feat: language parameter for potential accent tuning

1 files changed, 141 insertions, 0 deletions

diff --git a/audiobook.py b/audiobook.py
new file mode 100755
index 0000000..34806f2
--- /dev/null
+++ b/audiobook.py
@@ -0,0 +1,141 @@
+#!/usr/bin/env python3
+"""
+Qwen-Based Audiobook Converter
+Converts TXT, PDF and EPUB files into audiobooks using a local Qwen3-TTS server.
+
+Edit converter/config.py to change voice and processing settings.
+
+License: MIT
+"""
+
+import argparse
+import sys
+import traceback
+
+# Fix Windows console encoding for unicode output
+if sys.platform == "win32":
+    try:
+        sys.stdout.reconfigure(encoding="utf-8")
+        sys.stderr.reconfigure(encoding="utf-8")
+    except AttributeError:
+        pass
+
+from converter import config
+from converter.converter import AudiobookConverter, setup_directories, setup_logging
+from converter.tts import normalize_language
+
+
+def main() -> None:
+    """Entry point with argparse."""
+    parser = argparse.ArgumentParser(
+        description="Convert books to audiobooks using the Qwen3-TTS voice model",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  # Use custom voice (default - Vivian speaker)
+  python audiobook.py
+
+  # Use voice cloning with reference audio
+  python audiobook.py --clone path/to/reference.wav
+        """
+    )
+
+    parser.add_argument(
+        "--clone",
+        type=str,
+        metavar="PATH",
+        help=("Path to reference audio file for voice cloning (WAV format). "
+              "Passing this flag switches the converter to voice clone mode.")
+    )
+
+    parser.add_argument(
+        "--transcription",
+        type=str,
+        default=None,
+        help=("Transcript of the reference audio for in-context cloning (recommended for "
+              "highest quality). If omitted, a local Whisper backend is used if installed; "
+              "otherwise the converter falls back to x-vector-only mode.")
+    )
+
+    parser.add_argument(
+        "--no-transcription",
+        action="store_true",
+        help=("Skip automatic transcription of the reference audio (use x-vector-only "
+              "cloning). Ignored when --transcription is provided.")
+    )
+
+    parser.add_argument(
+        "--language",
+        type=str,
+        default=None,
+        metavar="LANG",
+        help=("Output language for the synthesized speech, e.g. English, Japanese, "
+              "or Auto (language names and short codes like en/ja are accepted). "
+              "Defaults to the mode's setting in converter/config.py (English).")
+    )
+
+    parser.add_argument(
+        "--speed",
+        type=float,
+        default=1.0,
+        help="Playback speed factor for the final audiobook (1.0 = normal). Pitch-preserving."
+    )
+
+    parser.add_argument(
+        "--format",
+        choices=list(config.AUDIO_FORMATS),
+        default=config.AUDIO_FORMAT,
+        help=f"Output container format (default: {config.AUDIO_FORMAT}). m4b uses AAC audio."
+    )
+
+    parser.add_argument(
+        "--single-file",
+        action="store_true",
+        help=("Combine all chapters into a single audio file. By default books with "
+              "chapters (e.g. EPUB) are converted to one file per chapter. "
+              "Ignored for m4b, which is always a single file.")
+    )
+
+    args = parser.parse_args()
+
+    if args.speed <= 0:
+        parser.error(f"--speed must be a positive number (got {args.speed:g})")
+
+    if args.language is not None:
+        try:
+            args.language = normalize_language(args.language)
+        except ValueError as exc:
+            parser.error(str(exc))
+
+    if not args.clone and (args.transcription or args.no_transcription):
+        print("[WARNING] --transcription/--no-transcription "
+              "are ignored without --clone")
+
+    setup_logging()
+    setup_directories()
+
+    try:
+        converter = AudiobookConverter(
+            voice_mode=config.VOICE_MODE_CLONE if args.clone else config.VOICE_MODE_CUSTOM,
+            voice_clone_ref_audio=args.clone,
+            voice_clone_ref_text=args.transcription,
+            skip_transcription=args.no_transcription,
+            speed=args.speed,
+            single_file=args.single_file,
+            output_format=args.format,
+            language=args.language,
+        )
+        ok = converter.run()
+    except KeyboardInterrupt:
+        print("\n[WARNING] Shutdown requested by user")
+        sys.exit(130)
+    except Exception as exc:
+        print(f"[FATAL] Fatal error: {exc}")
+        traceback.print_exc()
+        sys.exit(1)
+
+    sys.exit(0 if ok else 1)
+
+
+if __name__ == "__main__":
+    main()