Gemini Live API Interactive Demo

A Python application that demonstrates Google's Gemini Live API capabilities with real-time audio, camera/screen capture, and text interaction.

Features

• Real-time audio input/output
• Camera video feed integration
• Screen capture capability
• Text-based interaction
• Voice responses using Gemini's Puck voice model

Prerequisites

• Python 3.9+
• Google Gemini API key

Installation

1. Clone the repository
2. Install the required dependencies:

pip install google-genai opencv-python pyaudio pillow mss