A simple voice assistant built using the Gemini API and Python.
About Features Requirements Installation Usage License
This project is a basic implementation of a voice assistant using the Gemini API. It allows users to interact with the Gemini model using voice commands.
Key Features Real-time voice interaction with the Gemini model Supports audio input and output Simple and easy-to-use interface
Dependencies
Python 3.11 or later
Gemini API key (obtainable from the Google Cloud Console) https://aistudio.google.com/
PyAudio library (install using pip install pyaudio)
WebSockets library (install using pip install websockets)
Steps to Install
Clone the repository using: git clone https://github.com/fahdmirza/gemini_voice_assistant.git
Install the required libraries using: pip install -r requirements.txt
Set up your Gemini API key as an environment variable using: export GEMINI_API_KEY=your-api-key-here
Running the Voice Assistant Run the voice assistant using: python3 gemini_voice_assistant.py Start speaking to interact with the Gemini model Use voice commands to perform tasks or ask questions
This project is licensed under the Apache-2.0 License. See LICENSE for details.