Fix Piper 1.2+ synthesize API: handle single-speaker models (no sid input)

main.py

@@ -12,23 +12,28 @@ from pathlib import Path
 
 app = FastAPI(title="Piper TTS Space")
 
-# Voice model info: (lang, model_name, url_onnx, url_json)
+# Voice model info: (lang, model_name, url_onnx, url_json, is_multi_speaker)
 VOICE_MODELS = {
     "zh": ("zh_CN-huayan-medium", 
            "https://huggingface.co/rhasspy/piper-voices/resolve/main/zh/zh_CN/huayan/medium/zh_CN-huayan-medium.onnx",
-           "https://huggingface.co/rhasspy/piper-voices/resolve/main/zh/zh_CN/huayan/medium/zh_CN-huayan-medium.onnx.json"),
+           "https://huggingface.co/rhasspy/piper-voices/resolve/main/zh/zh_CN/huayan/medium/zh_CN-huayan-medium.onnx.json",
+           False),
     "en": ("en_US-lessac-medium",
            "https://huggingface.co/rhasspy/piper-voices/resolve/main/en/en_US/lessac/medium/en_US-lessac-medium.onnx",
-           "https://huggingface.co/rhasspy/piper-voices/resolve/main/en/en_US/lessac/medium/en_US-lessac-medium.onnx.json"),
+           "https://huggingface.co/rhasspy/piper-voices/resolve/main/en/en_US/lessac/medium/en_US-lessac-medium.onnx.json",
+           False),
     "ms": ("ms_MY-sirius-medium",
            "https://huggingface.co/rhasspy/piper-voices/resolve/main/ms/ms_MY/sirius/medium/ms_MY-sirius-medium.onnx",
-           "https://huggingface.co/rhasspy/piper-voices/resolve/main/ms/ms_MY/sirius/medium/ms_MY-sirius-medium.onnx.json"),
+           "https://huggingface.co/rhasspy/piper-voices/resolve/main/ms/ms_MY/sirius/medium/ms_MY-sirius-medium.onnx.json",
+           False),
     "ja": ("ja_JP-kenji-medium",
            "https://huggingface.co/rhasspy/piper-voices/resolve/main/ja/ja_JP/kenji/medium/ja_JP-kenji-medium.onnx",
-           "https://huggingface.co/rhasspy/piper-voices/resolve/main/ja/ja_JP/kenji/medium/ja_JP-kenji-medium.onnx.json"),
+           "https://huggingface.co/rhasspy/piper-voices/resolve/main/ja/ja_JP/kenji/medium/ja_JP-kenji-medium.onnx.json",
+           False),
     "ko": ("ko_KR-hui-hao-medium",
            "https://huggingface.co/rhasspy/piper-voices/resolve/main/ko/ko_KR/hui_hao/medium/ko_KR-hui-hao-medium.onnx",
-           "https://huggingface.co/rhasspy/piper-voices/resolve/main/ko/ko_KR/hui_hao/medium/ko_KR-hui-hao-medium.onnx.json"),
+           "https://huggingface.co/rhasspy/piper-voices/resolve/main/ko/ko_KR/hui_hao/medium/ko_KR-hui-hao-medium.onnx.json",
+           False),
 }
 
 MODEL_DIR = Path("/tmp/piper_models")
@@ -51,7 +56,7 @@ def get_voice(lang: str) -> PiperVoice:
     if lang not in VOICE_MODELS:
         raise ValueError(f"Language '{lang}' not available. Available: {list(VOICE_MODELS.keys())}")
     
-    model_name, url_onnx, url_json = VOICE_MODELS[lang]
+    model_name, url_onnx, url_json, _ = VOICE_MODELS[lang]
     onnx_path = MODEL_DIR / f"{model_name}.onnx"
     json_path = MODEL_DIR / f"{model_name}.onnx.json"
     
@@ -91,13 +96,19 @@ async def tts(request: TTSRequest):
         raise HTTPException(400, f"Voice load failed: {str(e)}")
     
     try:
+        # Check if model supports multi-speaker
+        _, _, _, is_multi_speaker = VOICE_MODELS[request.lang]
+        
         # Piper 1.2+ requires wav_file parameter - use wave.open with BytesIO
         buffer = BytesIO()
         with wave.open(buffer, 'wb') as wav_file:
             wav_file.setnchannels(1)
             wav_file.setsampwidth(2)  # 16-bit
             wav_file.setframerate(request.sample_rate)
-            voice.synthesize(request.text, speaker_id=request.speaker_id, wav_file=wav_file)
+            if is_multi_speaker:
+                voice.synthesize(request.text, speaker_id=request.speaker_id, wav_file=wav_file)
+            else:
+                voice.synthesize(request.text, wav_file=wav_file)
         buffer.seek(0)
         return Response(
             content=buffer.read(),
@@ -105,6 +116,23 @@ async def tts(request: TTSRequest):
             headers={"Content-Disposition": f"attachment; filename=tts_{uuid.uuid4().hex}.wav"}
         )
     except Exception as e:
+        # Fallback: try without speaker_id if it fails
+        if "sid" in str(e) or "speaker" in str(e).lower():
+            try:
+                buffer = BytesIO()
+                with wave.open(buffer, 'wb') as wav_file:
+                    wav_file.setnchannels(1)
+                    wav_file.setsampwidth(2)
+                    wav_file.setframerate(request.sample_rate)
+                    voice.synthesize(request.text, wav_file=wav_file)
+                buffer.seek(0)
+                return Response(
+                    content=buffer.read(),
+                    media_type="audio/wav",
+                    headers={"Content-Disposition": f"attachment; filename=tts_{uuid.uuid4().hex}.wav"}
+                )
+            except Exception as e2:
+                raise HTTPException(500, f"Synthesis failed (fallback): {str(e2)}")
         raise HTTPException(500, f"Synthesis failed: {str(e)}")
 
 @app.get("/health")