gemini-live-api-dev

This skill provides development guidance for the Gemini Live API, enabling real-time, bidirectional streaming of audio, video, and text over WebSockets. It covers SDK usage for Python and JavaScript, configuration for native audio, function calling, session management, and live translation.

5.5K
Installs
5
Use cases
5/10
Quality

Is gemini-live-api-dev safe to install?

Review the source first

Review the source first: our audit of gemini-live-api-dev's source files found 2 shell commands, 8 external URLs, no file writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill instructs the agent to execute shell commands for package installation and perform network requests to fetch documentation from Google's developer domains.

How we audit skills: our security review methodology.

Who is this skill for?

Developers building real-time, low-latency AI applications using Gemini's streaming capabilities.

What can you do with it?

  • Building real-time voice and video AI chatbots
  • Implementing live streaming translation across 70+ languages
  • Integrating Gemini Live API with third-party platforms like LiveKit, Pipecat, or Firebase
  • Configuring native audio and thinking levels for conversational agents
  • Managing session state, context compression, and ephemeral authentication

How good is this skill?

Quality score: 5/10. The skill provides clear, actionable instructions, specific SDK examples, and explicit warnings regarding deprecated models and API usage patterns.

What does the skill file contain?

SKILL.md
# Gemini Live API Development Skill

## Overview

The 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.

Key capabilities:
- **Bidirectional audio streaming** — real-time mic-to-speaker conversations
- **Video streaming** — send camera/screen frames alongside audio
- **Text input/output** — send and receive text within a live session
- **Audio transcriptions** — get text transcripts of both input and output audio
- **Voice Activity Dete...

Frequently asked questions

Which models are recommended for Live API development?

Use gemini-3.1-flash-live-preview for general real-time dialogue and gemini-3.5-live-translate-preview for real-time translation.

How do I send user input during a live session?

Use send_realtime_input (Python) or sendRealtimeInput (JavaScript) for all real-time audio, video, and text input. Do not use send_client_content for new messages.

Does the Live API support WebRTC?

The Live API natively supports WebSockets. For WebRTC, use partner integrations like LiveKit, Pipecat, Fishjam, Vision Agents, or Voximplant.

How should I handle documentation lookups?

If the search_docs MCP tool is available, use it as the primary source. Otherwise, fetch the llms.txt index from https://ai.google.dev/gemini-api/docs/llms.txt.

Data sourced from google-gemini/gemini-skills on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills

hyperframes-cli

163.9K

Developers building video compositions using the HyperFrames framework

The HyperFrames CLI manages the development loop for video compositions, including scaffolding, linting, validation, local previewing, and cloud rendering via AWS Lambda.

highvideocliheygen-com

hyperframes

157.0K

Developers and content creators who need to automate video production, motion graphics, or code-based video editing using HTML and CLI-based workflows

HyperFrames is an intent-routing skill that manages video, animation, and motion graphic creation by directing requests to specialized workflows. It renders video from HTML compositions where timing is defined by data attributes. The skill acts as a central entry point for authoring, editing, and rendering video projects.

highread-firstvideoheygen-com

video

40.8K

AI agents assisting users with video production, including product demos, explainers, social clips, and ads

The video skill provides a framework for agents to produce marketing videos using AI generation models, AI avatars, and programmatic video frameworks. It guides the agent through gathering project requirements, selecting appropriate tools based on the video type, and executing production workflows.

highvideomarketingcoreyhaines31

viral-short-form

20.6K

Content creators, marketers, and social media managers looking to improve the structure and performance of their short-form video and carousel content

The viral-short-form skill provides a structured framework for brainstorming and writing short-form video and carousel content for TikTok, Reels, and YouTube Shorts. It uses proven patterns for hooks, retention, and platform-specific formatting to help users create content that encourages saves and completions.

lowshort-formvideovyralcontent