from fastapi import FastAPI, UploadFile, File, HTTPException 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 for .wav file if not file.filename.endswith(".wav"): raise HTTPException(status_code=400, detail="Only .wav files are supported") # Save uploaded file file_path = os.path.join(UPLOAD_DIR, f"{uuid.uuid4()}.wav") with open(file_path, "wb") as f: f.write(await file.read()) # Speech recognition recognizer = sr.Recognizer() try: with sr.AudioFile(file_path) as source: audio_data = recognizer.record(source) recognized_text = recognizer.recognize_google(audio_data) return {"recognized_text": recognized_text} except sr.UnknownValueError: raise HTTPException(status_code=400, detail="Could not understand audio") except sr.RequestError as e: raise HTTPException(status_code=500, detail=f"Speech API error: {e}") finally: os.remove(file_path)