main.py

from fastapi import FastAPI, File, UploadFile, HTTPException
from fastapi.responses import JSONResponse
import speech_recognition as sr
import os
import uuid

app = FastAPI()

UPLOAD_DIR = "uploads"
os.makedirs(UPLOAD_DIR, exist_ok=True)

@app.post("/voice-to-text")
async def voice_to_text(file: UploadFile = File(...)):
    # Check file type
    if not file.filename.endswith(".wav"):
        raise HTTPException(status_code=400, detail="Only .wav files are supported")

    # Save uploaded file
    temp_filename = os.path.join(UPLOAD_DIR, f"{uuid.uuid4()}.wav")
    with open(temp_filename, "wb") as f:
        f.write(await file.read())

    # Recognize speech
    recognizer = sr.Recognizer()
    try:
        with sr.AudioFile(temp_filename) as source:
            audio_data = recognizer.record(source)
            text = recognizer.recognize_google(audio_data)
            return JSONResponse(content={"text": text})
    except sr.UnknownValueError:
        raise HTTPException(status_code=400, detail="Speech not recognized")
    except sr.RequestError as e:
        raise HTTPException(status_code=500, detail=f"API error: {e}")
    finally:
        os.remove(temp_filename)