feat: support for faster-qwen3-tts backend server

1 files changed, 46 insertions, 26 deletions

diff --git a/converter/converter.py b/converter/converter.py
index 4d20083..ec06bbb 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, normalize_language, speaker_display_name
+from .tts import FasterTTSClient, QwenTTSClient, normalize_language, speaker_display_name
 
 logger = logging.getLogger(__name__)
 
@@ -89,7 +89,8 @@ 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 = config.AUDIO_FORMAT,
-                 language: Optional[str] = None):
+                 language: Optional[str] = None, faster: bool = False,
+                 faster_voice: 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:
@@ -103,14 +104,21 @@ class AudiobookConverter:
         self.speed = speed
         self.single_file = single_file
         self.output_format = output_format
+        self.faster = faster
+        self.faster_voice = faster_voice
         self._validate_configuration()
-        self.tts = QwenTTSClient(
-            voice_mode=voice_mode,
-            voice_clone_ref_audio=voice_clone_ref_audio,
-            voice_clone_ref_text=voice_clone_ref_text,
-            skip_transcription=skip_transcription,
-            language=self.language,
-        )
+        if faster:
+            # The faster backend always voice-clones using a reference voice
+            # configured on the server, so no local reference audio is needed.
+            self.tts = FasterTTSClient(voice=faster_voice)
+        else:
+            self.tts = QwenTTSClient(
+                voice_mode=voice_mode,
+                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:
         """Validate configuration settings."""
@@ -119,7 +127,7 @@ class AudiobookConverter:
                 f"Unknown voice mode: {self.voice_mode!r} "
                 f"(expected one of {config.VOICE_MODES})"
             )
-        if self.voice_mode == config.VOICE_MODE_CLONE:
+        if self.voice_mode == config.VOICE_MODE_CLONE and not self.faster:
             if not self.voice_clone_ref_audio:
                 raise ValueError(
                     "Voice Clone mode requires a reference audio file. "
@@ -142,10 +150,13 @@ class AudiobookConverter:
         """Narrator name used in output file names.
 
         Custom voice mode uses the built-in speaker's display name; voice
-        clone mode uses the reference audio file's stem. Spaces become
-        underscores (e.g. "Uncle Fu" -> "Uncle_Fu").
+        clone mode uses the reference audio file's stem; the faster backend
+        uses the server-side voice name. Spaces become underscores
+        (e.g. "Uncle Fu" -> "Uncle_Fu").
         """
-        if self.voice_mode == config.VOICE_MODE_CLONE:
+        if self.faster:
+            narrator = self.faster_voice or config.FASTER_TTS_VOICE
+        elif self.voice_mode == config.VOICE_MODE_CLONE:
             narrator = Path(self.voice_clone_ref_audio).stem
         else:
             narrator = speaker_display_name()
@@ -371,24 +382,29 @@ class AudiobookConverter:
             logger.error(traceback.format_exc())
             return False
 
-    def run(self) -> bool:
-        """Main conversion process. Returns True if all books converted."""
-        api_url = config.VOICE_CLONE_API_URL if self.voice_mode == config.VOICE_MODE_CLONE else config.QWEN_API_URL
-
+    def _print_banner(self) -> None:
+        """Print the startup summary for the selected backend."""
         print("=" * 70)
         print("QWEN-BASED AUDIOBOOK CONVERTER")
         print("=" * 70)
         print(f"Books folder: {config.BOOKS_FOLDER}")
         print(f"Output folder: {config.AUDIOBOOKS_FOLDER}")
-        print(f"Qwen API endpoint: {api_url}")
-        print(f"Voice mode: {self.voice_mode}")
-        print("Model size: 1.7B (always)")
-        if self.voice_mode == config.VOICE_MODE_CUSTOM:
-            print(f"Speaker: {config.CUSTOM_VOICE_SPEAKER}")
-            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: {self.language}")
+        if self.faster:
+            print(f"Faster TTS endpoint: {config.FASTER_TTS_API_URL}")
+            print("Backend: faster (voice cloning, reference configured on server)")
+            print(f"Voice: {self.faster_voice or config.FASTER_TTS_VOICE}")
+        else:
+            api_url = (config.VOICE_CLONE_API_URL if self.voice_mode == config.VOICE_MODE_CLONE
+                       else config.QWEN_API_URL)
+            print(f"Qwen API endpoint: {api_url}")
+            print(f"Voice mode: {self.voice_mode}")
+            print("Model size: 1.7B (always)")
+            if self.voice_mode == config.VOICE_MODE_CUSTOM:
+                print(f"Speaker: {config.CUSTOM_VOICE_SPEAKER}")
+                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: {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)")
@@ -396,6 +412,10 @@ class AudiobookConverter:
             print(f"Playback speed: {self.speed:g}x")
         print("=" * 70)
 
+    def run(self) -> bool:
+        """Main conversion process. Returns True if all books converted."""
+        self._print_banner()
+
         # Check for books
         book_files = sorted(
             f for f in config.BOOKS_FOLDER.iterdir()