Gemini Live API (Gemini Developer API / Google AI Studio)

Overview

Best for: Low-cost voice agents, prototypes on the free tier, and multimodal assistants that also look at a camera or screen (1 fps).

At a glance

Connections drop at about 10 min; audio-only sessions stop at 15 min (2 min with video) without compression and resumption. 99 languages per the Live guide (overview page says 70). Free tier data is used to improve Google products. No BAA or region choice on the Developer API.

Features

• native audio output
• barge-in (serverContent.interrupted)
• automatic VAD with start/end sensitivity, prefix padding, silence duration; or manual activityStart/activityEnd
• function calling (async/NON_BLOCKING on 3.8) and Google Search grounding
• input and output audio transcription
• affective dialog (v1beta, not on 3.1 Flash Live)
• proactive audio (model may choose not to answer)
• thinking on extended-thinking and 3.1 Flash Live models
• image and video frame input (1 fps)
• context window compression (sliding window)
• session resumption handles and GoAway warnings
• ephemeral tokens with config locking (liveConnectConstraints)

Pricing

Free tier: Yes: free tier for all Live models with lower rate limits; free-tier content may be used to improve Google products.

Source: ai.google.dev

Setup

1. Sign in to Google AI Studio (aistudio.google.com) and create an API key for a Google Cloud project.
2. Start on the free tier; enable billing on the project to move to paid tiers and keep data out of product improvement.
3. Install the SDK (npm i @google/genai or pip install google-genai).
4. Server-to-server: connect with the API key. Client-to-server: your server calls client.authTokens.create (v1beta) with uses: 1 and liveConnectConstraints, and the browser uses token.name as its apiKey.
5. Enable contextWindowCompression and sessionResumption from day one and handle goAway by reconnecting with the latest handle.
6. Stream 16 kHz PCM, play 24 kHz PCM, and stop playback on serverContent.interrupted.

Endpoint

wss://generativelanguage.googleapis.com/ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent?key=API_KEY (ephemeral tokens use BidiGenerateContentConstrained with access_token)

Authentication

API key on the server only. Browsers and mobile use ephemeral tokens from POST https://generativelanguage.googleapis.com/v1beta/auth_tokens, sent as access_token query parameter or Authorization: Token <token>; lock model and config with liveConnectConstraints.

import { GoogleGenAI, Modality } from "@google/genai";
// Server side with an API key. In a browser, create an ephemeral token on your server
// (client.authTokens.create) and pass token.name as apiKey instead.
const ai = new GoogleGenAI({ apiKey: process.env.GEMINI_API_KEY });
const session = await ai.live.connect({
  model: "gemini-3.8-live",
  config: {
    responseModalities: [Modality.AUDIO],
    systemInstruction: "You are a friendly support agent. Keep answers short.",
    speechConfig: { voiceConfig: { prebuiltVoiceConfig: { voiceName: "Kore" } } },
    contextWindowCompression: { slidingWindow: {} }, // lifts the 15 min audio session cap
    sessionResumption: {},                            // survive the ~10 min connection limit
    outputAudioTranscription: {},
  },
  callbacks: {
    onmessage: (msg) => {
      for (const part of msg.serverContent?.modelTurn?.parts ?? []) // a message can hold several parts
        if (part.inlineData?.data) playPcm24k(Buffer.from(part.inlineData.data, "base64"));
      if (msg.serverContent?.interrupted) stopPlayback(); // barge-in
      if (msg.sessionResumptionUpdate?.newHandle) saveHandle(msg.sessionResumptionUpdate.newHandle);
      if (msg.goAway) scheduleReconnect(msg.goAway.timeLeft);
    },
    onerror: (e) => console.error(e),
    onclose: (e) => console.log("closed", e.reason),
  },
});
// 16 kHz mono PCM16 chunks from the microphone
export const sendAudio = (pcm16) =>
  session.sendRealtimeInput({ audio: { data: pcm16.toString("base64"), mimeType: "audio/pcm;rate=16000" } });

Written from the current docs. Check the vendor's SDK version before you ship.

Warnings

Plus 14 warnings that apply to all voice-to-voice APIs. See category warnings.

Limits

• Connection lifetime around 10 minutes (GoAway with timeLeft is sent before close)
• Without compression: audio-only sessions 15 minutes, audio+video 2 minutes
• Context window 128k tokens for native audio models (3.8 Live lists 131,072 input)
• Session resumption tokens valid 2 hours after the last session ends (Developer API)
• Ephemeral tokens: new-session window default 1 minute, message window default 30 minutes
• Rate limits are per project and shown in AI Studio; Live concurrency is not published on the rate-limit page

Models and products

Docs and sources

Docs

• Live API overview
• Live capabilities guide
• Session management
• Ephemeral tokens
• WebSocket get started
• Pricing

Sources used

• ai.google.dev/gemini-api/docs/pricing
• ai.google.dev/gemini-api/docs/models
• ai.google.dev/gemini-api/docs/models/gemini-3.8-live
• ai.google.dev/gemini-api/docs/live
• ai.google.dev/gemini-api/docs/live-guide
• ai.google.dev/gemini-api/docs/live-session
• ai.google.dev/gemini-api/docs/ephemeral-tokens
• ai.google.dev/gemini-api/docs/live-api/get-started-websocket
• ai.google.dev/gemini-api/docs/changelog
• ai.google.dev/gemini-api/docs/speech-generation
• cloud.google.com/vertex-ai/generative-ai/pricing