A british voice assistant natural speech frontend to GPT-3

jarvis.py

"""
GPT-3 British Voice Assistant

This project is a simple voice assistant that takes your natural speech as input
and returns a response generated by the GPT-3 AI model. The response is then
read out loud with a British accent.

Installation:

1. Create a virtual environment and activate it:

    python -m venv venv
    source venv/bin/activate  # Linux/Mac
    venv\Scripts\activate  # Windows

2. Install the required packages:

    pip install -r requirements.txt

3. Set your OpenAI API key as an environment variable:

    export OPENAI_API_KEY="your_api_key_here"  # Linux/Mac
    set OPENAI_API_KEY="your_api_key_here"  # Windows

Finding the Audio Device Index:

Before running the script, you need to find the correct audio device index
for your microphone. Run the following Python script:

    import speech_recognition as sr

    for index, name in enumerate(sr.Microphone.list_microphone_names()):
        print(f"Microphone with name \"{name}\" found for `Microphone(device_index={index})`")

This will display a list of available microphones and their corresponding
device indices. Note the device index for the microphone you want to use.

Running the Voice Assistant:

1. Open the script and replace the `device_index` variable in the `speech_to_text()`
   function with your desired device index:

    device_index = YOUR_DESIRED_DEVICE_INDEX  # Replace with the desired device index

2. Run the script:

    python voice_assistant.py

The voice assistant will now listen for your questions and provide responses
generated by the GPT-4 AI model.

To exit the script, press `Ctrl + C` in the terminal.
"""

import openai
import os
from gtts import gTTS
from pydub import AudioSegment
from pydub.playback import play
import speech_recognition as sr

# Load the OpenAI API key
openai.api_key = os.getenv("OPENAI_API_KEY")

def text_to_speech_british(text, speed_multiplier=1.5):
    tts = gTTS(text=text, lang='en', tld='co.uk', slow=False)
    tts.save('output.mp3')

    audio = AudioSegment.from_mp3('output.mp3')
    faster_audio = audio.speedup(playback_speed=speed_multiplier)

    play(faster_audio)

def ask_gpt4(question):
    response = openai.Completion.create(
        engine="text-davinci-003",
        prompt=question,
        max_tokens=100,
        n=1,
        stop=None,
        temperature=0.8,
    )

    return response.choices[0].text.strip()

def speech_to_text():
    recognizer = sr.Recognizer()
    device_index = 7
    with sr.Microphone(device_index=device_index) as source:
        print("Please ask your question:")
        audio = recognizer.listen(source)

    try:
        text = recognizer.recognize_google(audio)
        print(f"Recognized question: {text}")
        return text
    except sr.UnknownValueError:
        print("Could not understand your speech.")
        return None
    except sr.RequestError as e:
        print(f"Could not request results from Google Speech Recognition service; {e}")
        return None

if __name__ == '__main__':
    while True:
        question = speech_to_text()
        if question:
            response = ask_gpt4(question)
            print(response)
            text_to_speech_british(response, speed_multiplier=1.5)
        else:
            print("Please try again.")

requirements.txt

openai
gtts
pydub
SpeechRecognition