feat: language parameter for potential accent tuning

1 files changed, 11 insertions, 5 deletions

diff --git a/converter/converter.py b/converter/converter.py
index 6d09e09..29d3bc4 100644
--- a/converter/converter.py
+++ b/converter/converter.py
@@ -13,7 +13,7 @@ from typing import Dict, List, Optional, Tuple
 
 from . import audio, chunking, config, cover, extractors
 from .audio import TrackMeta
-from .tts import QwenTTSClient
+from .tts import QwenTTSClient, normalize_language
 
 logger = logging.getLogger(__name__)
 
@@ -88,11 +88,16 @@ class AudiobookConverter:
 
     def __init__(self, voice_mode: str = config.VOICE_MODE_CUSTOM, voice_clone_ref_audio: Optional[str] = None,
                  voice_clone_ref_text: Optional[str] = None, skip_transcription: bool = False,
-                 speed: float = 1.0, single_file: bool = False, output_format: str = "mp3"):
+                 speed: float = 1.0, single_file: bool = False, output_format: str = config.AUDIO_FORMAT,
+                 language: Optional[str] = None):
         if speed <= 0:
             raise ValueError(f"Speed must be a positive number, got {speed}")
         if output_format not in config.AUDIO_FORMATS:
             raise ValueError(f"Unsupported output format: {output_format}")
+        if language is None:
+            language = (config.VOICE_CLONE_LANGUAGE if voice_mode == config.VOICE_MODE_CLONE
+                        else config.CUSTOM_VOICE_LANGUAGE)
+        self.language = normalize_language(language)
         self.voice_mode = voice_mode
         self.voice_clone_ref_audio = voice_clone_ref_audio
         self.speed = speed
@@ -104,6 +109,7 @@ class AudiobookConverter:
             voice_clone_ref_audio=voice_clone_ref_audio,
             voice_clone_ref_text=voice_clone_ref_text,
             skip_transcription=skip_transcription,
+            language=self.language,
         )
 
     def _validate_configuration(self) -> None:
@@ -117,7 +123,7 @@ class AudiobookConverter:
             if not self.voice_clone_ref_audio:
                 raise ValueError(
                     "Voice Clone mode requires a reference audio file. "
-                    "Use --voice-sample <path> to specify it."
+                    "Use --clone <path> to specify it."
                 )
 
             if not Path(self.voice_clone_ref_audio).exists():
@@ -366,10 +372,10 @@ class AudiobookConverter:
         print("Model size: 1.7B (always)")
         if self.voice_mode == config.VOICE_MODE_CUSTOM:
             print(f"Speaker: {config.CUSTOM_VOICE_SPEAKER}")
-            print(f"Language: {config.CUSTOM_VOICE_LANGUAGE}")
+            print(f"Language: {self.language}")
         elif self.voice_mode == config.VOICE_MODE_CLONE:
             print(f"Reference audio: {Path(self.voice_clone_ref_audio).name}")
-            print(f"Language: {config.VOICE_CLONE_LANGUAGE}")
+            print(f"Language: {self.language}")
         print(f"Output format: {self.output_format}")
         if self.single_file and self.output_format != "m4b":
             print("Chapter mode: single file (--single-file)")