import speech_recognition as sr
from gtts import gTTS
import pygame
import openai
import os

# Initialize the OpenAI API with your key
openai.api_key = 'sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx'

def recognize_speech_from_mic(recognizer, microphone):
    """Capture speech from the microphone and convert it to text."""
    with microphone as source:
        recognizer.adjust_for_ambient_noise(source)
        audio = recognizer.listen(source)
        
    try:
        return recognizer.recognize_google(audio)
    except sr.RequestError:
        # API was unreachable or unresponsive
        return "API unavailable"
    except sr.UnknownValueError:
        # Speech was unintelligible
        return "Unable to recognize speech"

def get_openai_response(text):
    backoff_time = 1
    while True:
        try:
            response = openai.chat.completions.create(
                model="gpt-3.5-turbo",
                messages=[
                    {"role": "system", "content": "You are a helpful assistant."},
                    {"role": "user", "content": text},
                ]
            )
            response_text = response.choices[0].message.content
            print("Robot: " + response_text)
            return response_text
        except openai.RateLimitError:
            print("Rate limit exceeded, waiting for " + str(backoff_time) +" seconds.")
            time.sleep(backoff_time)
            backoff_time *= 2
            
def speak(text):
    """Convert text to speech and play it."""
    tts = gTTS(text=text, lang='en')
    tts.save("response.mp3")
    pygame.mixer.init()
    pygame.mixer.music.load("response.mp3")
    pygame.mixer.music.play()
    while pygame.mixer.music.get_busy():  # wait for audio to finish playing
        continue
    os.remove("response.mp3")

def start_chat():
    recognizer = sr.Recognizer()
    microphone = sr.Microphone(device_index=12)
    speak("Hello, I'm Robot, what is your questions?")
    while True:
        print("Say something!")
        speech_text = recognize_speech_from_mic(recognizer, microphone)
        if speech_text not in ["API unavailable", "Unable to recognize speech"]:
            if speech_text.upper() != "GOODBYE": #.find("GOOD BYE") != -1:
                response_text = get_openai_response(speech_text)
                speak(response_text)
            else:
            	speak("Bye bye!")
            	return

if __name__ == "__main__":
    start_chat()