AI / MLMédio

Gemini Live API Development Skill

porgoogle-gemini·google-gemini· v1.0.0 · atualizado em 2026-04-10

Score

Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API. Covers WebSocket-based audio/video/text streaming, voice activity detection (VAD), native audio features, function calling, session management, ephemeral tokens for client-side auth, and all Live API configuration options. SDKs covered - google-genai (Python), @google/genai (JavaScript/TypeScript).

gemini-apireal-time-streamingaudio-processingvideo-processingwebsocketfunction-callingvoice-activity-detection

0Stars

0Forks

0Usos

Fork

Documento do Skill

SKILL.mdgemini-live-api-dev/workflow

Authenticate: — Obtain and configure the API key using the `google-genai` (Python) or `@google/genai` (JavaScript) SDK.

Connect: — Establish a WebSocket connection to the Gemini Live API using the `live.connect` method, specifying the model (`gemini-3.1-flash-live-preview`) and configuration.

Send Input: — Send real-time audio, video, or text data using the `send_realtime_input` method, ensuring correct data formats (e.g., PCM for audio, JPEG for video).

Receive Responses: — Process the responses from the Gemini Live API, handling audio chunks, text transcripts, and other content parts.

Handle Events: — Implement callbacks for connection events (e.g., `onopen`, `onmessage`, `onerror`, `onclose`) to manage the session lifecycle.

Manage Session: — Implement session management features like context compression, session resumption, and GoAway signals.

Close Connection: — Properly close the WebSocket connection when the interaction is complete.

Telemetria de Agentes

Execuções

total

Taxa de Sucesso

últimos 30d

Latência Média

0.0s

p50

Alucinação

0.0%

detecção

Tokens Entrada

avg 0/exec

Tokens Saída

avg 0/exec

Uso por Plataforma

Skills Relacionados

Depende deGemini API Development Skill

90%

Compõe comGemini API in Vertex AI

85%

Compõe com ←Gemini API Development Skill

85%

Compõe com ←Gemini Interactions API Skill

85%

Similar aAgent Governance Patterns

60%

Similar aAgentic Evaluation Patterns

60%

Co-executedGemini API in Vertex AI

48%

Co-executed ←Gemini API Development Skill

49%

Co-executed ←Gemini Interactions API Skill

47%

Árvore do Skill

Gemini Live API Development Skill

gemini-live-api-dev

Fases Cognitivas5

1.SENSE

2.CONTEXTUALIZE

3.HYPOTHESIZE

4.ACT

5.REFLECT

Triggers8

build a real-time application with Gemini Live APIuse Gemini for bidirectional audio streamingintegrate Gemini with WebSockets for low-latency communicationimplement voice activity detection with Geminisend audio and video streams to Geminiuse the Gemini Live API for function callingcreate a live session with Geminitranscribe audio using Gemini Live API

Avaliar este Skill

Score Breakdown

⭐Avaliação Humana0%

🤖Sucesso de Agentes0%

🕐Atualidade100%

🔗Saúde de Dependências100%

🕸️Centralidade no Grafo0%

🛡️Segurança48%

CompositeScore = α·Humano + β·Agente + γ·Recência + δ·Deps + ε·Centralidade + ζ·Segurança

Instalação

$ synaptic mcp download gemini-live-api-dev

$ synaptic skills detail gemini-live-api-dev

$ synaptic skills live gemini-live-api-dev

Links

GitHub Repository