app.py

import speech_recognition as sr
from gtts import gTTS
from playsound import playsound


def speech_to_text():
    recognizer = sr.Recognizer()

    with sr.Microphone() as source:
        print("Speak something...")
        audio = recognizer.listen(source)

        try:
            user_input = recognizer.recognize_google(audio)
            return user_input
        except sr.UnknownValueError:
            print("Sorry, could not understand audio.")
            return None
        except sr.RequestError as e:
            print("Could not request results; {0}".format(e))
            return None


def text_to_speech(text):
    tts = gTTS(text=text, lang='en')
    tts.save("output.mp3")
    playsound("output.mp3")


def main():
    user_input = speech_to_text()
    if user_input:
        print("You said:", user_input)
        text_to_speech(user_input)


if __name__ == "__main__":
    main()