app.py

import openai
import pyttsx3
import speech_recognition as sr

openai.api_key = "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"

#initialize engine (text to speech)
engine = pyttsx3.init() 

def transcribe_audio_to_tell(filename):
    recognizer = sr.Recognizer()
    with sr.Audiofile(filename) as source: 
        audio = recognizer.record(source)
    try:
        return recognizer.recognize_google(audio)
    except:
        print('Skipping unknown error')

def generate_response(prompt):
    response = openai.Completion.create(
        engine = "text-davinci-003",
        prompt = prompt,
        max_token = 4000,
        n = 1,
        stop = None,
        temperature = 0.5,
    )
    return response["choices"][0]["text"]

def speak_text(text):
    engine.say(text)
    engine.runAndWait()

def main():
    while True:
        print("say 'Genius' to start recording your question...")
        with sr.Microphone() as source:
            recognizer = sr.recognizer()
            audio = recognizer.listen(source)
            try:
                transcription = recognizer.recognize_google(audio)
                if transcription.lower() == "genius":
                #RECORD AUDIO
                    filename = "input.wav"
                    print("say your question")
                    with sr.Microphone() as source:
                        recognizer = sr,recognizer()
                        source.pause_threshold = 1
                        audio = recognizer.listen(source, phrase_time_limit = None, timeout = None)
                        with open(filename, "wb") as f:
                            f.write(audio.get_wav_data())

                #AUDIO TO TEXT
                text = transcribe_audio_to_tell(filename)
                if text:
                    print(f"you said: {text}")

                    #RESPONSE USING GPT
                    response = geneate_response(text)
                    print(f"GPT-3 says: {response}")

                    #RECORD AUDIO USING GTTS
                    tts = gTTS(text=response, lang='en')
                    tts.save("sample.mp3")

                    #RESPONSE FROM TEXT TO SPEECH
                    speak_text(response)
            except Exception as e:
                print("An error occured: {}".format(e))

if __name__=="__main__":
    main()