LogoClawIndex
CasesSkillsAbout
LogoClawIndex

gemini-live-api-dev - Build Gemini Live API streaming applications

Build real-time, bidirectional streaming applications with the Gemini Live API over WebSockets.

Tags

Updated: 2026-09-29
GeminiLive APIWebSocketsreal-time streamingaudiovideovoice activity detectionfunction callingtranslation

Capabilities

Stream audio bidirectionallyStream video framesSend and receive textTranscribe audio streams

Typical Inputs

Gemini API keyAudio PCM dataVideo frames

Typical Outputs

Audio responsesText responsesAudio transcripts

What this skill does

  • Stream audio bidirectionally
  • Stream video frames
  • Send and receive text
  • Transcribe audio streams
  • Handle voice activity detection
  • Manage live sessions
  • Call synchronous functions
  • Use Google Search grounding
  • Authenticate with ephemeral tokens
  • Configure live translation

Inputs

  • Gemini API key
  • Audio PCM data
  • Video frames
  • Text messages
  • Live session configuration
  • Target language code

Outputs

  • Audio responses
  • Text responses
  • Audio transcripts
  • Session events
  • Interruption events

Requirements

  • WebSocket support
  • Gemini API access
  • Supported Gemini Live model
  • google-genai SDK
  • API authentication

Source

  • Spec: SKILL.md

ClawIndex

OpenClaw Skills & Use Case Index

ClawIndex is an ecosystem-driven index of OpenClaw skills and real-world use cases.

Index

Skills·
Cases

Meta

About·
Disclaimer·
Email·
GitHub
© 2026 ClawIndex All Rights Reserved.