Gemini Live API 支持与 Gemini 模型进行低延迟、实时的语音和视频 交互，并且是 双向的。
Live API 及其特殊模型系列可以处理连续的音频、视频或文本流 以提供即时、自然逼真的语音回答， 为您的用户打造浑然天成的对话式体验。
本页介绍了如何开始使用最常见的功能（ 流式音频输入和输出），但 Live API 支持许多不同的 功能和 配置选项。
Live API 是一种有状态 API，它会创建 WebSocket 连接，以 在客户端与 Gemini 服务器之间建立 会话。 如需了解详情，请参阅 Live API 参考文档 (Gemini Developer API | Agent Platform Gemini API (formerly Vertex AI))。
查看实用资源
Swift - 快速入门应用 | Android - 快速入门应用 | Web - 快速入门应用 | Flutter - 快速入门应用 | Unity - 即将推出！
在实际部署的应用中体验 Gemini Live API - 查看可通过 Firebase 控制台访问的 Flutter AI Playground 应用 。
准备工作
如果您尚未完成
入门指南，请先完成该指南。
该指南介绍了如何设置 Firebase 项目、
将应用连接到 Firebase、添加 SDK、
为所选的 Gemini API 提供方初始化后端服务，以及
创建 LiveModel 实例。
您可以使用提示和 Live API 在 Google AI Studio 或 Agent Studio 中进行原型设计。
支持此功能的模型
3.x 模型
Gemini Developer API
gemini-3.1-flash-live-preview
虽然这是一个预览版模型，但它在“免费层级” 中提供Gemini Developer API。
Agent Platform Gemini API (formerly Vertex AI)
不支持 Gemini Live 3.x 模型
2.5 模型
虽然该模型根据 Gemini API 提供商的不同而具有不同的模型名称，但该模型的功能是相同的。
Gemini Developer API
gemini-2.5-flash-native-audio-preview-12-2025gemini-2.5-flash-native-audio-preview-09-2025
虽然这些是预览版模型，但它们在“免费层级” 的 Gemini Developer API中提供。
Agent Platform Gemini API (formerly Vertex AI)
gemini-live-2.5-flash-native-audio（于 2025 年 12 月发布）gemini-live-2.5-flash-preview-native-audio-09-2025
使用 Agent Platform Gemini API (formerly Vertex AI) 时，Live API 模型 不支持
global位置。
流式传输音频输入和输出
|
点击您的 Gemini API 提供商，以查看此页面上特定于提供商的内容 和代码。 |
以下示例展示了发送流式音频输入 和接收流式音频输出 的基本实现 。
如需了解 Live API 的其他选项和功能，请查看本页稍后的 “您还可以执行以下操作”部分。
Swift
如需使用 Live API，请创建
LiveModel
实例并将
回答模态
设置为 audio。
import FirebaseAILogic
// Initialize the Gemini Developer API backend service.
// Create a `liveModel` instance with a model that supports the Live API.
let liveModel = FirebaseAI.firebaseAI(backend: .googleAI()).liveModel(
modelName: "gemini-2.5-flash-native-audio-preview-12-2025",
// Configure the model to respond with audio.
generationConfig: LiveGenerationConfig(
responseModalities: [.audio]
)
)
do {
let session = try await liveModel.connect()
// Load the audio file, or tap a microphone.
guard let audioFile = NSDataAsset(name: "audio.pcm") else {
fatalError("Failed to load audio file")
}
// Provide the audio data.
await session.sendAudioRealtime(audioFile.data)
var outputText = ""
for try await message in session.responses {
if case let .content(content) = message.payload {
content.modelTurn?.parts.forEach { part in
if let part = part as? InlineDataPart, part.mimeType.starts(with: "audio/pcm") {
// Handle 16bit pcm audio data at 24khz
playAudio(part.data)
}
}
// Optional: if you don't need to send more requests.
if content.isTurnComplete {
await session.close()
}
}
}
} catch {
fatalError(error.localizedDescription)
}
Kotlin
如需使用 Live API，请创建
LiveModel
实例并将
回答模态
设置为 AUDIO。
// Initialize the Gemini Developer API backend service.
// Create a `liveModel` instance with a model that supports the Live API.
val liveModel = Firebase.ai(backend = GenerativeBackend.googleAI()).liveModel(
modelName = "gemini-2.5-flash-native-audio-preview-12-2025",
// Configure the model to respond with audio.
generationConfig = liveGenerationConfig {
responseModality = ResponseModality.AUDIO
}
)
val session = liveModel.connect()
// This is the recommended approach.
// However, you can create your own recorder and handle the stream.
session.startAudioConversation()
Java
如需使用 Live API，请创建
LiveModel
实例并将
回答模态
设置为 AUDIO。
ExecutorService executor = Executors.newFixedThreadPool(1);
// Initialize the Gemini Developer API backend service.
// Create a `liveModel` instance with a model that supports the Live API.
LiveGenerativeModel lm = FirebaseAI.getInstance(GenerativeBackend.googleAI()).liveModel(
"gemini-2.5-flash-native-audio-preview-12-2025",
// Configure the model to respond with audio.
new LiveGenerationConfig.Builder()
.setResponseModality(ResponseModality.AUDIO)
.build()
);
LiveModelFutures liveModel = LiveModelFutures.from(lm);
ListenableFuture<LiveSession> sessionFuture = liveModel.connect();
Futures.addCallback(sessionFuture, new FutureCallback<LiveSession>() {
@Override
public void onSuccess(LiveSession ses) {
LiveSessionFutures session = LiveSessionFutures.from(ses);
session.startAudioConversation();
}
@Override
public void onFailure(Throwable t) {
// Handle exceptions
}
}, executor);
Web
如需使用 Live API，请创建
LiveGenerativeModel
实例并将
回答模态
设置为 AUDIO。
import { initializeApp } from "firebase/app";
import { getAI, getLiveGenerativeModel, GoogleAIBackend, ResponseModality } from "firebase/ai";
// TODO(developer): Replace the following with your app's Firebase configuration
// See: https://firebase.google.com/docs/web/learn-more#config-object
const firebaseConfig = {
// ...
};
// Initialize FirebaseApp
const firebaseApp = initializeApp(firebaseConfig);
// Initialize the Gemini Developer API backend service.
const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });
// Create a `LiveGenerativeModel` instance with a model that supports the Live API.
const liveModel = getLiveGenerativeModel(ai, {
model: "gemini-2.5-flash-native-audio-preview-12-2025",
// Configure the model to respond with audio.
generationConfig: {
responseModalities: [ResponseModality.AUDIO],
},
});
const session = await liveModel.connect();
// Start the audio conversation.
const audioConversationController = await startAudioConversation(session);
// ... Later, to stop the audio conversation
// await audioConversationController.stop()
Dart
如需使用 Live API，请创建
LiveGenerativeModel
实例并将
回答模态
设置为 audio。
import 'package:firebase_ai/firebase_ai.dart';
import 'package:firebase_core/firebase_core.dart';
import 'firebase_options.dart';
import 'package:your_audio_recorder_package/your_audio_recorder_package.dart';
late LiveModelSession _session;
final _audioRecorder = YourAudioRecorder();
await Firebase.initializeApp(
options: DefaultFirebaseOptions.currentPlatform,
);
// Initialize the Gemini Developer API backend service.
// Create a `liveGenerativeModel` instance with a model that supports the Live API.
final liveModel = FirebaseAI.googleAI().liveGenerativeModel(
model: 'gemini-2.5-flash-native-audio-preview-12-2025',
// Configure the model to respond with audio.
liveGenerationConfig: LiveGenerationConfig(
responseModalities: [ResponseModalities.audio],
),
);
_session = await liveModel.connect();
final audioRecordStream = _audioRecorder.startRecordingStream();
// Map the Uint8List stream to InlineDataPart stream.
final mediaChunkStream = audioRecordStream.map((data) {
return InlineDataPart('audio/pcm', data);
});
await _session.startMediaStream(mediaChunkStream);
// In a separate thread, receive the audio response from the model.
await for (final message in _session.receive()) {
// Process the received message.
}
Unity
如需使用 Live API，请创建
LiveModel
实例并将
回答模态
设置为 Audio。
using Firebase;
using Firebase.AI;
async Task SendTextReceiveAudio() {
// Initialize the Gemini Developer API backend service.
// Create a `LiveModel` instance with a model that supports the Live API.
var liveModel = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI()).GetLiveModel(
modelName: "gemini-2.5-flash-native-audio-preview-12-2025",
// Configure the model to respond with audio.
liveGenerationConfig: new LiveGenerationConfig(
responseModalities: new[] { ResponseModality.Audio })
);
LiveSession session = await liveModel.ConnectAsync();
// Start a coroutine to send audio from the Microphone.
var recordingCoroutine = StartCoroutine(SendAudio(session));
// Start receiving the response.
await ReceiveAudio(session);
}
IEnumerator SendAudio(LiveSession liveSession) {
string microphoneDeviceName = null;
int recordingFrequency = 16000;
int recordingBufferSeconds = 2;
var recordingClip = Microphone.Start(microphoneDeviceName, true,
recordingBufferSeconds, recordingFrequency);
int lastSamplePosition = 0;
while (true) {
if (!Microphone.IsRecording(microphoneDeviceName)) {
yield break;
}
int currentSamplePosition = Microphone.GetPosition(microphoneDeviceName);
if (currentSamplePosition != lastSamplePosition) {
// The Microphone uses a circular buffer, so we need to check if the
// current position wrapped around to the beginning, and handle it accordingly.
int sampleCount;
if (currentSamplePosition > lastSamplePosition) {
sampleCount = currentSamplePosition - lastSamplePosition;
} else {
sampleCount = recordingClip.samples - lastSamplePosition + currentSamplePosition;
}
if (sampleCount > 0) {
// Get the audio chunk.
float[] samples = new float[sampleCount];
recordingClip.GetData(samples, lastSamplePosition);
// Send the data, discarding the resulting Task to avoid the warning.
_ = liveSession.SendAudioAsync(samples);
lastSamplePosition = currentSamplePosition;
}
}
// Wait for a short delay before reading the next sample from the Microphone.
const float MicrophoneReadDelay = 0.5f;
yield return new WaitForSeconds(MicrophoneReadDelay);
}
}
Queue audioBuffer = new();
async Task ReceiveAudio(LiveSession liveSession) {
int sampleRate = 24000;
int channelCount = 1;
// Create a looping AudioClip to fill with the received audio data.
int bufferSamples = (int)(sampleRate * channelCount);
AudioClip clip = AudioClip.Create("StreamingPCM", bufferSamples, channelCount,
sampleRate, true, OnAudioRead);
// Attach the clip to an AudioSource and start playing it.
AudioSource audioSource = GetComponent();
audioSource.clip = clip;
audioSource.loop = true;
audioSource.Play();
// Start receiving the response.
await foreach (var message in liveSession.ReceiveAsync()) {
// Process the received message
foreach (float[] pcmData in message.AudioAsFloat) {
lock (audioBuffer) {
foreach (float sample in pcmData) {
audioBuffer.Enqueue(sample);
}
}
}
}
}
// This method is called by the AudioClip to load audio data.
private void OnAudioRead(float[] data) {
int samplesToProvide = data.Length;
int samplesProvided = 0;
lock(audioBuffer) {
while (samplesProvided < samplesToProvide && audioBuffer.Count > 0) {
data[samplesProvided] = audioBuffer.Dequeue();
samplesProvided++;
}
}
while (samplesProvided < samplesToProvide) {
data[samplesProvided] = 0.0f;
samplesProvided++;
}
}
价格和令牌计数
您可以在所选 Gemini API 提供商的 文档中找到 Live API 模型的价格信息： Gemini Developer API | Agent Platform Gemini API (formerly Vertex AI)。
无论您选择哪个 Gemini API 提供商，Live API 均不支持 Count Tokens API。
您还可以执行以下操作
查看 Live API 的全套解决方案 功能， 例如流式传输各种输入模态（音频、文本或视频 + 音频）。
使用各种 配置选项（例如添加转录或设置回答语音）自定义实现。
了解如何 管理会话，包括在会话期间更新 内容、压缩上下文窗口、检测会话 即将结束的时间以及恢复会话。
通过向模型授予对 工具的访问权限（例如函数调用和 Grounding with
Google Search ），增强实现。 即将推出有关如何将工具与 Live API 搭配使用的官方文档！了解 限制和规范， 了解使用 Live API， 例如会话时长、速率限制、支持的语言等。