This is a Python library for transcribing real-time communication from the user and using GPT3.5-Turbo to generate responses from the assistant.
- Cozmo's API only works with Python 3.9
You can fork this repo to build off of it, or download it if you must.
No proper .exe or application front end, merely execute the app.py file (Python 3.9) and start interacting.
- support compatability with NAO, a more serious unit
- build an app front-end
- find a way to speed up the response time, perhaps drop GPT3.5 or use a websocket to a fast computer
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
Please make sure to update tests as appropriate.