gemini-live-api-dev

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 Detection (VAD) — automatic interruption handling
• Native audio — thinking (with configurable thinkingLevel)
• Function calling — synchronous tool use
• Google Search grounding — ground responses in real-time search results
• Session management — context compression, session resumption, GoAway signals
• Ephemeral tokens — secure client-side authentication

[!NOTE] The Live API currently only supports WebSockets. For WebRTC support or simplified integration, use a partner integration.

Models

• gemini-3.1-flash-live-preview — Optimized for low-latency, real-time dialogue. Native audio output, thinking (via thinkingLevel). 128k context window. This is the recommended model for all Live API use cases.
• gemini-3.5-transcribe-live — Real-time streaming speech-to-text with interim hypotheses, finalized transcripts, smart formatting, and Hybrid VAD.
• gemini-3.5-live-translate-preview — Real-time streaming translation model.

[!WARNING] The following Live API models are deprecated and will be shut down. Migrate to gemini-3.1-flash-live-preview.

• gemini-2.5-flash-native-audio-preview-12-2025 — Migrate to gemini-3.1-flash-live-preview.
• gemini-live-2.5-flash-preview — Released June 17, 2025. Shutdown: December 9, 2025.
• gemini-2.0-flash-live-001 — Released April 9, 2025. Shutdown: December 9, 2025.

SDKs

• Python: google-genai — pip install google-genai
• JavaScript/TypeScript: @google/genai — npm install @google/genai

[!WARNING] Legacy SDKs google-generativeai (Python) and @google/generative-ai (JS) are deprecated. Use the new SDKs above.

Partner Integrations

To streamline real-time audio/video app development, use a third-party integration supporting the Gemini Live API over WebRTC or WebSockets:

• LiveKit — Use the Gemini Live API with LiveKit Agents.
• Pipecat by Daily — Create a real-time AI chatbot using Gemini Live and Pipecat.
• Fishjam by Software Mansion — Create live video and audio streaming applications with Fishjam.
• Vision Agents by Stream — Build real-time voice and video AI applications with Vision Agents.
• Voximplant — Connect inbound and outbound calls to Live API with Voximplant.
• Firebase AI SDK — Get started with the Gemini Live API using Firebase AI Logic.

Audio Formats

• Input: Raw PCM, little-endian, 16-bit, mono. 16kHz native (will resample others). MIME type: audio/pcm;rate=16000
• Output: Raw PCM, little-endian, 16-bit, mono. 24kHz sample rate.

[!IMPORTANT] Use send_realtime_input / sendRealtimeInput for all real-time user input (audio, video, and text). send_client_content / sendClientContent is only supported for seeding initial context history (requires setting initial_history_in_client_content in history_config). Do not use it to send new user messages during the conversation.

[!WARNING] Do not use media in sendRealtimeInput. Use the specific keys: audio for audio data, video for images/video frames, and text for text input.

Quick Start

Authentication

Python

from google import genai
 
client = genai.Client(api_key="YOUR_API_KEY")

JavaScript

import { GoogleGenAI } 

Connecting to the Live API

Python

JavaScript

Sending Text

Python

JavaScript

Sending Audio

Python

JavaScript

Sending Video

Python

JavaScript

Receiving Audio and Text

[!IMPORTANT] A single server event can contain multiple content parts simultaneously (e.g., audio chunks and transcript). Always process all parts in each event to avoid missing content.

Python

JavaScript

Live Translation (Gemini Live Translate)

The Live API supports real-time, low-latency streaming translation of speech (audio) across 70+ languages. For full details on options and capabilities, see the Live Translate Guide.

Model

• gemini-3.5-live-translate-preview — The recommended translation model for all Live Translate use cases.

Configuration (TranslationConfig)

To enable translation, specify a TranslationConfig object inside your live session setup:

• Python SDK: Configure the connection using translation_config on LiveConnectConfig:

  config = types.LiveConnectConfig(
      response_modalities=[types.Modality.AUDIO],
      translation_config=types.TranslationConfig(
          target_language_code="es",  # Target language code (e.g. es, fr, pl)
          echo_target_language=True,
      ),
      input_audio_transcription=types.AudioTranscriptionConfig(),
      output_audio_transcription=types.AudioTranscriptionConfig(),
  )
• Raw WebSockets: Place translationConfig inside generationConfig:

  {
    "setup": {
      "model": "models/gemini-3.5-live-translate-preview",
      "generationConfig": {
        "responseModalities": ["AUDIO"],
        "translationConfig": {
          "targetLanguageCode": "es",
          "echoTargetLanguage": true
        }
      }
    }
  }

Live Streaming Transcription (Gemini Live Transcribe)

The Live API supports real-time streaming speech-to-text over WebSockets with low-latency interim hypotheses, finalized transcripts, and Hybrid VAD. For full details, see the Live Transcription Guide and Colab Cookbook.

Model

• gemini-3.5-transcribe-live

Modes

• smart: cleans up filler words, resolves inline self-corrections, and structures formatting.
• verbatim (default): exact word-for-word transcript.

Python

config = types.LiveConnectConfig(
    response_modalities=["TEXT"],
    input_audio_transcription=types.AudioTranscriptionConfig(),
)
 
async with client.aio.live.connect(model="gemini-3.5-transcribe-live", config=config) as session:
    # Stream audio
    await session.send_realtime_input(audio=types.Blob(data=chunk, mime_type="audio/pcm;rate=16000"))
    # Hybrid VAD: notify turn end on client-detected silence for zero latency
    await session.send_realtime_input(audio_stream_end=True)

JavaScript

const session = await ai.live.connect({
  model: 'gemini-3.5-transcribe-live',
  config: {
    responseModalities: ['text'],
    inputAudioTranscription: { mode: 'smart' }
  },
  callbacks: {
    onmessage: (msg) => {
      if (msg.serverContent?.interimInputTranscription) {
        console.log('Interim:', msg.serverContent.interimInputTranscription.text);
      }
      if (msg.serverContent?.inputTranscription) {
        console.log('Final:', msg.serverContent.inputTranscription.text);
      }
    }
  }
});
 
session.sendRealtimeInput({ audio: { data: chunkBase64, mimeType: 'audio/pcm;rate=16000' } });
session.sendRealtimeInput({ audioStreamEnd: true }); // Hybrid VAD

Raw WebSockets

{
  "setup": {
    "model": "models/gemini-3.5-transcribe-live",
    "generationConfig": {
      "responseModalities": ["TEXT"],
      "speechConfig": {
        "voiceConfig": {}
      }
    },
    "inputAudioTranscription": {
      "mode": "smart"
    }
  }
}

Limitations

• Response modality — Only TEXT or AUDIO per session, not both. Native audio models only support audio.
• Audio-only session — 15 min without compression
• Audio+video session — 2 min without compression
• Connection lifetime — ~10 min (use session resumption)
• Context window — 128k tokens (native audio) / 32k tokens (standard)
• Async function calling — Not yet supported; function calling is synchronous only. The model will not start responding until you've sent the tool response.
• Proactive audio — Not yet supported in Gemini 3.1 Flash Live. Remove any configuration for this feature.
• Affective dialogue — Not yet supported in Gemini 3.1 Flash Live. Remove any configuration for this feature.
• Code execution — Not supported
• URL context — Not supported

Migrating from Gemini 2.5 Flash Live

When migrating from gemini-2.5-flash-native-audio-preview-12-2025 to gemini-3.1-flash-live-preview:

1. Model string — Update from gemini-2.5-flash-native-audio-preview-12-2025 to gemini-3.1-flash-live-preview.
2. Thinking configuration — Use thinkingLevel (minimal, low, medium, high) instead of thinkingBudget. Default is minimal for lowest latency.
3. Server events — A single event can contain multiple content parts simultaneously (audio + transcript). Process all parts in each event.
4. Client content — send_client_content is only for seeding initial context history (set initial_history_in_client_content in history_config). Use send_realtime_input for text during conversation.
5. Turn coverage — Defaults to TURN_INCLUDES_AUDIO_ACTIVITY_AND_ALL_VIDEO instead of TURN_INCLUDES_ONLY_ACTIVITY. If sending constant video frames, consider sending only during audio activity to reduce costs.
6. Async function calling — Not yet supported. Function calling is synchronous only.
7. Proactive audio & affective dialogue — Not yet supported. Remove any configuration for these features.

Best Practices

1. Use headphones when testing mic audio to prevent echo/self-interruption
2. Enable context window compression for sessions longer than 15 minutes
3. Implement session resumption to handle connection resets gracefully
4. Use ephemeral tokens for client-side deployments — never expose API keys in browsers
5. Use send_realtime_input for all real-time user input (audio, video, text). Reserve send_client_content only for seeding initial context history
6. Send audioStreamEnd when the mic is paused to flush cached audio
7. Clear audio playback queues on interruption signals
8. Process all parts in each server event — events can contain multiple content parts

Documentation Lookup

When MCP is Installed (Preferred)

If the search_docs tool (from the Google MCP server) is available, use it as your only documentation source:

1. Call search_docs with your query
2. Read the returned documentation
3. Trust MCP results as source of truth for API details — they are always up-to-date.

[!IMPORTANT] When MCP tools are present, never fetch URLs manually. MCP provides up-to-date, indexed documentation that is more accurate and token-efficient than URL fetching.

When MCP is NOT Installed (Fallback Only)

If no MCP documentation tools are available, fetch from the official docs index:

llms.txt URL: https://ai.google.dev/gemini-api/docs/llms.txt

This index contains links to all documentation pages in .md.txt format. Use web fetch tools to:

1. Fetch llms.txt to discover available documentation pages
2. Fetch specific pages (e.g., https://ai.google.dev/gemini-api/docs/live-session.md.txt)

Key Documentation Pages

[!IMPORTANT] Those are not all the documentation pages. Use the llms.txt index to discover available documentation pages

• Live API Overview — getting started, raw WebSocket usage
• Live Transcription — real-time speech-to-text, interim hypotheses, smart formatting, and Hybrid VAD
• Live Translate — configuration options and capabilities for translation
• Live API Capabilities Guide — voice config, transcription config, native audio (thinking), VAD configuration, media resolution
• Live API Tool Use — function calling (sync and async), Google Search grounding
• Session Management — context window compression, session resumption, GoAway signals
• Ephemeral Tokens — secure client-side authentication for browser/mobile
• WebSockets API Reference — raw WebSocket protocol details

Supported Languages

The Live API supports 70 languages including: English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Hindi, Arabic, Russian, and many more. Native audio models automatically detect and switch languages.