Connect

Gemini Live API Development

google-geminibygoogle-gemini
•
3.8k
•
Manage
Official
API Development

Builds real-time, bidirectional streaming applications using the Gemini Live API for low-latency voice and video interactions.

This skill provides specialized guidance for developers building low-latency, real-time applications using the Gemini Live API over WebSockets. It offers implementation patterns for bidirectional audio and video streaming, voice activity detection (VAD), and session management. Whether you are building an AI voice assistant or a real-time translation tool, this skill ensures best practices for handling asynchronous server events, function calling, and secure client-side authentication with ephemeral tokens across Python and JavaScript SDKs.

Key Features

01Voice Activity Detection (VAD) and interruption handling implementation
02Seamless function calling and Google Search grounding integration
033,794 GitHub stars
04Advanced session management with context compression and resumption
05Support for Gemini 3.1 Flash and 3.5 Live Translate models
06Real-time bidirectional audio and video streaming via WebSockets

Use Cases

01Creating interactive video agents that process live camera frames
02Developing low-latency AI voice assistants with native audio features
03Building real-time speech-to-speech translation applications