Add default voice for each language (#180)

Fix https://github.com/kyutai-labs/pocket-tts/issues/166

pocket_tts/default_parameters.py

@@ -1,4 +1,3 @@
-DEFAULT_AUDIO_PROMPT = "alba"
 DEFAULT_LANGUAGE = "english"
 DEFAULT_TEMPERATURE = 0.7
 DEFAULT_LSD_DECODE_STEPS = 1
@@ -41,9 +40,25 @@ DEFAULT_TEXT_FOR_LANGUAGE = {
     ),
 }
 
+DEFAULT_VOICE_FOR_LANGUAGE = {
+    "italian": "giovanni",
+    "spanish": "lola",
+    "german": "juergen",
+    "portuguese": "rafael",
+    "french": "estelle",
+}
+DEFAULT_VOICE_FALLBACK = "alba"
+
 
 def get_default_text_for_language(language: str | None) -> str:
     for key, text in DEFAULT_TEXT_FOR_LANGUAGE.items():
         if language is not None and key in language:
             return text
     return DEFAULT_TEXT_FOR_LANGUAGE[DEFAULT_LANGUAGE]
+
+
+def get_default_voice_for_language(language: str | None) -> str:
+    for key, voice in DEFAULT_VOICE_FOR_LANGUAGE.items():
+        if language is not None and key in language:
+            return voice
+    return DEFAULT_VOICE_FALLBACK

pocket_tts/main.py

@@ -16,7 +16,6 @@ from typing_extensions import Annotated
 
 from pocket_tts.data.audio import stream_audio_chunks
 from pocket_tts.default_parameters import (
-    DEFAULT_AUDIO_PROMPT,
     DEFAULT_EOS_THRESHOLD,
     DEFAULT_FRAMES_AFTER_EOS,
     DEFAULT_LSD_DECODE_STEPS,
@@ -24,6 +23,7 @@ from pocket_tts.default_parameters import (
     DEFAULT_TEMPERATURE,
     MAX_TOKEN_PER_CHUNK,
     get_default_text_for_language,
+    get_default_voice_for_language,
 )
 from pocket_tts.models.tts_model import TTSModel, export_model_state
 from pocket_tts.utils.logging_utils import enable_logging
@@ -136,7 +136,7 @@ def text_to_speech(
         raise HTTPException(status_code=400, detail="Text cannot be empty")
 
     if voice_url is None and voice_wav is None:
-        voice_url = DEFAULT_AUDIO_PROMPT
+        voice_url = get_default_voice_for_language(str(tts_model.origin))
 
     if voice_url is not None and voice_wav is not None:
         raise HTTPException(status_code=400, detail="Cannot provide both voice_url and voice_wav")
@@ -223,8 +223,17 @@ def serve(
 def generate(
     text: Annotated[str, typer.Option(help="Text to generate")] = None,
     voice: Annotated[
-        str, typer.Option(help="Path to audio conditioning file (voice to clone)")
-    ] = DEFAULT_AUDIO_PROMPT,
+        str | None,
+        typer.Option(
+            help=(
+                "Path to audio conditioning file (voice to clone). "
+                "Defaults to a built-in voice chosen from the language: "
+                "'giovanni' for italian, 'lola' for spanish, 'juergen' for german, "
+                "'rafael' for portuguese, 'estelle' for french, 'alba' otherwise."
+            ),
+            show_default=False,
+        ),
+    ] = None,
     quiet: Annotated[bool, typer.Option("-q", "--quiet", help="Disable logging output")] = False,
     language: Annotated[
         str | None,
@@ -293,6 +302,8 @@ def generate(
         )
         tts_model.to(device)
 
+        if voice is None:
+            voice = get_default_voice_for_language(language)
         model_state_for_voice = tts_model.get_state_for_audio_prompt(voice)
         # Stream audio generation directly to file or stdout
         audio_chunks = tts_model.generate_audio_stream(

pocket_tts/models/tts_model.py

@@ -295,7 +295,7 @@ class TTSModel(nn.Module):
         if language is not None:
             if language == "french":
                 raise ValueError(
-                    "The french model is not ready yet, please use 'french_24l' instead."
+                    "For technical reasons, only a larger 24-layer model is available for French. Please use the 'french_24l' language instead."
                 )
             config = CONFIGS_DIR / f"{language}.yaml"
         config = Path(config)

pocket_tts/static/index.html

@@ -40,13 +40,15 @@
                 id="voice-url-input"
                 class="w-full border rounded p-2"
                 placeholder="hf://kyutai/tts-voices/alba-mackenna/casual.wav"
-                value="alba"
             />
             <p class="text-xs text-gray-500 mt-1">
                 Supports: http://, https://, or hf:// URLs.<br>
-                You can also use predefined voices:<br>
-                "alba", "anna", "azelma", "bill_boerst", "caro_davy", "charles", "eponine", "eve",
-                "fantine", "george", "jane", "jean", "mary", "michael", "paul", "peter_yearsley", "stuart_bell", "vera".
+                You can also use predefined voices (language code in parentheses):<br>
+                "alba" (en), "anna" (en), "azelma" (en), "bill_boerst" (en), "caro_davy" (en),
+                "charles" (en), "cosette" (en), "eponine" (en), "eve" (en), "fantine" (en),
+                "george" (en),  "jane" (en), "javert" (en), "jean" (en),
+                "marius" (en), "mary" (en), "michael" (en), "paul" (en),
+                "peter_yearsley" (en), "stuart_bell" (en), "vera" (en), "giovanni" (it), "lola" (es), "juergen" (de), "rafael" (pt), "estelle" (fr).
                 <br/>
                 You can find more voices in our
                 <a

pocket_tts/utils/utils.py

@@ -34,11 +34,16 @@ _ORIGINS_OF_PREDEFINED_VOICES = {
     "peter_yearsley": "hf://kyutai/tts-voices/voice-zero/peter_yearsley.wav",
     "stuart_bell": "hf://kyutai/tts-voices/voice-zero/stuart_bell.wav",
     "caro_davy": "hf://kyutai/tts-voices/voice-zero/caro_davy.wav",
+    "giovanni": "hf://kyutai/pocket-tts/common_voice_it_36520747-enhanced-v2.mp3@64ab7d24c479d736a83b8cc666c4a776fca30fda",
+    "lola": "hf://kyutai/pocket-tts/common_voice_es_19762977-enhanced-v2.mp3@64ab7d24c479d736a83b8cc666c4a776fca30fda",
+    "juergen": "hf://kyutai/pocket-tts/de-DE-juergen.mp3@64ab7d24c479d736a83b8cc666c4a776fca30fda",
+    "rafael": "hf://kyutai/pocket-tts/g-Vi8PgmSY0-enhanced-v2.wav@64ab7d24c479d736a83b8cc666c4a776fca30fda",
+    "estelle": "hf://kyutai/tts-voices/unmute-prod-website/developpeuse-3.wav@1fc7395b7e012e2bbebfca14b942a4ef62ccc899",
 }
 
 
 def get_predefined_voice(language: str, name: str) -> str:
-    return f"hf://kyutai/pocket-tts-without-voice-cloning/languages/{language}/embeddings/{name}.safetensors@d29db7978e464fb90cb3359ee0c69a273b9142cc"
+    return f"hf://kyutai/pocket-tts-without-voice-cloning/languages/{language}/embeddings/{name}.safetensors@e041936c75475d350b405bc870bcf7c22da4e9e6"
 
 
 def make_cache_directory() -> Path: