fix(audio_helpers): update opus bitrate to 128kbps in ffmpeg command

Complete the Language enum unification (commit 0dc491e) for the PyQt
GUI, which was left resolving languages from kokoro letter codes
(voice[0]) while domain and WebUI already used Language enums.

- selected_lang is now always a Language enum: voices resolve via
  language_for_voice_id(), profiles via resolve_profile_language()
- kokoro letter->Language mapping stays in the engine (new public
  language_for_code()); the Language.from_code() domain shim is removed
- legacy profile files with letter codes ("a", "e", ...) are tolerated
  only at the profile read boundary; new profiles save ISO codes
- conversion.py letter comparisons replaced with enum comparisons, and
  SynthParams lang_code= -> language= (would TypeError at runtime)
- subtitle dropdown enabled for all languages; word-count and
  highlighting modes restricted to English with auto-switch to Sentence
- tests: engine mapping + profile language resolution added; 1566 pass

.gitignore

@@ -40,3 +40,6 @@ test_assets/
 dev_notes/
 .claude/
 .coverage
+
+# CodeGraph index (local, machine-specific)
+.codegraph/

abogen/constants.py

@@ -70,11 +70,12 @@ SUPPORTED_INPUT_FORMATS = [
     "vtt",
 ]
 
-# Supported languages for subtitle generation
-# Currently, only English (EN_US, EN_GB) are supported for subtitle generation.
-# This is because tokens that contain timestamps are not generated for other languages in the Kokoro pipeline.
-# Please refer to: https://github.com/hexgrad/kokoro/blob/6d87f4ae7abc2d14dbc4b3ef2e5f19852e861ac2/kokoro/pipeline.py
-SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION = [Language.EN_US, Language.EN_GB]
+# Supported languages for subtitle generation.
+# All languages are supported: only English emits per-word timestamped tokens
+# in the Kokoro pipeline, but other languages fall back to segment-level fake
+# tokens (see abogen.domain.tokens.FakeToken), so subtitles are still
+# generated at segment granularity.
+SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION = list(Language)
 
 # Voice and sample text mapping
 SAMPLE_VOICE_TEXTS = {

abogen/domain/audio_helpers.py

@@ -33,7 +33,7 @@ def build_ffmpeg_command(path: Path, fmt: str, metadata: Optional[Dict[str, str]
     if fmt == "mp3":
         base += ["-c:a", "libmp3lame", "-qscale:a", "2"]
     elif fmt == "opus":
-        base += ["-c:a", "libopus", "-b:a", "24000"]
+        base += ["-c:a", "libopus", "-b:a", "128000"]
     elif fmt == "m4b":
         base += ["-c:a", "aac", "-q:a", "2", "-movflags", "+faststart+use_metadata_tags"]
     else:

abogen/domain/conversion_pipeline.py

@@ -112,12 +112,10 @@ def spacy_pre_tts_segmentation(
 
 
 def _to_language_enum(lang_code: Any) -> Language:
-    """Convert lang_code to Language enum."""
-    if isinstance(lang_code, Language):
-        return lang_code
+    """Convert lang_code to Language enum (ISO code or Language enum)."""
     try:
         return Language.from_str(str(lang_code))
-    except (ValueError, AttributeError):
+    except ValueError:
         return Language.EN_US
 
 

abogen/domain/enums.py

@@ -212,8 +212,12 @@ class Language(str, Enum):
 
     @property
     def supports_subtitle_tokens(self) -> bool:
-        """True if this language generates timestamped tokens for subtitles."""
-        return self in (self.EN_US, self.EN_GB)
+        """True if this language supports subtitle generation.
+
+        All languages are supported: languages without per-word timestamped
+        tokens fall back to segment-level fake tokens in the pipeline.
+        """
+        return True
 
     @classmethod
     def from_str(cls, value: str) -> Language:

abogen/domain/split_pattern.py

@@ -16,7 +16,7 @@ def get_split_pattern(language: Language, subtitle_mode: str) -> str:
     """Get the appropriate split pattern based on language and subtitle mode.
 
     Args:
-        language: Language enum value.
+        language: Language enum value, ISO code, or kokoro letter code.
         subtitle_mode: Subtitle mode ("Sentence", "Sentence + Comma", "Line", etc.)
 
     Returns:

abogen/entity_analysis.py

@@ -9,15 +9,26 @@ from collections import Counter
 from dataclasses import dataclass, field
 from typing import Any, Dict, Iterable, List, Mapping, Optional, Tuple
 
-try:  # pragma: no cover - fallback when spaCy not available during tests
-    import spacy  # type: ignore[import-not-found]
-except Exception:  # pragma: no cover - spaCy optional during runtime bootstrap
-    spacy = None
-
 _Language = Any  # type: ignore[misc,assignment]
 Doc = Any  # type: ignore[misc,assignment]
 Span = Any  # type: ignore[misc,assignment]
 
+_SPACY: Any = None
+_SPACY_LOADED = False
+
+
+def _get_spacy() -> Any:
+    """Import spaCy lazily (it pulls in torch/thinc, ~2s at startup)."""
+    global _SPACY, _SPACY_LOADED
+    if not _SPACY_LOADED:
+        _SPACY_LOADED = True
+        try:  # pragma: no cover - fallback when spaCy not available during tests
+            import spacy  # type: ignore[import-not-found]
+        except Exception:  # pragma: no cover - spaCy optional during runtime bootstrap
+            spacy = None
+        _SPACY = spacy
+    return _SPACY
+
 
 _TITLE_PREFIXES = (
     "mr",
@@ -167,6 +178,7 @@ def _resolve_model_name(language: str) -> str:
 
 
 def _load_model(language: str) -> Any:
+    spacy = _get_spacy()
     if spacy is None:
         raise EntityModelError(
             "spaCy is not available. Install spaCy to enable entity extraction."

abogen/heteronym_overrides.py

@@ -5,10 +5,21 @@ import re
 from dataclasses import dataclass
 from typing import Any, Dict, Iterable, List, Mapping, Optional, Sequence, Tuple
 
-try:  # pragma: no cover - optional dependency
+_SPACY: Any = None
+_SPACY_LOADED = False
+
+
+def _get_spacy() -> Any:
+    """Import spaCy lazily (it pulls in torch/thinc, ~2s at startup)."""
+    global _SPACY, _SPACY_LOADED
+    if not _SPACY_LOADED:
+        _SPACY_LOADED = True
+        try:  # pragma: no cover - optional dependency
             import spacy  # type: ignore
-except Exception:  # pragma: no cover - spaCy may be unavailable in minimal environments
+        except Exception:  # pragma: no cover - spaCy may be unavailable in minimal environments
             spacy = None
+        _SPACY = spacy
+    return _SPACY
 
 
 @dataclass(frozen=True)
@@ -184,6 +195,7 @@ def _build_replacement_sentence(
 
 
 def _load_spacy(language: str) -> Any:
+    spacy = _get_spacy()
     if spacy is None:
         return None
 
@@ -221,7 +233,7 @@ def extract_heteronym_overrides(
     if not lang.startswith("en"):
         return []
 
-    if spacy is None:
+    if _get_spacy() is None:
         return []
 
     nlp = _load_spacy(lang)

abogen/pyqt/book_handler.py

@@ -45,9 +45,9 @@ import urllib.parse
 import textwrap
 
 # Setup logging
-logging.basicConfig(
-    level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
-)
+from abogen.utils import setup_console_logging
+
+setup_console_logging()
 
 _HTML_TAG_PATTERN = re.compile(r"<[^>]+>")
 _LEADING_DASH_PATTERN = re.compile(r"^\s*[-–—]\s*")

abogen/pyqt/conversion.py

@@ -22,6 +22,7 @@ from abogen.constants import (
 )
 from abogen.infrastructure.subtitle_writer import make_subtitle_writer, resolve_subtitle_format
 from abogen.domain.split_pattern import get_split_pattern
+from abogen.domain.enums import Language
 from abogen.domain.subtitle_processor import (
     parse_subtitle_file,
     process_subtitle_entries,
@@ -872,12 +873,12 @@ class ConversionThread(QThread):
                     )
                     spacy_sentences = None
                     active_split_pattern = self.split_pattern
-                    spacing_pattern = r"\s*" if self.lang_code in ["z", "j"] else r"\s+"
+                    spacing_pattern = r"\s*" if self.lang_code in (Language.JA, Language.ZH) else r"\s+"
 
                     # Pre-load spaCy model for English if it will be needed for subtitle generation
                     if (
                         use_spacy
-                        and self.lang_code in ["a", "b"]
+                        and self.lang_code in (Language.EN_US, Language.EN_GB)
                         and self.subtitle_mode in ["Sentence", "Sentence + Comma"]
                     ):
                         from abogen.spacy_utils import get_spacy_model
@@ -894,7 +895,7 @@ class ConversionThread(QThread):
                                 )
                             )
 
-                    if use_spacy and self.lang_code not in ["a", "b"]:
+                    if use_spacy and self.lang_code not in (Language.EN_US, Language.EN_GB):
                         # Non-English: use spaCy for pre-TTS segmentation
                         self.log_updated.emit(
                             ("\nUsing spaCy for sentence segmentation (pre-TTS)...", "grey")
@@ -1011,7 +1012,7 @@ class ConversionThread(QThread):
                             audio_sink=merged_sink if merge_chapters_at_end else None,
                             subtitle_mode=self.subtitle_mode,
                             max_subtitle_words=self.max_subtitle_words,
-                            lang_code=self.lang_code,
+                            language=self.lang_code,
                             use_spacy_segmentation=getattr(self, "use_spacy_segmentation", False),
                         )
 

abogen/pyqt/gui.py

@@ -75,6 +75,7 @@ from abogen.domain.text_utils import calculate_text_length
 
 from abogen.pyqt.conversion import ConversionThread, VoicePreviewThread, PlayAudioThread, ChapterOptionsDialog, TimestampDetectionDialog
 from abogen.pyqt.book_handler import HandlerDialog
+from abogen.domain.enums import Language
 from abogen.constants import (
     PROGRAM_NAME,
     VERSION,
@@ -88,8 +89,9 @@ from abogen.constants import (
 from abogen.tts_plugin.utils import get_voices
 import threading
 from abogen.pyqt.voice_formula_gui import VoiceFormulaDialog
-from abogen.voice_profiles import load_profiles
+from abogen.voice_profiles import load_profiles, resolve_profile_language
 from abogen.domain.settings_core import all_settings_defaults
+from plugins.kokoro.engine import language_for_code, language_for_voice_id
 
 # Module-level default cache for use outside __init__
 _DEFAULTS = all_settings_defaults()
@@ -397,11 +399,7 @@ class InputBox(QLabel):
         # Re-enable subtitle and replace newlines controls when cleared
         window = self.window()
         if hasattr(window, "subtitle_combo"):
-            # Only enable if language supports it
-            current_lang = getattr(window, "selected_lang", "a")
-            window.subtitle_combo.setEnabled(
-                current_lang in SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION
-            )
+            window.subtitle_combo.setEnabled(True)
         if hasattr(window, "replace_newlines_combo"):
             window.replace_newlines_combo.setEnabled(True)
 
@@ -941,7 +939,7 @@ class abogen(QWidget):
             self.selected_lang = None
         else:
             self.selected_voice = self.config.get("selected_voice", _d["selected_voice"])
-            self.selected_lang = self.selected_voice[0] if self.selected_voice else None
+            self.selected_lang = language_for_voice_id(self.selected_voice)
         self.is_converting = False
         self.subtitle_mode = self.config.get("subtitle_mode", _d["subtitle_mode"])
         self.max_subtitle_words = self.config.get("max_subtitle_words", _d["max_subtitle_words"])
@@ -988,6 +986,11 @@ class abogen(QWidget):
         self.queued_items = []
         self.current_queue_index = 0
 
+        from abogen.utils import timed_log
+        import logging
+        _startup_log = logging.getLogger("abogen.startup")
+
+        with timed_log("GUI initUI (widget building)", logger=_startup_log):
             self.initUI()
         self.speed_slider.setValue(int(self.config.get("speed", _d["speed"]) * 100))
         self.update_speed_label()
@@ -1003,13 +1006,16 @@ class abogen(QWidget):
             if self.selected_profile_name:
                 from abogen.voice_profiles import load_profiles
 
+                with timed_log("voice profile load", logger=_startup_log):
                     entry = load_profiles().get(self.selected_profile_name, {})
                 if isinstance(entry, dict):
                     self.mixed_voice_state = entry.get("voices", [])
-                    self.selected_lang = entry.get("language")
+                    self.selected_lang = resolve_profile_language(entry)
                 else:
                     self.mixed_voice_state = entry
-                    self.selected_lang = entry[0][0] if entry and entry[0] else None
+                    self.selected_lang = (
+                        language_for_voice_id(entry[0]) if entry and entry[0] else Language.EN_US
+                    )
         if self.save_option == "Choose output folder" and self.selected_output_folder:
             self.save_path_label.setText(self.selected_output_folder)
             self.save_path_row_widget.show()
@@ -1175,6 +1181,7 @@ class abogen(QWidget):
             "Sentence + Comma: Subtitles will be generated for each sentence and comma.\n"
             "Sentence + Highlighting: Subtitles with word-by-word karaoke highlighting.\n"
             "1+ word: Subtitles will be generated for each word(s).\n\n"
+            "Word-count and highlighting modes are only available for English.\n"
             "Supported languages for subtitle generation:\n"
             + "\n".join(
                 f'"{lang}" => {LANGUAGE_DESCRIPTIONS.get(lang, lang)}'
@@ -1753,8 +1760,9 @@ class abogen(QWidget):
 
     def update_subtitle_options_availability(self):
         """
-        Update the enabled state of subtitle options based on the selected language.
-        For non-English languages, only sentence-based and line-based modes are supported.
+        Update the enabled state of subtitle options based on the selected
+        language and input type. Subtitle generation works for every language,
+        but word-count and highlighting modes are only available for English.
         """
         # Check if current file is a subtitle file
         is_subtitle_input = False
@@ -1763,16 +1771,14 @@ class abogen(QWidget):
         ):
             is_subtitle_input = True
 
-        if self.selected_lang not in SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION:
-            self.subtitle_combo.setEnabled(False)
-            self.subtitle_format_combo.setEnabled(False)
-            return
-
         # Only enable subtitle_combo if it's NOT a subtitle input
         self.subtitle_combo.setEnabled(not is_subtitle_input)
         self.subtitle_format_combo.setEnabled(True)
 
-        is_english = self.selected_lang in ["a", "b"]
+        is_english = self.selected_lang in (
+            Language.EN_US,
+            Language.EN_GB,
+        )
 
         # Items to keep enabled for non-English
         allowed_modes = ["Disabled", "Line", "Sentence", "Sentence + Comma"]
@@ -1787,10 +1793,7 @@ class abogen(QWidget):
             if is_english:
                 item.setEnabled(True)
             else:
-                if text in allowed_modes:
-                    item.setEnabled(True)
-                else:
-                    item.setEnabled(False)
+                item.setEnabled(text in allowed_modes)
 
         # If current selection is disabled, switch to a valid one
         current_text = self.subtitle_combo.currentText()
@@ -1809,7 +1812,7 @@ class abogen(QWidget):
 
     def on_voice_changed(self, index):
         voice = self.voice_combo.itemData(index)
-        self.selected_voice, self.selected_lang = voice, voice[0]
+        self.selected_voice, self.selected_lang = voice, language_for_voice_id(voice)
         self.config["selected_voice"] = voice
         save_config(self.config)
         # Enable/disable subtitle options based on language
@@ -1826,10 +1829,12 @@ class abogen(QWidget):
             # set mixed voices and language
             if isinstance(entry, dict):
                 self.mixed_voice_state = entry.get("voices", [])
-                self.selected_lang = entry.get("language")
+                self.selected_lang = resolve_profile_language(entry)
             else:
                 self.mixed_voice_state = entry
-                self.selected_lang = entry[0][0] if entry and entry[0] else None
+                self.selected_lang = (
+                    language_for_voice_id(entry[0]) if entry and entry[0] else Language.EN_US
+                )
             self.selected_voice = None
             self.config["selected_profile_name"] = pname
             self.config.pop("selected_voice", None)
@@ -1839,7 +1844,7 @@ class abogen(QWidget):
         else:
             self.mixed_voice_state = None
             self.selected_profile_name = None
-            self.selected_voice, self.selected_lang = data, data[0]
+            self.selected_voice, self.selected_lang = data, language_for_voice_id(data)
             self.config["selected_voice"] = data
             if "selected_profile_name" in self.config:
                 del self.config["selected_profile_name"]
@@ -1850,8 +1855,9 @@ class abogen(QWidget):
         from abogen.voice_profiles import load_profiles
 
         entry = load_profiles().get(profile_name, {})
-        lang = entry.get("language") if isinstance(entry, dict) else None
-        enable = lang in SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION
+        enable = (
+            resolve_profile_language(entry) in SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION
+        )
         self.subtitle_combo.setEnabled(enable)
         self.subtitle_format_combo.setEnabled(enable)
 
@@ -2233,18 +2239,18 @@ class abogen(QWidget):
         else:
             return self.selected_voice
 
-    def get_selected_lang(self, voice_formula) -> str:
+    def get_selected_lang(self, voice_formula) -> Language:
         if self.selected_profile_name:
             from abogen.voice_profiles import load_profiles
 
             entry = load_profiles().get(self.selected_profile_name, {})
-            selected_lang = entry.get("language")
+            selected_lang = resolve_profile_language(entry)
         else:
-            selected_lang = self.selected_voice[0] if self.selected_voice else None
+            selected_lang = language_for_voice_id(self.selected_voice)
         # fallback: extract from formula if missing
         if not selected_lang:
             m = re.search(r"\b([a-z])", voice_formula)
-            selected_lang = m.group(1) if m else None
+            selected_lang = language_for_code(m.group(1)) if m else Language.EN_US
         return selected_lang
 
     def get_actual_subtitle_mode(self) -> str:
@@ -2420,7 +2426,7 @@ class abogen(QWidget):
             self.update_log((gpu_msg, gpu_ok))
             self.update_log("Loading modules...")
 
-            lang_code = self.selected_lang or "a"
+            lang_code = self.selected_lang or Language.EN_US
             load_thread = LoadPipelineThread(
                 pipeline_loaded_callback, lang_code=lang_code, use_gpu=gpu_ok
             )
@@ -2751,12 +2757,12 @@ class abogen(QWidget):
                 from abogen.voice_profiles import load_profiles
 
                 entry = load_profiles().get(self.selected_profile_name, {})
-                lang_to_cache = entry.get("language")
+                lang_to_cache = resolve_profile_language(entry)
             else:
                 lang_to_cache = self.selected_lang
             if not lang_to_cache and self.mixed_voice_state:
                 lang_to_cache = (
-                    self.mixed_voice_state[0][0][0]
+                    language_for_voice_id(self.mixed_voice_state[0][0])
                     if self.mixed_voice_state and self.mixed_voice_state[0][0]
                     else None
                 )
@@ -2860,7 +2866,7 @@ class abogen(QWidget):
             )
             self.loading_movie.start()
 
-        lang = self.selected_lang or "a"
+        lang = self.selected_lang or Language.EN_US
         load_thread = LoadPipelineThread(
             self._on_pipeline_loaded_for_preview, lang_code=lang, use_gpu=self.gpu_ok
         )
@@ -2892,17 +2898,17 @@ class abogen(QWidget):
                 from abogen.voice_profiles import load_profiles
 
                 entry = load_profiles().get(self.selected_profile_name, {})
-                lang = entry.get("language")
+                lang = resolve_profile_language(entry)
             else:
                 lang = self.selected_lang
             if not lang and self.mixed_voice_state:
                 lang = (
-                    self.mixed_voice_state[0][0][0]
+                    language_for_voice_id(self.mixed_voice_state[0][0])
                     if self.mixed_voice_state and self.mixed_voice_state[0][0]
                     else None
                 )
         else:
-            lang = self.selected_voice[0]
+            lang = language_for_voice_id(self.selected_voice)
             voice = self.selected_voice
 
         # use same gpu/cpu logic as in conversion
@@ -3948,7 +3954,9 @@ Categories=AudioVideo;Audio;Utility;
                     initial_state = entry.get("voices", [])
                 else:
                     initial_state = entry
-                    self.selected_lang = entry[0][0] if entry and entry[0] else None
+                    self.selected_lang = (
+                        language_for_voice_id(entry[0]) if entry and entry[0] else Language.EN_US
+                    )
         dialog = VoiceFormulaDialog(
             self, initial_state=initial_state, selected_profile=selected_profile
         )

abogen/pyqt/main.py

@@ -1,3 +1,4 @@
+import logging
 import os
 import sys
 import platform
@@ -6,8 +7,14 @@ import platform
 from abogen import shutdown  # noqa: F401
 shutdown.register_shutdown()
 
+from abogen.utils import get_resource_path, setup_console_logging, timed_log  # noqa: E402
+
+_log = logging.getLogger("abogen.startup")
+setup_console_logging()
+
 # Fix PyTorch DLL loading issue ([WinError 1114]) on Windows before importing PyQt6
 if platform.system() == "Windows":
+    with timed_log("PyTorch DLLs (Windows)", logger=_log):
         import ctypes
         from importlib.util import find_spec
 
@@ -25,7 +32,8 @@ if platform.system() == "Windows":
 
 
 # Qt platform plugin detection (fixes #59)
-try:
+with timed_log("Qt platform plugin detection", logger=_log):
+    try:
         from PyQt6.QtCore import QLibraryInfo
 
         # Get the path to the plugins directory
@@ -39,17 +47,16 @@ try:
 
         if os.path.isdir(platform_dir):
             os.environ["QT_QPA_PLATFORM_PLUGIN_PATH"] = platform_dir
-        print("QT_QPA_PLATFORM_PLUGIN_PATH set to:", platform_dir)
+            _log.info("QT_QPA_PLATFORM_PLUGIN_PATH set to: %s", platform_dir)
         else:
-        print("PyQt6 platform plugins not found at", platform_dir)
-except ImportError:
-    print("PyQt6 not installed.")
+            _log.warning("PyQt6 platform plugins not found at %s", platform_dir)
+    except ImportError:
+        _log.warning("PyQt6 not installed.")
 
 
-from abogen.utils import get_resource_path
-
 # Pre-load "libxcb-cursor" on Linux (fixes #101)
 if platform.system() == "Linux":
+    with timed_log("libxcb-cursor preload (Linux)", logger=_log):
         arch = platform.machine().lower()
         lib_filename = {"x86_64": "libxcb-cursor-amd64.so.0", "amd64": "libxcb-cursor-amd64.so.0", "aarch64": "libxcb-cursor-arm64.so.0", "arm64": "libxcb-cursor-arm64.so.0"}.get(arch)
         if lib_filename:
@@ -71,6 +78,7 @@ if platform.system() == "Linux":
 
 # Set application ID for Windows taskbar icon
 if platform.system() == "Windows":
+    with timed_log("Windows AppUserModelID", logger=_log):
         try:
             from abogen.constants import PROGRAM_NAME, VERSION
             import ctypes
@@ -78,31 +86,34 @@ if platform.system() == "Windows":
             app_id = f"{PROGRAM_NAME}.{VERSION}"
             ctypes.windll.shell32.SetCurrentProcessExplicitAppUserModelID(app_id)
         except Exception as e:
-        print("Warning: failed to set AppUserModelID:", e)
+            _log.warning("Failed to set AppUserModelID: %s", e)
 
-from PyQt6.QtWidgets import QApplication
-from PyQt6.QtGui import QIcon
-from PyQt6.QtCore import (
+with timed_log("PyQt6 imports", logger=_log):
+    from PyQt6.QtWidgets import QApplication
+    from PyQt6.QtGui import QIcon
+    from PyQt6.QtCore import (
         QLibraryInfo,
         qInstallMessageHandler,
         QtMsgType,
-)
+    )
 
 # Add the directory to Python path
 sys.path.insert(0, os.path.join(os.path.dirname(__file__)))
 
 # Set Hugging Face Hub environment variables
-os.environ["HF_HUB_DISABLE_TELEMETRY"] = "1"  # Disable Hugging Face telemetry
-os.environ["HF_HUB_ETAG_TIMEOUT"] = "10"  # Metadata request timeout (seconds)
-os.environ["HF_HUB_DOWNLOAD_TIMEOUT"] = "10"  # File download timeout (seconds)
-os.environ["HF_HUB_DISABLE_SYMLINKS_WARNING"] = "1"  # Disable symlinks warning
-from abogen.utils import load_config
-if load_config().get("disable_kokoro_internet", False):
-    print("INFO: Kokoro's internet access is disabled.")
+with timed_log("config load + HF env setup", logger=_log):
+    os.environ["HF_HUB_DISABLE_TELEMETRY"] = "1"  # Disable Hugging Face telemetry
+    os.environ["HF_HUB_ETAG_TIMEOUT"] = "10"  # Metadata request timeout (seconds)
+    os.environ["HF_HUB_DOWNLOAD_TIMEOUT"] = "10"  # File download timeout (seconds)
+    os.environ["HF_HUB_DISABLE_SYMLINKS_WARNING"] = "1"  # Disable symlinks warning
+    from abogen.utils import load_config
+    if load_config().get("disable_kokoro_internet", False):
+        _log.info("Kokoro's internet access is disabled.")
         os.environ["HF_HUB_OFFLINE"] = "1"  # Disable Hugging Face Hub internet access
 
-from abogen.pyqt.gui import abogen
-from abogen.constants import PROGRAM_NAME, VERSION
+with timed_log("GUI module import (abogen.pyqt.gui)", logger=_log):
+    from abogen.pyqt.gui import abogen
+    from abogen.constants import PROGRAM_NAME, VERSION
 
 # Set environment variables for AMD ROCm
 os.environ["MIOPEN_FIND_MODE"] = "FAST"
@@ -150,6 +161,7 @@ if platform.system() == "Linux":
 
 def main():
     """Main entry point for console usage."""
+    with timed_log("QApplication creation", logger=_log):
         app = QApplication(sys.argv)
 
     # Set application icon using get_resource_path from utils
@@ -164,8 +176,11 @@ def main():
         except AttributeError:
             pass
 
+    with timed_log("main window construction", logger=_log):
         ex = abogen()
+    with timed_log("window show", logger=_log):
         ex.show()
+    _log.info("App startup complete. Showing window.")
     sys.exit(app.exec())
 
 

abogen/pyqt/voice_formula_gui.py

@@ -28,7 +28,6 @@ from PyQt6.QtWidgets import (
 from PyQt6.QtCore import Qt, QTimer, QPoint, QRect, QSize
 from PyQt6.QtGui import QPixmap, QIcon, QAction
 from abogen.constants import (
-    SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION,
     LANGUAGE_DESCRIPTIONS,
     COLORS,
 )
@@ -949,7 +948,9 @@ class VoiceFormulaDialog(QDialog):
         lang = state.get("language") if isinstance(state, dict) else None
         # apply language selection
         if lang:
-            i = self.language_combo.findData(lang)
+            from abogen.voice_profiles import resolve_profile_language
+
+            i = self.language_combo.findData(resolve_profile_language(state))
             if i >= 0:
                 self.language_combo.blockSignals(True)
                 self.language_combo.setCurrentIndex(i)
@@ -1571,9 +1572,10 @@ class VoiceFormulaDialog(QDialog):
             parent.selected_profile_name = None
             lang = self.language_combo.currentData()
             parent.selected_lang = lang
-            parent.subtitle_combo.setEnabled(
-                lang in SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION
-            )
+            if hasattr(parent, "update_subtitle_options_availability"):
+                parent.update_subtitle_options_availability()
+            else:
+                parent.subtitle_combo.setEnabled(True)
             # Reset start flag and trigger preview
             self._started = False
             parent.preview_voice()

abogen/spacy_contraction_resolver.py

@@ -6,10 +6,9 @@ from dataclasses import dataclass
 from functools import lru_cache
 from typing import Any, Dict, Optional, Tuple
 
-try:  # pragma: no cover - optional dependency
-    import spacy
-except Exception:  # pragma: no cover - spaCy unavailable at runtime
-    spacy = None
+# spaCy is intentionally NOT imported at module level: importing it pulls in
+# thinc -> torch, which costs seconds of startup time. It is imported lazily
+# inside _load_spacy_model below.
 
 # Lazy spaCy type hints to avoid a hard dependency at import time.
 Language = Any  # type: ignore[assignment]
@@ -37,7 +36,9 @@ _DEFAULT_MODEL = os.environ.get("ABOGEN_SPACY_MODEL", "en_core_web_sm")
 
 @lru_cache(maxsize=1)
 def _load_spacy_model(model: str = _DEFAULT_MODEL) -> Optional[Language]:
-    if spacy is None:
+    try:  # pragma: no cover - optional dependency
+        import spacy
+    except Exception:  # pragma: no cover - spaCy unavailable at runtime
         logger.debug("spaCy is not installed; skipping contraction disambiguation")
         return None
 

abogen/spacy_utils.py

@@ -57,7 +57,9 @@ def get_spacy_model(language: Language, log_callback=None):
             print(msg)
 
     if not isinstance(language, Language):
-        raise TypeError(f"language must be Language enum, got {type(language).__name__}: {language!r}")
+        raise TypeError(
+            f"language must be Language enum, got {type(language).__name__}: {language!r}"
+        )
 
     if language in _nlp_cache:
         return _nlp_cache[language]

abogen/utils.py

@@ -6,7 +6,9 @@ import re
 import shutil
 import subprocess
 import sys
+import time
 import warnings
+from contextlib import contextmanager
 from threading import Thread
 from typing import Dict, Optional
 
@@ -29,6 +31,125 @@ _load_environment()
 
 warnings.filterwarnings("ignore")
 
+# --- Console log colorization via rich (mirrors AutoSubSync's approach) ---
+
+try:  # rich is a declared dependency, but degrade gracefully if unavailable
+    from rich.console import Console
+    from rich.highlighter import NullHighlighter
+    from rich.logging import RichHandler
+
+    _RICH_AVAILABLE = True
+except Exception:  # pragma: no cover - fallback to plain logging
+    Console = None
+    NullHighlighter = None
+    RichHandler = None
+    _RICH_AVAILABLE = False
+
+
+def _console_supports_color() -> bool:
+    if os.environ.get("NO_COLOR"):
+        return False
+    try:
+        return bool(sys.stderr.isatty())
+    except Exception:
+        return False
+
+
+_RICH_CONSOLE = None
+if Console is not None:
+    try:
+        _RICH_CONSOLE = Console(stderr=True, no_color=not _console_supports_color())
+    except Exception:  # pragma: no cover - defensive
+        _RICH_CONSOLE = None
+
+
+_ANSI_ESCAPE_RE = re.compile(r"\x1b\[[0-9;]*[A-Za-z]")
+
+if RichHandler is not None:
+
+    class RichConsoleHandler(RichHandler):
+        """RichHandler with default settings, except raw ANSI escapes are
+        stripped from messages first (werkzeug colorizes its own log lines
+        when attached to a TTY; without this they render as literal "[36m"
+        fragments)."""
+
+        def emit(self, record):
+            # Werkzeug logs its dev-server banner at INFO but hardcodes a
+            # "WARNING: " prefix into the message text. Promote the record so
+            # the level tag matches the content.
+            try:
+                message = _ANSI_ESCAPE_RE.sub("", record.getMessage())
+            except Exception:  # pragma: no cover - defensive
+                message = ""
+            if record.levelno < logging.WARNING and message.startswith("WARNING: "):
+                record.levelno = logging.WARNING
+                record.levelname = "WARNING"
+            super().emit(record)
+
+        def render_message(self, record, message):
+            message = _ANSI_ESCAPE_RE.sub("", message)
+            if message.startswith("WARNING: "):
+                message = message[len("WARNING: ") :]
+            return super().render_message(record, message)
+
+else:  # pragma: no cover - rich unavailable fallback
+    RichConsoleHandler = None  # type: ignore[assignment, misc]
+
+
+def console_handler(show_level=True):
+    """Build a colored console handler. Rich's RichHandler when available
+    (no timestamps, colored level tags), plain StreamHandler otherwise."""
+    if _RICH_CONSOLE is not None and RichConsoleHandler is not None:
+        return RichConsoleHandler(
+            console=_RICH_CONSOLE,
+            show_path=False,
+            show_time=False,
+            rich_tracebacks=True,
+        )
+    handler = logging.StreamHandler(sys.stderr)
+    prefix = "%(levelname)s - " if show_level else ""
+    handler.setFormatter(logging.Formatter(f"{prefix}%(message)s"))
+    return handler
+
+
+def setup_console_logging(level=logging.INFO):
+    """Configure the root logger once with a colored console handler."""
+    root = logging.getLogger()
+    if not root.handlers:
+        root.addHandler(console_handler())
+    root.setLevel(level)
+
+
+@contextmanager
+def timed_log(label, logger=None, level=logging.INFO):
+    """Context manager that logs the wall-clock time a block of code takes.
+
+    Used to surface which load/startup steps are slow. The elapsed time is
+    colorized: green < 1s, yellow 1-5s, red > 5s.
+    """
+    log = logger or logging.getLogger(__name__)
+    start = time.perf_counter()
+    try:
+        yield
+    finally:
+        elapsed = time.perf_counter() - start
+        if _RICH_AVAILABLE and _RICH_CONSOLE is not None and not _RICH_CONSOLE.no_color:
+            if elapsed >= 5.0:
+                color = "red"
+            elif elapsed >= 1.0:
+                color = "yellow"
+            else:
+                color = "green"
+            log.log(
+                level,
+                "Loaded %s in %s",
+                f"[cyan]{label}[/cyan]",
+                f"[{color}]{elapsed:.2f}s[/{color}]",
+                extra={"markup": True, "highlighter": NullHighlighter()},
+            )
+        else:
+            log.log(level, "Loaded %s in %.2fs", label, elapsed)
+
 
 def detect_encoding(file_path):
     try:
@@ -527,6 +648,10 @@ class LoadPipelineThread(Thread):
         try:
             from abogen.domain.pipeline_factory import create_pipeline_for_job
 
+            with timed_log(
+                f"TTS pipeline (lang={self.lang_code}, gpu={self.use_gpu})",
+                logger=logging.getLogger("abogen.startup"),
+            ):
                 backend = create_pipeline_for_job(
                     "kokoro", language=self.lang_code, use_gpu=self.use_gpu
                 )

abogen/voice_profiles.py

@@ -2,6 +2,7 @@ import json
 import os
 from typing import Any, Dict, Iterable, List, Tuple
 
+from abogen.domain.enums import Language
 from abogen.tts_plugin.utils import get_voices, is_plugin_registered
 from abogen.utils import get_user_config_path
 
@@ -176,13 +177,35 @@ def save_profile(name: str, *, language: str, voices: Iterable) -> None:
         raise ValueError("At least one voice with a weight above zero is required")
 
     if not language:
-        language = "a"
+        language = Language.EN_US
 
     profiles = load_profiles()
     profiles[name] = {"provider": "kokoro", "language": language, "voices": normalized}
     save_profiles(profiles)
 
 
+def resolve_profile_language(entry: Any) -> Language:
+    """Resolve a profile's stored language to a Language enum.
+
+    New profiles store ISO codes (Language enum values); legacy profiles may
+    store kokoro letter codes ("a", "b", ...). Unparseable values fall back
+    to EN_US.
+    """
+
+    raw = entry.get("language") if isinstance(entry, dict) else None
+    if isinstance(raw, Language):
+        return raw
+    text = str(raw or "").strip()
+    if not text:
+        return Language.EN_US
+    try:
+        return Language.from_str(text)
+    except ValueError:
+        from plugins.kokoro.engine import language_for_code
+
+        return language_for_code(text)
+
+
 def remove_profile(name: str) -> None:
     delete_profile(name)
 

abogen/webui/app.py

@@ -9,11 +9,19 @@ from flask import Flask
 
 from abogen import shutdown  # noqa: F401
 shutdown.register_shutdown()
-from abogen.utils import get_user_cache_path, get_user_output_path, get_user_settings_dir
+from abogen.utils import (
+    get_user_cache_path,
+    get_user_output_path,
+    get_user_settings_dir,
+    setup_console_logging,
+    timed_log,
+)
 
 from .conversion_runner import run_conversion_job
 from .service import build_service
 
+_logger = logging.getLogger("abogen.startup")
+
 
 class _SuppressSuccessfulAccessFilter(logging.Filter):
     """Filter out successful (HTTP 200) werkzeug access logs."""
@@ -79,8 +87,10 @@ def _get_secret_key() -> str:
 
 
 def create_app(config: Optional[dict[str, Any]] = None) -> Flask:
+    with timed_log("default directories", logger=_logger):
         uploads_dir, outputs_dir = _default_dirs()
 
+    with timed_log("Flask app creation + config", logger=_logger):
         app = Flask(
             __name__,
             static_folder="static",
@@ -102,6 +112,7 @@ def create_app(config: Optional[dict[str, Any]] = None) -> Flask:
             base_config.update(config)
         app.config.update(base_config)
 
+    with timed_log("conversion service (incl. queue state load)", logger=_logger):
         service = build_service(
             runner=run_conversion_job,
             output_root=Path(app.config["OUTPUT_FOLDER"]),
@@ -109,6 +120,7 @@ def create_app(config: Optional[dict[str, Any]] = None) -> Flask:
         )
     app.extensions["conversion_service"] = service
 
+    with timed_log("blueprint registration", logger=_logger):
         from abogen.webui.routes import (
             main_bp,
             jobs_bp,
@@ -137,6 +149,16 @@ def create_app(config: Optional[dict[str, Any]] = None) -> Flask:
 
 
 def main() -> None:
+    setup_console_logging()
+    # Route Flask's dev-server banner through our logger instead of click.echo.
+    import flask.cli as flask_cli
+
+    def _show_server_banner(debug, app_import_path):
+        _logger.info(" * Serving Flask app %r", app_import_path)
+        _logger.info(" * Debug mode: %s", "on" if debug else "off")
+
+    flask_cli.show_server_banner = _show_server_banner
+
     app = create_app()
     host = os.environ.get("ABOGEN_HOST", "0.0.0.0")
     port = int(os.environ.get("ABOGEN_PORT", "8808"))

abogen/webui/debug_tts_runner.py

@@ -47,6 +47,13 @@ def _resolve_voice_setting(value: str) -> tuple[str, Optional[str], Optional[str
 
 
 def _load_pipeline(language: Language, use_gpu: bool) -> Any:
+    import logging
+    from abogen.utils import timed_log
+
+    with timed_log(
+        f"TTS pipeline (lang={language}, gpu={use_gpu})",
+        logger=logging.getLogger("abogen.startup"),
+    ):
         device = "cpu"
         if use_gpu:
             device = _select_device()

abogen/webui/routes/utils/form.py

@@ -809,6 +809,8 @@ def build_pending_job_from_extraction(
         analysis_requested=initial_analysis,
     )
 
+    apply_book_step_form(pending, form, settings=settings, profiles=profiles_map)
+
     return PendingBuildResult(
         pending=pending,
         selected_speaker_config=selected_speaker_config or None,

abogen/webui/service.py

@@ -17,7 +17,7 @@ from typing import Any, Callable, Dict, Iterable, List, Optional, Mapping
 from abogen.domain.metadata_helpers import normalize_metadata_map
 
 from abogen.domain.enums import Language
-from abogen.utils import get_internal_cache_path, get_user_settings_dir
+from abogen.utils import console_handler, get_internal_cache_path, get_user_settings_dir
 
 
 
@@ -32,9 +32,7 @@ STATE_VERSION = 8
 
 _JOB_LOGGER = logging.getLogger("abogen.jobs")
 if not _JOB_LOGGER.handlers:
-    handler = logging.StreamHandler(sys.stdout)
-    handler.setFormatter(logging.Formatter("%(asctime)s [%(levelname)s] %(message)s", "%Y-%m-%d %H:%M:%S"))
-    _JOB_LOGGER.addHandler(handler)
+    _JOB_LOGGER.addHandler(console_handler())
     _JOB_LOGGER.propagate = False
 _JOB_LOGGER.setLevel(logging.DEBUG)
 

plugins/kokoro/engine.py

@@ -73,17 +73,27 @@ def engine_language(lang: Language) -> str:
     return _KOKORO_LANG_MAP.get(lang, "a")
 
 
-def language_for_voice_id(voice_id: str) -> Language:
+def language_for_code(code: str | None) -> Language:
+    """Map a kokoro engine language code (single letter) to a Language enum.
+
+    Used to resolve legacy data such as old profile files that stored
+    kokoro letter codes. This is kokoro-specific knowledge that stays
+    inside the engine. Unparseable values fall back to EN_US.
+    """
+    letter = str(code or "").strip()[:1].lower()
+    if letter in _CODE_TO_LANGUAGE:
+        return _CODE_TO_LANGUAGE[letter]
+    return Language.EN_US
+
+
+def language_for_voice_id(voice_id: str | None) -> Language:
     """Determine which Language a voice belongs to from its voice ID.
 
     Kokoro voice IDs encode language as a prefix (e.g. "af_heart" → "a" → EN_US).
     This is kokoro-specific knowledge that stays inside the engine.
     Callers pass a voice ID string; the engine returns a Language enum.
     """
-    prefix = str(voice_id or "").strip()[:1].lower()
-    if prefix in _CODE_TO_LANGUAGE:
-        return _CODE_TO_LANGUAGE[prefix]
-    return Language.EN_US
+    return language_for_code(voice_id)
 
 
 class KokoroSession:

pyproject.toml

@@ -50,6 +50,7 @@ dependencies = [
   "num2words>=0.5.13",
   "httpx>=0.27.0",
   "PyQt6>=6.5.0",
+  "rich>=13.0.0",
 ]
 
 classifiers = [

tests/test_enums.py

@@ -119,7 +119,7 @@ class TestLanguage:
     def test_supports_subtitle_tokens(self):
         assert Language.EN_US.supports_subtitle_tokens is True
         assert Language.EN_GB.supports_subtitle_tokens is True
-        assert Language.ZH.supports_subtitle_tokens is False
+        assert Language.ZH.supports_subtitle_tokens is True
 
     def test_from_str_case_insensitive(self):
         assert Language.from_str("EN-US") == Language.EN_US
@@ -129,3 +129,8 @@ class TestLanguage:
     def test_from_str_invalid(self):
         with pytest.raises(ValueError, match="Invalid Language"):
             Language.from_str("en")
+
+    def test_kokoro_letter_codes_not_accepted_by_domain(self):
+        # Letter codes are kokoro-engine internals, not domain API.
+        with pytest.raises(ValueError):
+            Language.from_str("a")

tests/test_kokoro_plugin.py

@@ -196,3 +196,42 @@ class TestKokoroVoiceLister:
             assert isinstance(voice.tags, tuple)
             assert len(voice.tags) > 0
         engine.dispose()
+
+
+# ──────────────────────────────────────────────────────────────
+# Language mapping helpers
+# ──────────────────────────────────────────────────────────────
+
+class TestKokoroLanguageMapping:
+    """Language resolution helpers: the letter codes live in the engine only."""
+
+    def test_language_for_code(self) -> None:
+        from abogen.domain.enums import Language
+        from plugins.kokoro.engine import language_for_code
+
+        assert language_for_code("a") == Language.EN_US
+        assert language_for_code("b") == Language.EN_GB
+        assert language_for_code("e") == Language.ES
+        assert language_for_code("f") == Language.FR
+        assert language_for_code("h") == Language.HI
+        assert language_for_code("i") == Language.IT
+        assert language_for_code("j") == Language.JA
+        assert language_for_code("p") == Language.PT_BR
+        assert language_for_code("z") == Language.ZH
+
+    def test_language_for_code_fallbacks(self) -> None:
+        from abogen.domain.enums import Language
+        from plugins.kokoro.engine import language_for_code
+
+        assert language_for_code("x") == Language.EN_US
+        assert language_for_code("") == Language.EN_US
+
+    def test_language_for_voice_id(self) -> None:
+        from abogen.domain.enums import Language
+        from plugins.kokoro.engine import language_for_voice_id
+
+        assert language_for_voice_id("af_heart") == Language.EN_US
+        assert language_for_voice_id("bf_emma") == Language.EN_GB
+        assert language_for_voice_id("ef_dora") == Language.ES
+        assert language_for_voice_id("zf_xiaobei") == Language.ZH
+        assert language_for_voice_id("") == Language.EN_US

tests/test_pending_job_metadata.py

@@ -0,0 +1,49 @@
+import sys
+import types
+from pathlib import Path
+from types import SimpleNamespace
+
+
+_real_routes = sys.modules.get("abogen.webui.routes")
+# Import routes.utils.form without executing routes/__init__.py (which imports
+# every blueprint). Use a temporary namespace package, then restore the real
+# module so later tests can still `from abogen.webui.routes import ...`.
+routes_package = types.ModuleType("abogen.webui.routes")
+routes_package.__path__ = [
+    str(Path(__file__).parents[1] / "abogen" / "webui" / "routes")
+]
+sys.modules["abogen.webui.routes"] = routes_package
+
+from abogen.webui.routes.utils.form import (  # noqa: E402
+    build_pending_job_from_extraction,
+    load_settings,
+)
+
+if _real_routes is not None:
+    sys.modules["abogen.webui.routes"] = _real_routes
+else:
+    del sys.modules["abogen.webui.routes"]
+
+
+def test_user_metadata_overrides_extraction_fallback(tmp_path: Path) -> None:
+    extraction = SimpleNamespace(
+        chapters=[SimpleNamespace(title="Chapter 1", text="Text")],
+        metadata={"title": "423d828962c34d2b8a53bbe91176305a"},
+        cover_image=None,
+        cover_mime=None,
+        total_characters=4,
+        combined_text="Text",
+    )
+
+    result = build_pending_job_from_extraction(
+        stored_path=tmp_path / "book.txt",
+        original_name="book.txt",
+        extraction=extraction,
+        form={"meta_title": "My Book", "meta_author": "Ada Author"},
+        settings=load_settings(),
+        profiles={},
+    )
+
+    assert result.pending.metadata_tags["title"] == "My Book"
+    assert result.pending.metadata_tags["author"] == "Ada Author"
+    assert result.pending.metadata_tags["authors"] == "Ada Author"

tests/test_voice_profiles.py

@@ -0,0 +1,28 @@
+"""Tests for voice profile language resolution."""
+
+from __future__ import annotations
+
+from abogen.domain.enums import Language
+from abogen.voice_profiles import resolve_profile_language
+
+
+class TestResolveProfileLanguage:
+
+    def test_iso_code(self) -> None:
+        assert resolve_profile_language({"language": "en-US"}) == Language.EN_US
+        assert resolve_profile_language({"language": "es"}) == Language.ES
+
+    def test_enum_value(self) -> None:
+        assert resolve_profile_language({"language": Language.ZH}) == Language.ZH
+
+    def test_legacy_kokoro_letter(self) -> None:
+        assert resolve_profile_language({"language": "a"}) == Language.EN_US
+        assert resolve_profile_language({"language": "e"}) == Language.ES
+        assert resolve_profile_language({"language": "z"}) == Language.ZH
+
+    def test_missing_or_unparseable_falls_back(self) -> None:
+        assert resolve_profile_language({}) == Language.EN_US
+        assert resolve_profile_language({"language": ""}) == Language.EN_US
+        assert resolve_profile_language({"language": "xx"}) == Language.EN_US
+        assert resolve_profile_language(None) == Language.EN_US
+        assert resolve_profile_language([]) == Language.EN_US