gemini-live-api-dev

Stream audio, video, and text bidirectionally over WebSockets with Gemini Live API.

302|22|Updated Feb 12, 2026
One-click install
npx skills add https://github.com/JetBrains/skills --skill gemini-live-api-dev-jetbrains
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-live-api-dev
Source: https://github.com/JetBrains/skills/tree/main/gemini-live-api-dev
Command: npx skills add https://github.com/JetBrains/skills --skill gemini-live-api-dev-jetbrains

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enable developers to rapidly build real-time, bidirectional streaming experiences with Gemini Live API, eliminating complex boilerplate for low-latency communication.

Core Features & Use Cases

  • Real-time bidirectional streaming of audio, video, and text over WebSockets
  • Voice Activity Detection (VAD), native audio features, and proactive audio behaviors
  • Function calling, Google Search grounding, and session management with ephemeral tokens
  • Quick integration for Python (google-genai) and JavaScript/TypeScript (@google/genai)

Quick Start

Create a Live API client and initiate a WebSocket session using the gemini-2.5-flash-native-audio-preview-12-2025 model to begin streaming.

Frequently Asked Questions about gemini-live-api-dev

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build real-time streaming applications with the Gemini Live API?

The Gemini Live API enables bidirectional streaming over WebSockets, allowing simultaneous transmission of real-time voice, video, and text. This low-latency connection supports multimodal data exchange and event-driven messaging for interactive sessions.

How do I set up authentication and manage sessions for WebSocket connectivity?

Authentication for WebSocket connectivity uses ephemeral tokens to securely manage live sessions. This provides temporary access for real-time data streaming and model interaction without exposing long-term credentials.

Can I use the Gemini Live API with Python and JavaScript for voice activity detection?

Yes, the Gemini Live API supports Python and JavaScript/TypeScript clients for implementing voice activity detection (VAD). It provides native audio features and proactive audio behaviors directly over the WebSocket connection.

What is the best way to integrate function calling and Google Search grounding into a live audio stream?

To integrate function calling and Google Search grounding into a live audio stream, apply event-driven messaging within your bidirectional WebSocket session. This enables real-time model interactions and contextual responses.

Does the Gemini Live API support bidirectional video and text streaming over WebSockets?

Yes, the Gemini Live API supports bidirectional streaming of video and text over WebSockets. It enables low-latency, multimodal data exchange and session control for applications needing live, interactive voice and video experiences.