feat: support for faster-qwen3-tts backend server

1 files changed, 53 insertions, 10 deletions

diff --git a/audiobook.py b/audiobook.py
index 34806f2..ed92e53 100755
--- a/audiobook.py
+++ b/audiobook.py
@@ -37,6 +37,9 @@ Examples:
 
   # Use voice cloning with reference audio
   python audiobook.py --clone path/to/reference.wav
+
+  # Use the faster-qwen3-tts server (voice cloning, configured server-side)
+  python audiobook.py --faster
         """
     )
 
@@ -96,27 +99,65 @@ Examples:
               "Ignored for m4b, which is always a single file.")
     )
 
+    parser.add_argument(
+        "--faster",
+        action="store_true",
+        help=("Use a faster-qwen3-tts OpenAI-compatible server instead of the Qwen "
+              "Gradio demos (5-10x faster inference via CUDA graphs). Always voice "
+              "cloning: the reference audio and transcript are configured on the "
+              "server itself (see the 'Faster backend' section of the README).")
+    )
+
+    parser.add_argument(
+        "--faster-voice",
+        type=str,
+        default=None,
+        metavar="NAME",
+        help=("Voice entry to request from the faster server's voice config "
+              "(default: the FASTER_TTS_VOICE setting in converter/config.py, "
+              "typically 'default'). Must match a key in the server's voices.json, "
+              "or 'default' when the server was started with --ref-audio.")
+    )
+
     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")
+    if args.faster:
+        if args.clone:
+            print("[WARNING] --clone is ignored with --faster: the faster backend "
+                  "always uses voice cloning, and the reference voice is configured "
+                  "on the faster server (see README)")
+            args.clone = None
+        if args.transcription or args.no_transcription:
+            print("[WARNING] --transcription/--no-transcription are ignored with "
+                  "--faster: the reference transcript is configured on the faster "
+                  "server (--ref-text or voices.json, see README)")
+            args.transcription = None
+            args.no_transcription = False
+        if args.language is not None:
+            print("[WARNING] --language is ignored with --faster: language is "
+                  "configured on the faster server (see README)")
+            args.language = None
+    else:
+        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_mode=config.VOICE_MODE_CLONE if (args.clone or args.faster)
+            else config.VOICE_MODE_CUSTOM,
             voice_clone_ref_audio=args.clone,
             voice_clone_ref_text=args.transcription,
             skip_transcription=args.no_transcription,
@@ -124,6 +165,8 @@ Examples:
             single_file=args.single_file,
             output_format=args.format,
             language=args.language,
+            faster=args.faster,
+            faster_voice=args.faster_voice,
         )
         ok = converter.run()
     except KeyboardInterrupt: