utils/stt.py

import speech_recognition as sr

def speech_to_text(audio_path):
    recognizer = sr.Recognizer()
    with sr.AudioFile(audio_path) as source:
        audio_data = recognizer.record(source)
        try:
            return recognizer.recognize_google(audio_data)
        except sr.UnknownValueError:
            return "Sorry, I could not understand your request."