Agent skill · Google (Gemini)
Gemini Live API skill for Claude Code, Codex and Cursor
Officialname: gemini-live-api-dev★ 4.3k (repo)pushed 2026-10-13Apache-2.0SKILL.md on GitHubchecked 2026-11-07
What it does, in the publisher's words
Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) to Gemini 3.8 Live. Covers WebSocket-based audio/video/text streaming, voice activity detection (VAD), background reasoning (extended thinking), asynchronous function calling, session management, ephemeral tokens, live transcription, and live translation.
The description field of the SKILL.md. The agent reads only this at startup and decides from it when to load the full skill.
Install Gemini Live API
The skills CLI copies the skill into the folder of each agent you pick (Claude Code, Codex, Cursor, Copilot, Gemini CLI, OpenCode, Windsurf...). Add -g for all projects. Needs Node.js 22.20+. docs
npx skills add google-gemini/gemini-skills --skill gemini-live-api-dev
This repo is a plugin marketplace. Inside Claude Code, add it and install the plugin that holds the skill (gemini-skills), or copy only this skill into ~/.claude/skills. docs
/plugin marketplace add google-gemini/gemini-skills /plugin install <plugin>@gemini-skills # or only this skill: npx skills add google-gemini/gemini-skills --skill gemini-live-api-dev -a claude-code
Download the skill folder, zip it, then Customize > Skills > + > Create skill > Upload a skill. Code execution must be on (Settings > Capabilities). docs
git clone --depth 1 https://github.com/google-gemini/gemini-skills.git /tmp/gemini-live-api-dev-src cp -r /tmp/gemini-live-api-dev-src/skills/gemini-live-api-dev ./gemini-live-api-dev zip -r gemini-live-api-dev.zip gemini-live-api-dev
Codex reads skills from .agents/skills in the repo or ~/.agents/skills. Type $ in Codex to use one. docs
npx skills add google-gemini/gemini-skills --skill gemini-live-api-dev -a codex
gh skill (GitHub CLI 2.90+, preview) installs it for Copilot in VS Code, the CLI and the cloud agent. Copilot also reads .github/skills and ~/.copilot/skills. docs
gh skill install google-gemini/gemini-skills gemini-live-api-dev
Cursor reads .cursor/skills, .agents/skills and ~/.cursor/skills (and .claude/skills). It does not install loose skills from a GitHub URL, so copy it in. docs
npx skills add google-gemini/gemini-skills --skill gemini-live-api-dev -a cursor
Installs from the GitHub repo; --path picks this skill out of the repo. Default scope is user (all projects). docs
gemini skills install https://github.com/google-gemini/gemini-skills.git --path skills/gemini-live-api-dev
OpenCode reads .opencode/skills, ~/.config/opencode/skills and the Claude and .agents folders. docs
npx skills add google-gemini/gemini-skills --skill gemini-live-api-dev -a opencode
Windsurf (now Devin Desktop) reads .devin/skills, .windsurf/skills and ~/.codeium/windsurf/skills. docs
npx skills add google-gemini/gemini-skills --skill gemini-live-api-dev -a windsurf
Works with
Claude Code, Claude.ai and Claude Desktop, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode, Windsurf and other agents that read the open Agent Skills format.
What's in the SKILL.md
- Overview
- Models
- Current Models (Use These)
- SDKs
- Partner Integrations
- Audio Formats
- Quick Start
- Authentication
- Connecting to the Live API
- Sending Text
- Sending Audio
- Sending Video
- Receiving Audio and Text
- Background Reasoning (Extended Thinking)
- Live Translation (Gemini Live Translate)
- Model
- Configuration (TranslationConfig)
- Live Streaming Transcription (Gemini Live Transcribe)
- Model
- Modes
- Python
- JavaScript
- Raw WebSockets
- Limitations
- + 7 more
Bundled files
- references/migration.md
Loaded only when the instructions point to them.
Facts
- Skill name
- gemini-live-api-dev
- Publisher
- Google (Gemini) (official)
- Repo
- google-gemini/gemini-skills
- License
- Apache-2.0
- SKILL.md size
- 1,488 words, 404 lines
- Bundled files
- 1, 1 docs
- Repo stars
- 4.3k (as of 2026-10-24)
- SKILL.md checked
- 2026-11-07
Pairs with the Gemini MCP server: the server gives the agent the tools, the skill teaches it how to use them.
More skills from google-gemini/gemini-skills
- Gemini API: Writes code against the Gemini API for chat, multimodal input, image, video and speech.
Related ai & ml skills
- Claude API · Anthropic
- ChatGPT Apps · OpenAI
- OpenAI Docs · OpenAI
- Hugging Face CLI · Hugging Face
- Gradio · Hugging Face
- Hugging Face LLM Trainer · Hugging Face
- Transformers.js · Hugging Face
- Cloudflare Agents SDK · Cloudflare
FAQ
What does the gemini-live-api-dev skill do?+
Builds real-time voice and video streaming apps on the Gemini Live API over WebSockets. In its own SKILL.md, Google (Gemini) describes it as: "Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) to Gemini 3.8 Live."
How do I install the gemini-live-api-dev skill?+
Run npx skills add google-gemini/gemini-skills --skill gemini-live-api-dev and pick your agents, or use the tab for your agent above. In Claude Code the skill ends up in ~/.claude/skills/gemini-live-api-dev/SKILL.md; in Codex and Cursor in .agents/skills/gemini-live-api-dev/.
Does Gemini Live API work in Codex, Cursor and Copilot, or only Claude?+
It's a standard SKILL.md, so any agent that reads the Agent Skills format can use it: Claude Code, the Claude apps, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode, Windsurf and more.
Who maintains Gemini Live API?+
Google (Gemini), the company or project behind it, in the google-gemini/gemini-skills repo on GitHub, last pushed 2026-10-13. License: Apache-2.0.
Read a skill's SKILL.md and scripts before you install it: skills aren't verified by any agent vendor. Claude skills marketplace · How to install skills · MCP servers