence")
+        assert r"\s*" in pattern
+
+    def test_non_cjk_spacing_uses_plus(self):
+        pattern = get_split_pattern("e", "Sentence")
+        assert r"\s+" in pattern

tests/test_subtitle_writer.py

@@ -0,0 +1,264 @@
+"""Tests for infrastructure/subtitle_writer.py — SrtWriter, AssWriter, VttWriter."""
+from __future__ import annotations
+
+import pytest
+from pathlib import Path
+
+from abogen.infrastructure.subtitle_writer import (
+    AssWriter,
+    SrtWriter,
+    SubtitleAlignment,
+    SubtitleConfig,
+    SubtitleFormat,
+    SubtitleMode,
+    VttWriter,
+    create_subtitle_writer,
+)
+
+
+# ===================================================================
+# SrtWriter._format_time
+# ===================================================================
+
+class TestSrtFormatTime:
+    def test_zero(self):
+        assert SrtWriter._format_time(0.0) == "00:00:00,000"
+
+    def test_simple(self):
+        assert SrtWriter._format_time(61.5) == "00:01:01,500"
+
+    def test_hours(self):
+        assert SrtWriter._format_time(3661.123) == "01:01:01,123"
+
+    def test_large(self):
+        assert SrtWriter._format_time(7384.0) == "02:03:04,000"
+
+    def test_fractional_seconds(self):
+        assert SrtWriter._format_time(0.999) == "00:00:00,999"
+
+    def test_matches_old_format_timestamp(self):
+        """Verify matches old _format_timestamp(ass=False) from conversion_runner."""
+        import math
+        for t in [0.0, 61.5, 3661.123, 7384.0, 0.999, 125.7]:
+            h = int(t // 3600)
+            m = int((t % 3600) // 60)
+            s = int(t % 60)
+            ms = int((t - math.floor(t)) * 1000)
+            expected = f"{h:02d}:{m:02d}:{s:02d},{ms:03d}"
+            assert SrtWriter._format_time(t) == expected, f"Mismatch at t={t}"
+
+
+# ===================================================================
+# AssWriter._format_time
+# ===================================================================
+
+class TestAssFormatTime:
+    def test_zero(self):
+        assert AssWriter._format_time(0.0) == "0:00:00.00"
+
+    def test_simple(self):
+        assert AssWriter._format_time(61.5) == "0:01:01.50"
+
+    def test_hours(self):
+        assert AssWriter._format_time(3661.12) == "1:01:01.12"
+
+    def test_centiseconds(self):
+        assert AssWriter._format_time(1.55) == "0:00:01.55"
+
+    def test_matches_old_format_timestamp_ass(self):
+        """Verify matches old _format_timestamp(ass=True) from conversion_runner.
+
+        Note: the old code used int(milliseconds/10) which truncates centiseconds,
+        while the new code uses float formatting which rounds. For most values they
+        match; the difference is at most 1 centisecond due to float precision.
+        """
+        import math
+        for t in [0.0, 61.5, 1.55, 125.7]:
+            h = int(t // 3600)
+            m = int((t % 3600) // 60)
+            s = int(t % 60)
+            ms = int((t - math.floor(t)) * 1000)
+            cs = int(ms / 10)
+            expected = f"{h:01d}:{m:02d}:{s:02d}.{cs:02d}"
+            assert AssWriter._format_time(t) == expected, f"Mismatch at t={t}"
+
+
+# ===================================================================
+# SrtWriter full write
+# ===================================================================
+
+class TestSrtWriter:
+    def test_single_entry(self, tmp_path):
+        path = tmp_path / "test.srt"
+        writer = SrtWriter(path, SubtitleConfig(format=SubtitleFormat.SRT, mode=SubtitleMode.LINE))
+        writer.write_entry(start=0.0, end=2.5, text="Hello")
+        writer.close()
+        content = path.read_text()
+        assert "1\n" in content
+        assert "00:00:00,000 --> 00:00:02,500" in content
+        assert "Hello\n" in content
+
+    def test_multiple_entries(self, tmp_path):
+        path = tmp_path / "test.srt"
+        writer = SrtWriter(path, SubtitleConfig(format=SubtitleFormat.SRT, mode=SubtitleMode.LINE))
+        writer.write_entry(start=0.0, end=1.0, text="First")
+        writer.write_entry(start=1.0, end=2.0, text="Second")
+        writer.close()
+        content = path.read_text()
+        assert "1\n" in content
+        assert "2\n" in content
+        assert "First" in content
+        assert "Second" in content
+
+    def test_voice_prefix(self, tmp_path):
+        path = tmp_path / "test.srt"
+        writer = SrtWriter(path, SubtitleConfig(format=SubtitleFormat.SRT, mode=SubtitleMode.LINE))
+        writer.write_entry(start=0.0, end=1.0, text="Hello", voice="af_heart")
+        writer.close()
+        content = path.read_text()
+        assert "[af_heart] Hello" in content
+
+    def test_auto_index(self, tmp_path):
+        path = tmp_path / "test.srt"
+        writer = SrtWriter(path, SubtitleConfig(format=SubtitleFormat.SRT, mode=SubtitleMode.LINE))
+        writer.write_entry(start=0.0, end=1.0, text="A")
+        writer.write_entry(start=1.0, end=2.0, text="B")
+        writer.write_entry(start=2.0, end=3.0, text="C")
+        writer.close()
+        content = path.read_text()
+        assert "1\n" in content
+        assert "2\n" in content
+        assert "3\n" in content
+
+
+# ===================================================================
+# AssWriter full write
+# ===================================================================
+
+class TestAssWriter:
+    def test_header_structure(self, tmp_path):
+        path = tmp_path / "test.ass"
+        writer = AssWriter(path, SubtitleConfig(format=SubtitleFormat.ASS, mode=SubtitleMode.LINE))
+        writer.open()
+        writer.close()
+        content = path.read_text()
+        assert "[Script Info]" in content
+        assert "[V4+ Styles]" in content
+        assert "[Events]" in content
+        assert "Format: Layer, Start, End" in content
+
+    def test_single_entry(self, tmp_path):
+        path = tmp_path / "test.ass"
+        writer = AssWriter(path, SubtitleConfig(format=SubtitleFormat.ASS, mode=SubtitleMode.LINE))
+        writer.write_entry(start=0.0, end=2.5, text="Hello")
+        writer.close()
+        content = path.read_text()
+        assert "Dialogue:" in content
+        assert "Hello" in content
+
+    def test_voice_prefix(self, tmp_path):
+        path = tmp_path / "test.ass"
+        writer = AssWriter(path, SubtitleConfig(format=SubtitleFormat.ASS, mode=SubtitleMode.LINE))
+        writer.write_entry(start=0.0, end=1.0, text="Hello", voice="af_heart")
+        writer.close()
+        content = path.read_text()
+        assert "[af_heart] Hello" in content
+
+    def test_highlight_mode(self, tmp_path):
+        path = tmp_path / "test.ass"
+        config = SubtitleConfig(
+            format=SubtitleFormat.ASS,
+            mode=SubtitleMode.SENTENCE_HIGHLIGHT,
+        )
+        writer = AssWriter(path, config)
+        writer.write_entry(start=0.0, end=1.0, text="Hello world")
+        writer.close()
+        content = path.read_text()
+        assert "Highlight" in content
+        assert r"{\k100}" in content
+
+    def test_centered_alignment(self, tmp_path):
+        path = tmp_path / "test.ass"
+        config = SubtitleConfig(
+            format=SubtitleFormat.ASS,
+            mode=SubtitleMode.LINE,
+            alignment=SubtitleAlignment.CENTER,
+        )
+        writer = AssWriter(path, config)
+        writer.open()
+        writer.close()
+        content = path.read_text()
+        # Centered uses alignment=5
+        assert ",5," in content or ",5\n" in content
+
+
+# ===================================================================
+# VttWriter
+# ===================================================================
+
+class TestVttWriter:
+    def test_header(self, tmp_path):
+        path = tmp_path / "test.vtt"
+        writer = VttWriter(path, SubtitleConfig(format=SubtitleFormat.VTT, mode=SubtitleMode.LINE))
+        writer.open()
+        writer.close()
+        content = path.read_text()
+        assert content.startswith("WEBVTT")
+
+    def test_single_entry(self, tmp_path):
+        path = tmp_path / "test.vtt"
+        writer = VttWriter(path, SubtitleConfig(format=SubtitleFormat.VTT, mode=SubtitleMode.LINE))
+        writer.write_entry(start=0.0, end=2.5, text="Hello")
+        writer.close()
+        content = path.read_text()
+        assert "1\n" in content
+        assert "Hello" in content
+
+
+# ===================================================================
+# create_subtitle_writer factory
+# ===================================================================
+
+class TestCreateSubtitleWriter:
+    def test_srt(self, tmp_path):
+        path = tmp_path / "test.srt"
+        writer = create_subtitle_writer(path, "srt", "Line")
+        assert isinstance(writer, SrtWriter)
+        writer.close()
+
+    def test_ass(self, tmp_path):
+        path = tmp_path / "test.ass"
+        writer = create_subtitle_writer(path, "ass", "Line")
+        assert isinstance(writer, AssWriter)
+        writer.close()
+
+    def test_vtt(self, tmp_path):
+        path = tmp_path / "test.vtt"
+        writer = create_subtitle_writer(path, "vtt", "Line")
+        assert isinstance(writer, VttWriter)
+        writer.close()
+
+    def test_unsupported_raises(self, tmp_path):
+        path = tmp_path / "test.xyz"
+        with pytest.raises(ValueError):
+            create_subtitle_writer(path, "xyz", "Line")
+
+
+# ===================================================================
+# Context manager
+# ===================================================================
+
+class TestContextManager:
+    def test_srt_context_manager(self, tmp_path):
+        path = tmp_path / "test.srt"
+        with SrtWriter(path, SubtitleConfig(format=SubtitleFormat.SRT, mode=SubtitleMode.LINE)) as writer:
+            writer.write_entry(start=0.0, end=1.0, text="Hello")
+        content = path.read_text()
+        assert "Hello" in content
+
+    def test_ass_context_manager(self, tmp_path):
+        path = tmp_path / "test.ass"
+        with AssWriter(path, SubtitleConfig(format=SubtitleFormat.ASS, mode=SubtitleMode.LINE)) as writer:
+            writer.write_entry(start=0.0, end=1.0, text="Hello")
+        content = path.read_text()
+        assert "Dialogue:" in content

tests/test_title_builder.py

@@ -0,0 +1,59 @@
+"""Tests for domain/title_builder.py."""
+import sys
+import os
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
+
+from abogen.domain.title_builder import build_title_intro_text, build_outro_text
+
+
+class TestBuildTitleIntroText:
+    def test_empty_metadata(self):
+        result = build_title_intro_text({}, "book.epub")
+        assert result == "book."
+
+    def test_title_from_metadata(self):
+        result = build_title_intro_text({"title": "My Book"}, "book.epub")
+        assert result == "My Book."
+
+    def test_title_fallback_basename(self):
+        result = build_title_intro_text({}, "my_book.epub")
+        assert result == "my_book."
+
+    def test_with_author(self):
+        result = build_title_intro_text({"title": "My Book", "author": "John Doe"}, "book.epub")
+        assert result == "My Book. By John Doe."
+
+    def test_with_subtitle(self):
+        result = build_title_intro_text({"title": "My Book", "subtitle": "A Tale"}, "book.epub")
+        assert result == "My Book. A Tale."
+
+    def test_duplicate_title_subtitle(self):
+        result = build_title_intro_text({"title": "My Book", "subtitle": "My Book"}, "book.epub")
+        assert result == "My Book."
+
+    def test_with_series(self):
+        result = build_title_intro_text({"title": "My Book", "series": "Series", "series_index": "3"}, "book.epub")
+        assert result == "Book 3 of the Series. My Book."
+
+
+class TestBuildOutroText:
+    def test_empty(self):
+        result = build_outro_text({}, "book.epub")
+        assert result == "The end of book."
+
+    def test_title_only(self):
+        result = build_outro_text({"title": "My Book"}, "book.epub")
+        assert result == "The end of My Book."
+
+    def test_author_only(self):
+        result = build_outro_text({"author": "John Doe"}, "book.epub")
+        assert result == "The end of book from John Doe."
+
+    def test_title_and_author(self):
+        result = build_outro_text({"title": "My Book", "author": "John Doe"}, "book.epub")
+        assert result == "The end of My Book from John Doe."
+
+    def test_with_series(self):
+        result = build_outro_text({"title": "My Book", "series": "Series", "series_index": "3"}, "book.epub")
+        assert "The end of My Book." in result
+        assert "Book 3 of the Series." in result

tests/test_voice_fallback.py

@@ -0,0 +1,139 @@
+import sys
+import types
+
+if "soundfile" not in sys.modules:
+    soundfile_stub = types.ModuleType("soundfile")
+
+    class _SoundFileStub:  # pragma: no cover - placeholder to satisfy imports
+        def __init__(self, *args: object, **kwargs: object) -> None:
+            raise RuntimeError("soundfile is not installed in the test environment")
+
+    soundfile_stub.SoundFile = _SoundFileStub  # type: ignore[attr-defined]
+    sys.modules["soundfile"] = soundfile_stub
+
+if "static_ffmpeg" not in sys.modules:
+    sys.modules["static_ffmpeg"] = types.ModuleType("static_ffmpeg")
+
+if "ebooklib" not in sys.modules:
+    ebooklib_stub = types.ModuleType("ebooklib")
+    ebooklib_epub_stub = types.ModuleType("ebooklib.epub")
+    ebooklib_stub.epub = ebooklib_epub_stub  # type: ignore[attr-defined]
+    sys.modules["ebooklib"] = ebooklib_stub
+    sys.modules["ebooklib.epub"] = ebooklib_epub_stub
+
+if "fitz" not in sys.modules:
+    sys.modules["fitz"] = types.ModuleType("fitz")
+
+if "markdown" not in sys.modules:
+    markdown_stub = types.ModuleType("markdown")
+
+    class _MarkdownStub:
+        def __init__(self, *args: object, **kwargs: object) -> None:
+            self.toc_tokens = []
+
+        def convert(self, text: str) -> str:
+            return text
+
+    markdown_stub.Markdown = _MarkdownStub  # type: ignore[attr-defined]
+    sys.modules["markdown"] = markdown_stub
+
+if "bs4" not in sys.modules:
+    bs4_stub = types.ModuleType("bs4")
+
+    class _BeautifulSoupStub:
+        def __init__(self, *args: object, **kwargs: object) -> None:
+            self._text = ""
+
+        def find(self, *args: object, **kwargs: object) -> None:
+            return None
+
+        def get_text(self) -> str:
+            return self._text
+
+        def decompose(self) -> None:  # pragma: no cover - compatibility shim
+            return None
+
+    class _NavigableStringStub(str):
+        pass
+
+    bs4_stub.BeautifulSoup = _BeautifulSoupStub  # type: ignore[attr-defined]
+    bs4_stub.NavigableString = _NavigableStringStub  # type: ignore[attr-defined]
+    sys.modules["bs4"] = bs4_stub
+
+
+from unittest.mock import patch, MagicMock
+
+
+class TestResolveFallbackVoiceSpec:
+    """Tests for the voice fallback resolution helper."""
+
+    def test_uses_base_voice_spec(self) -> None:
+        from abogen.domain.voice_resolution import resolve_fallback_voice_spec
+
+        result = resolve_fallback_voice_spec(
+            base_spec="af_heart",
+            job_voice="af_bella",
+            voice_cache_keys=[],
+        )
+        assert result == "af_heart"
+
+    def test_falls_back_to_job_voice(self) -> None:
+        from abogen.domain.voice_resolution import resolve_fallback_voice_spec
+
+        result = resolve_fallback_voice_spec(
+            base_spec="",
+            job_voice="af_bella",
+            voice_cache_keys=[],
+        )
+        assert result == "af_bella"
+
+    def test_skips_custom_mix_uses_job_voice(self) -> None:
+        from abogen.domain.voice_resolution import resolve_fallback_voice_spec
+
+        result = resolve_fallback_voice_spec(
+            base_spec="__custom_mix",
+            job_voice="af_bella",
+            voice_cache_keys=[],
+        )
+        assert result == "af_bella"
+
+    def test_falls_back_to_voice_cache(self) -> None:
+        from abogen.domain.voice_resolution import resolve_fallback_voice_spec
+
+        result = resolve_fallback_voice_spec(
+            base_spec="",
+            job_voice="",
+            voice_cache_keys=["kokoro:af_heart"],
+        )
+        assert result == "af_heart"
+
+    def test_skips_custom_mix_in_cache(self) -> None:
+        from abogen.domain.voice_resolution import resolve_fallback_voice_spec
+
+        result = resolve_fallback_voice_spec(
+            base_spec="",
+            job_voice="",
+            voice_cache_keys=["__custom_mix", "kokoro:af_heart"],
+        )
+        assert result == "af_heart"
+
+    def test_falls_back_to_default_voice(self) -> None:
+        from abogen.domain.voice_resolution import resolve_fallback_voice_spec
+
+        with patch("abogen.domain.voice_resolution.get_default_voice", return_value="af_heart"):
+            result = resolve_fallback_voice_spec(
+                base_spec="",
+                job_voice="",
+                voice_cache_keys=[],
+            )
+        assert result == "af_heart"
+
+    def test_empty_base_and_job_with_cache(self) -> None:
+        from abogen.domain.voice_resolution import resolve_fallback_voice_spec
+
+        result = resolve_fallback_voice_spec(
+            base_spec="",
+            job_voice="",
+            voice_cache_keys=["kokoro:af_bella", "kokoro:af_heart"],
+        )
+        assert result == "af_bella"

tests/test_voice_resolution.py

@@ -0,0 +1,274 @@
+"""Tests for voice resolution helpers.
+
+Tests import from domain.voice_resolution (new location).
+"""
+
+from __future__ import annotations
+
+from types import SimpleNamespace
+from typing import Any, Dict
+from unittest.mock import patch
+
+import pytest
+
+
+# ---------------------------------------------------------------------------
+# spec_to_voice_ids
+# ---------------------------------------------------------------------------
+
+
+class TestSpecToVoiceIds:
+    """spec_to_voice_ids extracts voice identifiers from a spec string."""
+
+    def test_empty_string(self):
+        from abogen.domain.voice_resolution import spec_to_voice_ids
+
+        assert spec_to_voice_ids("") == set()
+
+    def test_none(self):
+        from abogen.domain.voice_resolution import spec_to_voice_ids
+
+        assert spec_to_voice_ids(None) == set()
+
+    def test_custom_mix_returns_empty(self):
+        from abogen.domain.voice_resolution import spec_to_voice_ids
+
+        assert spec_to_voice_ids("__custom_mix") == set()
+
+    def test_single_known_voice(self):
+        from abogen.domain.voice_resolution import spec_to_voice_ids
+
+        with patch("abogen.domain.voice_resolution.get_voices", return_value={"af_heart"}):
+            assert spec_to_voice_ids("af_heart") == {"af_heart"}
+
+    def test_unknown_single_voice_returns_empty(self):
+        from abogen.domain.voice_resolution import spec_to_voice_ids
+
+        with patch("abogen.domain.voice_resolution.get_voices", return_value=set()):
+            assert spec_to_voice_ids("nonexistent") == set()
+
+    def test_formula_with_star(self):
+        from abogen.domain.voice_resolution import spec_to_voice_ids
+
+        with patch("abogen.domain.voice_resolution.extract_voice_ids", return_value=["v1", "v2"]):
+            result = spec_to_voice_ids("v1*v2")
+            assert result == {"v1", "v2"}
+
+    def test_formula_value_error_returns_empty(self):
+        from abogen.domain.voice_resolution import spec_to_voice_ids
+
+        with patch("abogen.domain.voice_resolution.extract_voice_ids", side_effect=ValueError("bad")):
+            assert spec_to_voice_ids("bad*spec") == set()
+
+    def test_whitespace_stripped(self):
+        from abogen.domain.voice_resolution import spec_to_voice_ids
+
+        assert spec_to_voice_ids("  ") == set()
+
+
+# ---------------------------------------------------------------------------
+# job_voice_fallback
+# ---------------------------------------------------------------------------
+
+
+class TestJobVoiceFallback:
+    """job_voice_fallback resolves a fallback voice from job attributes."""
+
+    def test_direct_voice(self):
+        from abogen.domain.voice_resolution import job_voice_fallback
+
+        job = SimpleNamespace(voice="af_heart", speakers=None, chapters=[])
+        assert job_voice_fallback(job) == "af_heart"
+
+    def test_custom_mix_ignored(self):
+        from abogen.domain.voice_resolution import job_voice_fallback
+
+        job = SimpleNamespace(voice="__custom_mix", speakers=None, chapters=[])
+        assert job_voice_fallback(job) == ""
+
+    def test_narrator_speaker(self):
+        from abogen.domain.voice_resolution import job_voice_fallback
+
+        job = SimpleNamespace(
+            voice="__custom_mix",
+            speakers={"narrator": {"resolved_voice": "af_heart"}},
+            chapters=[],
+        )
+        assert job_voice_fallback(job) == "af_heart"
+
+    def test_speaker_voice_formula(self):
+        from abogen.domain.voice_resolution import job_voice_fallback
+
+        job = SimpleNamespace(
+            voice="",
+            speakers={"speaker1": {"voice_formula": "v1*v2"}},
+            chapters=[],
+        )
+        assert job_voice_fallback(job) == "v1*v2"
+
+    def test_chapter_voice(self):
+        from abogen.domain.voice_resolution import job_voice_fallback
+
+        job = SimpleNamespace(
+            voice="",
+            speakers=None,
+            chapters=[{"resolved_voice": "af_bella"}],
+        )
+        assert job_voice_fallback(job) == "af_bella"
+
+    def test_empty_job(self):
+        from abogen.domain.voice_resolution import job_voice_fallback
+
+        job = SimpleNamespace(voice="", speakers=None, chapters=[])
+        assert job_voice_fallback(job) == ""
+
+    def test_narrator_custom_mix_falls_through(self):
+        from abogen.domain.voice_resolution import job_voice_fallback
+
+        job = SimpleNamespace(
+            voice="",
+            speakers={"narrator": {"voice": "__custom_mix"}},
+            chapters=[{"voice": "af_heart"}],
+        )
+        assert job_voice_fallback(job) == "af_heart"
+
+
+# ---------------------------------------------------------------------------
+# chapter_voice_spec
+# ---------------------------------------------------------------------------
+
+
+class TestChapterVoiceSpec:
+    """chapter_voice_spec resolves voice for a chapter override."""
+
+    def test_no_override_uses_fallback(self):
+        from abogen.domain.voice_resolution import chapter_voice_spec
+
+        job = SimpleNamespace(voice="af_heart", speakers=None, chapters=[])
+        assert chapter_voice_spec(job, None) == "af_heart"
+
+    def test_resolved_voice_wins(self):
+        from abogen.domain.voice_resolution import chapter_voice_spec
+
+        job = SimpleNamespace(voice="af_heart", speakers=None, chapters=[])
+        override = {"resolved_voice": "af_bella", "voice_formula": "x", "voice": "y"}
+        assert chapter_voice_spec(job, override) == "af_bella"
+
+    def test_formula_second(self):
+        from abogen.domain.voice_resolution import chapter_voice_spec
+
+        job = SimpleNamespace(voice="", speakers=None, chapters=[])
+        override = {"voice_formula": "v1*v2", "voice": "y"}
+        assert chapter_voice_spec(job, override) == "v1*v2"
+
+    def test_voice_third(self):
+        from abogen.domain.voice_resolution import chapter_voice_spec
+
+        job = SimpleNamespace(voice="", speakers=None, chapters=[])
+        override = {"voice": "af_nicole"}
+        assert chapter_voice_spec(job, override) == "af_nicole"
+
+    def test_empty_override_falls_to_fallback(self):
+        from abogen.domain.voice_resolution import chapter_voice_spec
+
+        job = SimpleNamespace(voice="af_heart", speakers=None, chapters=[])
+        assert chapter_voice_spec(job, {}) == "af_heart"
+
+
+# ---------------------------------------------------------------------------
+# chunk_voice_spec
+# ---------------------------------------------------------------------------
+
+
+class TestChunkVoiceSpec:
+    """chunk_voice_spec resolves voice for a TTS chunk."""
+
+    def test_chunk_direct_voice(self):
+        from abogen.domain.voice_resolution import chunk_voice_spec
+
+        job = SimpleNamespace(speakers=None)
+        chunk = {"resolved_voice": "af_heart"}
+        assert chunk_voice_spec(job, chunk, "fallback") == "af_heart"
+
+    def test_chunk_speaker_lookup(self):
+        from abogen.domain.voice_resolution import chunk_voice_spec
+
+        job = SimpleNamespace(speakers={"narrator": {"resolved_voice": "af_bella"}})
+        chunk = {"speaker_id": "narrator"}
+        assert chunk_voice_spec(job, chunk, "") == "af_bella"
+
+    def test_chunk_voice_profile_lookup(self):
+        from abogen.domain.voice_resolution import chunk_voice_spec
+
+        job = SimpleNamespace(speakers={"角色A": {"voice": "af_nicole"}})
+        chunk = {"voice_profile": "角色A"}
+        assert chunk_voice_spec(job, chunk, "") == "af_nicole"
+
+    def test_uses_fallback_string(self):
+        from abogen.domain.voice_resolution import chunk_voice_spec
+
+        job = SimpleNamespace(speakers=None)
+        chunk = {}
+        assert chunk_voice_spec(job, chunk, "my_fallback") == "my_fallback"
+
+    def test_fallback_to_job(self):
+        from abogen.domain.voice_resolution import chunk_voice_spec
+
+        job = SimpleNamespace(voice="af_heart", speakers=None, chapters=[])
+        chunk = {}
+        assert chunk_voice_spec(job, chunk, "") == "af_heart"
+
+
+# ---------------------------------------------------------------------------
+# collect_required_voice_ids
+# ---------------------------------------------------------------------------
+
+
+class TestCollectRequiredVoiceIds:
+    """collect_required_voice_ids gathers all voice IDs from a job."""
+
+    def test_includes_job_voice(self):
+        from abogen.domain.voice_resolution import collect_required_voice_ids
+
+        job = SimpleNamespace(voice="af_heart", chapters=[], chunks=[], speakers={})
+        with patch("abogen.domain.voice_resolution.get_voices", return_value={"af_heart"}), \
+             patch("abogen.domain.voice_resolution.job_voice_fallback", return_value=""):
+            result = collect_required_voice_ids(job)
+        assert "af_heart" in result
+
+    def test_includes_chapter_voices(self):
+        from abogen.domain.voice_resolution import collect_required_voice_ids
+
+        job = SimpleNamespace(
+            voice="",
+            chapters=[{"resolved_voice": "af_bella"}],
+            chunks=[],
+            speakers={},
+        )
+        with patch("abogen.domain.voice_resolution.get_voices", return_value={"af_bella"}), \
+             patch("abogen.domain.voice_resolution.job_voice_fallback", return_value=""):
+            result = collect_required_voice_ids(job)
+        assert "af_bella" in result
+
+    def test_includes_chunk_voices(self):
+        from abogen.domain.voice_resolution import collect_required_voice_ids
+
+        job = SimpleNamespace(
+            voice="",
+            chapters=[],
+            chunks=[{"voice": "af_nicole"}],
+            speakers={},
+        )
+        with patch("abogen.domain.voice_resolution.get_voices", return_value={"af_nicole"}), \
+             patch("abogen.domain.voice_resolution.job_voice_fallback", return_value=""):
+            result = collect_required_voice_ids(job)
+        assert "af_nicole" in result
+
+    def test_always_includes_kokoro_voices(self):
+        from abogen.domain.voice_resolution import collect_required_voice_ids
+
+        job = SimpleNamespace(voice="", chapters=[], chunks=[], speakers={})
+        with patch("abogen.domain.voice_resolution.get_voices", return_value={"af_heart", "af_bella"}), \
+             patch("abogen.domain.voice_resolution.job_voice_fallback", return_value=""):
+            result = collect_required_voice_ids(job)
+        assert {"af_heart", "af_bella"}.issubset(result)

tests/test_voice_utils.py

@@ -0,0 +1,118 @@
+"""Tests for domain/voice_utils.py."""
+import sys
+import os
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
+
+from abogen.domain.voice_utils import (
+    infer_provider_from_spec,
+    supertonic_voice_from_spec,
+    split_speaker_reference,
+    formula_from_kokoro_entry,
+    coerce_truthy,
+)
+
+
+class TestInferProviderFromSpec:
+    def test_empty_returns_fallback(self):
+        assert infer_provider_from_spec("", "kokoro") == "kokoro"
+
+    def test_supertonic_uppercase(self):
+        assert infer_provider_from_spec("M1", "kokoro") == "supertonic"
+
+    def test_kokoro_voice(self):
+        assert infer_provider_from_spec("af_bella", "kokoro") == "kokoro"
+
+    def test_custom_mix(self):
+        assert infer_provider_from_spec("__custom_mix", "kokoro") == "kokoro"
+
+    def test_formula(self):
+        assert infer_provider_from_spec("af_bella*0.5+am_adam*0.5", "kokoro") == "kokoro"
+
+
+class TestSupertonicVoiceFromSpec:
+    def test_normal(self):
+        assert supertonic_voice_from_spec("m1", "m2") == "M1"
+
+    def test_empty_uses_fallback(self):
+        assert supertonic_voice_from_spec("", "m2") == "M2"
+
+    def test_formula_uses_fallback(self):
+        assert supertonic_voice_from_spec("m1*0.5", "m2") == "M2"
+
+    def test_both_empty_uses_default(self):
+        assert supertonic_voice_from_spec("", "") == "M1"
+
+
+class TestSplitSpeakerReference:
+    def test_speaker(self):
+        name, original = split_speaker_reference("speaker:John")
+        assert name == "John"
+        assert original == "speaker:John"
+
+    def test_profile(self):
+        name, original = split_speaker_reference("profile:Main")
+        assert name == "Main"
+        assert original == "profile:Main"
+
+    def test_invalid_prefix(self):
+        name, original = split_speaker_reference("voice:John")
+        assert name is None
+        assert original == "voice:John"
+
+    def test_no_colon(self):
+        name, original = split_speaker_reference("John")
+        assert name is None
+        assert original == "John"
+
+    def test_empty(self):
+        name, original = split_speaker_reference("")
+        assert name is None
+        assert original == ""
+
+
+class TestFormulaFromKokoroEntry:
+    def test_normal(self):
+        entry = {"voices": [["af_bella", 0.5], ["am_adam", 0.5]]}
+        result = formula_from_kokoro_entry(entry)
+        assert "af_bella" in result
+        assert "am_adam" in result
+
+    def test_empty(self):
+        assert formula_from_kokoro_entry({}) == ""
+
+    def test_invalid_items(self):
+        entry = {"voices": [["af_bella", "invalid"], ["am_adam", 0.5]]}
+        result = formula_from_kokoro_entry(entry)
+        assert "am_adam" in result
+        assert "af_bella" not in result
+
+
+class TestCoerceTruthy:
+    def test_bool_true(self):
+        assert coerce_truthy(True) is True
+
+    def test_bool_false(self):
+        assert coerce_truthy(False) is False
+
+    def test_string_true(self):
+        assert coerce_truthy("true") is True
+        assert coerce_truthy("yes") is True
+        assert coerce_truthy("1") is True
+        assert coerce_truthy("on") is True
+
+    def test_string_false(self):
+        assert coerce_truthy("false") is False
+        assert coerce_truthy("no") is False
+        assert coerce_truthy("0") is False
+        assert coerce_truthy("off") is False
+        assert coerce_truthy("") is False
+
+    def test_none_default_true(self):
+        assert coerce_truthy(None, True) is True
+
+    def test_none_default_false(self):
+        assert coerce_truthy(None, False) is False
+
+    def test_int(self):
+        assert coerce_truthy(1) is True
+        assert coerce_truthy(0) is False

tests/test_webui_form_limits.py

@@ -0,0 +1,53 @@
+from abogen.webui.app import create_app
+
+
+def _large_chapter_form() -> dict[str, str]:
+    data = {"step": "chapters"}
+    for index in range(370):
+        prefix = f"chapter-{index}"
+        data[f"{prefix}-enabled"] = "on"
+        data[f"{prefix}-title"] = f"Chapter {index} " + ("x" * 1400)
+        data[f"{prefix}-voice"] = "af_heart"
+        data[f"{prefix}-formula"] = "default"
+    return data
+
+
+def test_large_chapter_form_reaches_wizard_route(tmp_path):
+    app = create_app(
+        {
+            "TESTING": True,
+            "SECRET_KEY": "test",
+            "OUTPUT_FOLDER": str(tmp_path / "output"),
+            "UPLOAD_FOLDER": str(tmp_path / "uploads"),
+        }
+    )
+
+    with app.test_client() as client:
+        response = client.post(
+            "/wizard/update?format=json",
+            data=_large_chapter_form(),
+        )
+
+    assert response.status_code == 400
+    assert response.get_json()["error"] == "Missing job ID"
+
+
+def test_large_multipart_chapter_form_reaches_wizard_route(tmp_path):
+    app = create_app(
+        {
+            "TESTING": True,
+            "SECRET_KEY": "test",
+            "OUTPUT_FOLDER": str(tmp_path / "output"),
+            "UPLOAD_FOLDER": str(tmp_path / "uploads"),
+        }
+    )
+
+    with app.test_client() as client:
+        response = client.post(
+            "/wizard/update?format=json",
+            data=_large_chapter_form(),
+            content_type="multipart/form-data",
+        )
+
+    assert response.status_code == 400
+    assert response.get_json()["error"] == "Missing job ID"