NanoAssistant is a simple voice assistant developed using Python. It uses OpenAI's GPT-3 API for language understanding and response generation, SoundDevice for recording audio, and pyttsx3 for text-to-speech conversion.
- Voice Recognition: Listens to user's voice commands and transcribes them to text.
- AI Conversation: Communicates with users in natural language using OpenAI's GPT-3 model.
- Text-to-Speech: Converts the assistant's text responses into voice and speaks them out.
To run this application, you will need:
Python 3.7 or higher. OpenAI Python SoundDevice pyttsx3 scipy numpy
First, clone this repository to your local machine using:
git clone https://github.com/username/nanoassistant.git
You can start the assistant by running the nanoassistant.py script:
python nanoassistant.py
The assistant will start listening for your commands. You can speak your commands, and the assistant will respond. To stop the assistant, say "goodbye".
This project is licensed under the terms of the MIT license. See the LICENSE file for the full license text.
Feel free to fork this project, make some changes, and submit a pull request. All contributions are welcome!
Remember to keep your OpenAI API keys secret and secure, and never expose them in your code or version control system.
Note: This project is for educational purposes only. Use at your own risk.