capture_speech

import speech_recognition as sr
from text_to_speech import text_to_speech #a different module, but you can guess what it does
import pygame

pygame.mixer.init()

def capture_speech():
    r = sr.Recognizer()
    with sr.Microphone() as source:                # use the default microphone as the audio source
        pygame.mixer.Sound("open_mic.wav").play()  #play a prompt sound so that the user knows that they can speak
        audio = r.listen(source)                   # listen for the first phrase and extract it into audio data

    try:
        text = r.recognize_google(audio)          #the speech recongition library in python lets you swap out for google or whisper

    except:                            # if speech is unintelligible or absent
        text_to_speech('I did not hear that. Please try again.')
        text = capture_speech()

    return text


if __name__ == "__main__":
    text = capture_speech()
    print(text)