gemini-live-api-dev

1# Gemini Live API Development Skill
2 
3## Overview
4 
5The Live API enables **low-latency, real-time voice and video interactions** with Gemini over WebSockets. It processes continuous streams of audio, video, or text to deliver immediate, human-like spoken responses and background reasoning.
6 
7Key capabilities:
8- **Bidirectional audio streaming** — real-time mic-to-speaker conversations
9- **Background reasoning (extended thinking)** — multi-step background reasoning with spoken conversational fillers
10- **Live streaming transcription** — real-time speech-to-text with interim and finalized streams
11- **Video streaming** — send camera/screen frames alongside audio
12- **Text input/output** — send and receive text within a live session
13- **Audio transcriptions** — get text transcripts of both input and output audio
14- **Voice Activity Detection (VAD)** — automatic server VAD, client-side Hybrid VAD, and manual Push-to-Talk
15- **Asynchronous function calling** — non-blocking tool execution while audio continues streaming
16- **Full-session client content** — inject and update conversation turns mid-stream
17- **Session management** — context compression, session resumption, GoAway signals
18- **Ephemeral tokens** — secure client-side authentication
19 
20> [!NOTE]
21> The Live API connects directly via **WebSockets**. For WebRTC support or simplified integration, use a [partner integration](#partner-integrations).
22 
23## Models
24 
25### Current Models (Use These)
26…