This page provides a collection of reference implementations for the Gemini Live API on Vertex AI. Ranging from dependency-free JavaScript starters to comprehensive React-based architectures, these demos demonstrate how to build robust, real-time voice agents using the Live API and ADK.
Demo apps
- Getting started web app: A basic web application to get started with voice and camera interactions.
- React demo app: A comprehensive React client featuring real-time streaming, tool use, and media handling.
- Plain JS demo app: A dependency-free JavaScript implementation for understanding core API mechanics.
- Real-time advisor: A specialized advisor persona that can switch between silent and outspoken modes.
- Customer support agent: An advanced agent with emotion detection, multimodal input, and tool execution.
- Gaming assistant: A gaming companion with persona switching and screen sharing capabilities.
- Gemini Live Telephony App: A real-time, voice-to-AI application that uses Twilio for telephony, a FastAPI backend, and the Live API for conversational AI.
ADK bidi-streaming development guide
The Agent Development Kit (ADK) provides a production-ready framework for building Bidi-streaming applications with the Live API. The following guide and demos introduce ADK's streaming architecture, which enables real-time, two-way communication between users and AI agents through multimodal channels (text, audio, video).
Other tools
- PCM audio debugger: A standalone tool for testing and debugging raw PCM audio streams and WebSocket connections.