sciver

SkillOfficialGoogle

Gemini Live API Skill

Builds real-time voice and video apps on the Gemini Live API.

Google’s official skill covers streaming audio, video and text over WebSocket to the Gemini Live API: voice activity detection (VAD), spoken responses, background reasoning and migrating older Live models to Gemini 3.8 Live. It helps the agent write correct code against the current SDK; it requires a Gemini API key.

Installation

Manual install

$npx skills add google-gemini/gemini-skills --skill gemini-live-api-dev

Details

Works in
Gemini CLI, Claude Code, Codex, Cursor
License
Apache-2.0
Tasks
Audio, Code
Rating
Source
github.com/google-gemini/gemini-skills/tree/main/skills/gemini-live-api-dev (opens in a new tab)

Tags

  • gemini
  • live api
  • google
  • voice assistant
  • realtime
  • websocket

Log in to rate

A pack is your own set of skills and MCP servers. sciver loads it in your AI with one command.

View in the library