upd4

app.py

@@ -1,46 +1,48 @@
-from fastapi import FastAPI
-
+from fastapi import FastAPI, WebSocket, WebSocketDisconnect
 import outetts
-import os
+import io
 
 # Initialize the interface
 interface = outetts.Interface(
     config=outetts.ModelConfig.auto_config(
         model=outetts.Models.VERSION_1_0_SIZE_1B,
-        # For llama.cpp backend
         backend=outetts.Backend.LLAMACPP,
         quantization=outetts.LlamaCppQuantization.FP16
-        # For transformers backend
-        #backend=outetts.Backend.HF,
     )
 )
 
 # Load the default speaker profile
 speaker = interface.load_default_speaker("EN-FEMALE-1-NEUTRAL")
 
-# Or create your own speaker profiles in seconds and reuse them instantly
-# speaker = interface.create_speaker("path/to/audio.wav")
-# interface.save_speaker(speaker, "speaker.json")
-# speaker = interface.load_speaker("speaker.json")
-
-# Generate speech
-output = interface.generate(
-    config=outetts.GenerationConfig(
-        text="Hello, how are you doing?",
-        generation_type=outetts.GenerationType.CHUNKED,
-        speaker=speaker,
-        sampler_config=outetts.SamplerConfig(
-            temperature=0.4
-        ),
-    )
-)
-
-# Save to file
-output_path = os.path.join(os.getcwd(),"output.wav")
-output.save(output_path)
-
 app = FastAPI()
 
 @app.get("/")
 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