up10

app.py

@@ -1,7 +1,8 @@
-from fastapi import FastAPI, WebSocket, WebSocketDisconnect
+from fastapi import FastAPI, Request
+from fastapi.responses import StreamingResponse, JSONResponse
 import outetts
 import io
-
+import json
 # Initialize the interface
 interface = outetts.Interface(
     config=outetts.ModelConfig.auto_config(
@@ -23,29 +24,37 @@ app = FastAPI()
 def greet_json():
     return {"Hello": "World!"}
 
-@app.websocket("/ws/tts")
-async def websocket_tts(websocket: WebSocket):
-    await websocket.accept()
+@app.post("/tts")
+async def tts_endpoint(request: Request):
+    """
+    Accepts JSON {"text": "..."} and streams the generated audio as WAV.
+    """
     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
-                    ),
-                )
+        data = await request.json()
+        text = data.get("text")
+        if not text:
+            return JSONResponse({"error": "Missing 'text' in request"}, status_code=400)
+
+        # Generate audio from text
+        output = interface.generate(
+            config=outetts.GenerationConfig(
+                text=text,
+                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
+        )
+        audio_buffer = io.BytesIO()
+        output.save(audio_buffer)
+        audio_buffer.seek(0)
+
+        def audio_stream():
+            yield audio_buffer.read()
+
+        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.