https://github.com/lenochxd/chatgpt-voice-assistant

Use GPT3.5 api with your voice
https://github.com/lenochxd/chatgpt-voice-assistant

assistant assistant-chat-bots chatgpt chatgpt-api python python-3 python-script python3 voice-recognition

Last synced: about 2 months ago
JSON representation

Use GPT3.5 api with your voice

• Host: GitHub
• URL: https://github.com/lenochxd/chatgpt-voice-assistant
• Owner: Lenochxd
• Created: 2022-12-18T16:24:37.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2022-12-22T23:20:53.000Z (about 2 years ago)
• Last Synced: 2024-05-02T05:38:28.393Z (8 months ago)
• Topics: assistant, assistant-chat-bots, chatgpt, chatgpt-api, python, python-3, python-script, python3, voice-recognition
• Language: Python
• Homepage:
• Size: 10.7 KB
• Stars: 8
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# ChatGPT Voice Assistant

Not really a voice assistant, but rather ChatGPT without a keyboard.

## Usage

1. Make sure to have [python](https://www.python.org/downloads/ "install python here") installed

2. `pip install -r requirements.txt`

3. `python main.py`

4. You can now open and edit `settings/settings.json`

- **prefix:** is used to know where is the beginning of a sentence, it's like "Alexa" or "Ok google".

- **api-key:** The OpenAI API uses API keys for authentication. Visit your [API Keys](https://beta.openai.com/account/api-keys) page to retrieve the API key you'll use in your requests, 18$ of credits are free.

- **engine:** OpenIA API setting, the default one (`text-davinci-003`) is the best for ChatGPT-3, you can find the others engines [here](https://beta.openai.com/docs/models/gpt-3 "here").

- **max_tokens** OpenIA API setting which is used to put a limit on your request so as not to use too many tokens.

- **temperature:** Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer.

- **language:** .

- **voice selected  &  voices:** Change voice, documentation [here](https://support.microsoft.com/en-gb/topic/download-languages-and-voices-for-immersive-reader-read-mode-and-read-aloud-4c83a8d8-7486-42f7-8e46-2b0fdf753130: "here")

- **device selected  &  audio devices:** Select your microphone, make sure to select the first one with the name of your microphone, if the microphone does not work, try another one.

5. `python main.py`