app.py

from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from TTS.api import TTS
import torch

app = FastAPI()

# Initialize the TTS model
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2")
device = "cuda" if torch.cuda.is_available() else "cpu"
tts.to(device)

# Get available voices and languages
available_voices = tts.list_speakers()
available_languages = tts.list_languages()

class TextToSpeechRequest(BaseModel):
    text: str
    voice: str
    language: str

@app.get("/voices")
def get_voices():
    return {"voices": available_voices}

@app.get("/languages")
def get_languages():
    return {"languages": available_languages}

@app.post("/generate")
def generate_speech(request: TextToSpeechRequest):
    if request.voice not in available_voices:
        raise HTTPException(status_code=400, detail="Invalid voice selected")
    if request.language not in available_languages:
        raise HTTPException(status_code=400, detail="Invalid language selected")

    output_path = "output.wav"
    tts.tts_to_file(text=request.text, speaker=request.voice, language=request.language, file_path=output_path)
    return {"message": "Speech generated successfully", "file_path": output_path}