up11

Dockerfile

@@ -12,4 +12,5 @@ RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
 COPY --chown=user . /app
 
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+#CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--ws", "auto", "--allow-websocket-origin", "*"]

app.py

@@ -24,6 +24,35 @@ app = FastAPI()
 def greet_json():
     return {"Hello": "World!"}
 
+@app.websocket("/ws/tts")
+async def websocket_tts(websocket: WebSocket):
+    await websocket.accept()
+    try:
+        while True:
+            # Empfange Text-Chunk vom Client
+            data = await websocket.receive_text()
+            # Generiere Audio aus Text
+            output = interface.generate(
+                config=outetts.GenerationConfig(
+                    text=data,
+                    generation_type=outetts.GenerationType.CHUNKED,
+                    speaker=speaker,
+                    sampler_config=outetts.SamplerConfig(
+                        temperature=0.4
+                    ),
+                )
+            )
+            # Schreibe Audio in BytesIO
+            audio_buffer = io.BytesIO()
+            output.save(audio_buffer)
+            audio_bytes = audio_buffer.getvalue()
+            # Sende Audiodaten als Bytes zurück
+            await websocket.send_bytes(audio_bytes)
+    except WebSocketDisconnect:
+        pass
+
+
+'''
 @app.post("/tts")
 async def tts_endpoint(request: Request):
     """
@@ -56,5 +85,7 @@ async def tts_endpoint(request: Request):
         return StreamingResponse(audio_stream(), media_type="audio/wav")
     except Exception as e:
         return JSONResponse({"error": str(e)}, status_code=500)
+'''
+
 
 # WebSocket endpoint removed; use POST /tts for TTS requests.