app.py

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(
        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")

app = FastAPI()

@app.get("/")
def greet_json():
    return {"Hello": "World!"}

@app.post("/tts")
async def tts_endpoint(request: Request):
    """
    Accepts JSON {"text": "..."} and streams the generated audio as WAV.
    """
    try:
        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
                ),
            )
        )
        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.