我們推出 2.5 版思考模型的更新內容。瞭解詳情

本頁面由 Cloud Translation API 翻譯而成。

Live API capabilities guide

本指南涵蓋 Live API 的功能和設定，請參閱「開始使用 Live API」頁面，瞭解常見用途的概略說明和程式碼範例。

事前準備

熟悉核心概念：如果您尚未熟悉這些概念，請先參閱「開始使用 Live API 」頁面。本課程將介紹 Live API 的基本原則、運作方式，以及不同模型與其對應的音訊產生方法 (原生音訊或半階層) 之間的差異。
在 AI Studio 中試用 Live API：建議您在開始建構前，先在 Google AI Studio 中試用 Live API。如要在 Google AI Studio 中使用 Live API，請選取「串流」。

建立連線

以下範例說明如何使用 API 金鑰建立連線：

Python

import asyncio
from google import genai

client = genai.Client()

model = "gemini-live-2.5-flash-preview"
config = {"response_modalities": ["TEXT"]}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        print("Session started")

if __name__ == "__main__":
    asyncio.run(main())

JavaScript

import { GoogleGenAI, Modality } from '@google/genai';

const ai = new GoogleGenAI({});
const model = 'gemini-live-2.5-flash-preview';
const config = { responseModalities: [Modality.TEXT] };

async function main() {

  const session = await ai.live.connect({
    model: model,
    callbacks: {
      onopen: function () {
        console.debug('Opened');
      },
      onmessage: function (message) {
        console.debug(message);
      },
      onerror: function (e) {
        console.debug('Error:', e.message);
      },
      onclose: function (e) {
        console.debug('Close:', e.reason);
      },
    },
    config: config,
  });

  // Send content...

  session.close();
}

main();

互動模式

以下各節將提供 Live API 中可用的不同輸入和輸出模式的範例和相關背景資訊。

收發文字

以下說明如何傳送及接收文字訊息：

Python

import asyncio
from google import genai

client = genai.Client()
model = "gemini-live-2.5-flash-preview"

config = {"response_modalities": ["TEXT"]}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        message = "Hello, how are you?"
        await session.send_client_content(
            turns={"role": "user", "parts": [{"text": message}]}, turn_complete=True
        )

        async for response in session.receive():
            if response.text is not None:
                print(response.text, end="")

if __name__ == "__main__":
    asyncio.run(main())

JavaScript

import { GoogleGenAI, Modality } from '@google/genai';

const ai = new GoogleGenAI({});
const model = 'gemini-live-2.5-flash-preview';
const config = { responseModalities: [Modality.TEXT] };

async function live() {
  const responseQueue = [];

  async function waitMessage() {
    let done = false;
    let message = undefined;
    while (!done) {
      message = responseQueue.shift();
      if (message) {
        done = true;
      } else {
        await new Promise((resolve) => setTimeout(resolve, 100));
      }
    }
    return message;
  }

  async function handleTurn() {
    const turns = [];
    let done = false;
    while (!done) {
      const message = await waitMessage();
      turns.push(message);
      if (message.serverContent && message.serverContent.turnComplete) {
        done = true;
      }
    }
    return turns;
  }

  const session = await ai.live.connect({
    model: model,
    callbacks: {
      onopen: function () {
        console.debug('Opened');
      },
      onmessage: function (message) {
        responseQueue.push(message);
      },
      onerror: function (e) {
        console.debug('Error:', e.message);
      },
      onclose: function (e) {
        console.debug('Close:', e.reason);
      },
    },
    config: config,
  });

  const inputTurns = 'Hello how are you?';
  session.sendClientContent({ turns: inputTurns });

  const turns = await handleTurn();
  for (const turn of turns) {
    if (turn.text) {
      console.debug('Received text: %s\n', turn.text);
    }
    else if (turn.data) {
      console.debug('Received inline data: %s\n', turn.data);
    }
  }

  session.close();
}

async function main() {
  await live().catch((e) => console.error('got error', e));
}

main();

逐步更新內容

使用遞增更新功能傳送文字輸入內容、建立工作階段背景資訊或還原工作階段背景資訊。如果是短時間的內容，您可以傳送逐向互動，以代表確切的事件順序：

Python

turns = [
    {"role": "user", "parts": [{"text": "What is the capital of France?"}]},
    {"role": "model", "parts": [{"text": "Paris"}]},
]

await session.send_client_content(turns=turns, turn_complete=False)

turns = [{"role": "user", "parts": [{"text": "What is the capital of Germany?"}]}]

await session.send_client_content(turns=turns, turn_complete=True)

JavaScript

let inputTurns = [
  { "role": "user", "parts": [{ "text": "What is the capital of France?" }] },
  { "role": "model", "parts": [{ "text": "Paris" }] },
]

session.sendClientContent({ turns: inputTurns, turnComplete: false })

inputTurns = [{ "role": "user", "parts": [{ "text": "What is the capital of Germany?" }] }]

session.sendClientContent({ turns: inputTurns, turnComplete: true })

對於較長的背景資訊，建議您提供單一訊息摘要，以便釋出脈絡窗口，供後續互動使用。如要瞭解其他載入工作階段內容的方法，請參閱「繼續工作階段」。

傳送及接收音訊

入門指南會介紹最常見的音訊範例：音訊轉音訊。

以下是音訊轉文字的範例，可讀取 WAV 檔案、以正確格式傳送，並接收文字輸出內容：

Python

# Test file: https://storage.googleapis.com/generativeai-downloads/data/16000.wav
# Install helpers for converting files: pip install librosa soundfile
import asyncio
import io
from pathlib import Path
from google import genai
from google.genai import types
import soundfile as sf
import librosa

client = genai.Client()
model = "gemini-live-2.5-flash-preview"

config = {"response_modalities": ["TEXT"]}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:

        buffer = io.BytesIO()
        y, sr = librosa.load("sample.wav", sr=16000)
        sf.write(buffer, y, sr, format='RAW', subtype='PCM_16')
        buffer.seek(0)
        audio_bytes = buffer.read()

        # If already in correct format, you can use this:
        # audio_bytes = Path("sample.pcm").read_bytes()

        await session.send_realtime_input(
            audio=types.Blob(data=audio_bytes, mime_type="audio/pcm;rate=16000")
        )

        async for response in session.receive():
            if response.text is not None:
                print(response.text)

if __name__ == "__main__":
    asyncio.run(main())

JavaScript

// Test file: https://storage.googleapis.com/generativeai-downloads/data/16000.wav
// Install helpers for converting files: npm install wavefile
import { GoogleGenAI, Modality } from '@google/genai';
import * as fs from "node:fs";
import pkg from 'wavefile';
const { WaveFile } = pkg;

const ai = new GoogleGenAI({});
const model = 'gemini-live-2.5-flash-preview';
const config = { responseModalities: [Modality.TEXT] };

async function live() {
  const responseQueue = [];

  async function waitMessage() {
    let done = false;
    let message = undefined;
    while (!done) {
      message = responseQueue.shift();
      if (message) {
        done = true;
      } else {
        await new Promise((resolve) => setTimeout(resolve, 100));
      }
    }
    return message;
  }

  async function handleTurn() {
    const turns = [];
    let done = false;
    while (!done) {
      const message = await waitMessage();
      turns.push(message);
      if (message.serverContent && message.serverContent.turnComplete) {
        done = true;
      }
    }
    return turns;
  }

  const session = await ai.live.connect({
    model: model,
    callbacks: {
      onopen: function () {
        console.debug('Opened');
      },
      onmessage: function (message) {
        responseQueue.push(message);
      },
      onerror: function (e) {
        console.debug('Error:', e.message);
      },
      onclose: function (e) {
        console.debug('Close:', e.reason);
      },
    },
    config: config,
  });

  // Send Audio Chunk
  const fileBuffer = fs.readFileSync("sample.wav");

  // Ensure audio conforms to API requirements (16-bit PCM, 16kHz, mono)
  const wav = new WaveFile();
  wav.fromBuffer(fileBuffer);
  wav.toSampleRate(16000);
  wav.toBitDepth("16");
  const base64Audio = wav.toBase64();

  // If already in correct format, you can use this:
  // const fileBuffer = fs.readFileSync("sample.pcm");
  // const base64Audio = Buffer.from(fileBuffer).toString('base64');

  session.sendRealtimeInput(
    {
      audio: {
        data: base64Audio,
        mimeType: "audio/pcm;rate=16000"
      }
    }

  );

  const turns = await handleTurn();
  for (const turn of turns) {
    if (turn.text) {
      console.debug('Received text: %s\n', turn.text);
    }
    else if (turn.data) {
      console.debug('Received inline data: %s\n', turn.data);
    }
  }

  session.close();
}

async function main() {
  await live().catch((e) => console.error('got error', e));
}

main();

以下是文字轉語音的範例。您可以將 AUDIO 設為回應模式，接收音訊。這個範例會將收到的資料儲存為 WAV 檔案：

Python

import asyncio
import wave
from google import genai

client = genai.Client()
model = "gemini-live-2.5-flash-preview"

config = {"response_modalities": ["AUDIO"]}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        wf = wave.open("audio.wav", "wb")
        wf.setnchannels(1)
        wf.setsampwidth(2)
        wf.setframerate(24000)

        message = "Hello how are you?"
        await session.send_client_content(
            turns={"role": "user", "parts": [{"text": message}]}, turn_complete=True
        )

        async for response in session.receive():
            if response.data is not None:
                wf.writeframes(response.data)

            # Un-comment this code to print audio data info
            # if response.server_content.model_turn is not None:
            #      print(response.server_content.model_turn.parts[0].inline_data.mime_type)

        wf.close()

if __name__ == "__main__":
    asyncio.run(main())

JavaScript

import { GoogleGenAI, Modality } from '@google/genai';
import * as fs from "node:fs";
import pkg from 'wavefile';
const { WaveFile } = pkg;

const ai = new GoogleGenAI({});
const model = 'gemini-live-2.5-flash-preview';
const config = { responseModalities: [Modality.AUDIO] };

async function live() {
  const responseQueue = [];

  async function waitMessage() {
    let done = false;
    let message = undefined;
    while (!done) {
      message = responseQueue.shift();
      if (message) {
        done = true;
      } else {
        await new Promise((resolve) => setTimeout(resolve, 100));
      }
    }
    return message;
  }

  async function handleTurn() {
    const turns = [];
    let done = false;
    while (!done) {
      const message = await waitMessage();
      turns.push(message);
      if (message.serverContent && message.serverContent.turnComplete) {
        done = true;
      }
    }
    return turns;
  }

  const session = await ai.live.connect({
    model: model,
    callbacks: {
      onopen: function () {
        console.debug('Opened');
      },
      onmessage: function (message) {
        responseQueue.push(message);
      },
      onerror: function (e) {
        console.debug('Error:', e.message);
      },
      onclose: function (e) {
        console.debug('Close:', e.reason);
      },
    },
    config: config,
  });

  const inputTurns = 'Hello how are you?';
  session.sendClientContent({ turns: inputTurns });

  const turns = await handleTurn();

  // Combine audio data strings and save as wave file
  const combinedAudio = turns.reduce((acc, turn) => {
    if (turn.data) {
      const buffer = Buffer.from(turn.data, 'base64');
      const intArray = new Int16Array(buffer.buffer, buffer.byteOffset, buffer.byteLength / Int16Array.BYTES_PER_ELEMENT);
      return acc.concat(Array.from(intArray));
    }
    return acc;
  }, []);

  const audioBuffer = new Int16Array(combinedAudio);

  const wf = new WaveFile();
  wf.fromScratch(1, 24000, '16', audioBuffer);
  fs.writeFileSync('output.wav', wf.toBuffer());

  session.close();
}

async function main() {
  await live().catch((e) => console.error('got error', e));
}

main();

音訊格式

Live API 中的音訊資料一律為原始、小端序的 16 位元 PCM。音訊輸出一律會使用 24 kHz 的取樣率。輸入音訊的預設取樣率為 16kHz，但 Live API 會視需要重新取樣，因此可傳送任何取樣率。如要傳達輸入音訊的取樣率，請將每個含有音訊的 Blob 的 MIME 類型設為 audio/pcm;rate=16000 之類的值。

音訊轉錄

您可以在設定設定檔中傳送 output_audio_transcription，啟用模型的音訊輸出轉錄功能。系統會根據模型的回覆推斷語音轉錄語言。

Python

import asyncio
from google import genai
from google.genai import types

client = genai.Client()
model = "gemini-live-2.5-flash-preview"

config = {"response_modalities": ["AUDIO"],
        "output_audio_transcription": {}
}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        message = "Hello? Gemini are you there?"

        await session.send_client_content(
            turns={"role": "user", "parts": [{"text": message}]}, turn_complete=True
        )

        async for response in session.receive():
            if response.server_content.model_turn:
                print("Model turn:", response.server_content.model_turn)
            if response.server_content.output_transcription:
                print("Transcript:", response.server_content.output_transcription.text)

if __name__ == "__main__":
    asyncio.run(main())

JavaScript

import { GoogleGenAI, Modality } from '@google/genai';

const ai = new GoogleGenAI({});
const model = 'gemini-live-2.5-flash-preview';

const config = {
  responseModalities: [Modality.AUDIO],
  outputAudioTranscription: {}
};

async function live() {
  const responseQueue = [];

  async function waitMessage() {
    let done = false;
    let message = undefined;
    while (!done) {
      message = responseQueue.shift();
      if (message) {
        done = true;
      } else {
        await new Promise((resolve) => setTimeout(resolve, 100));
      }
    }
    return message;
  }

  async function handleTurn() {
    const turns = [];
    let done = false;
    while (!done) {
      const message = await waitMessage();
      turns.push(message);
      if (message.serverContent && message.serverContent.turnComplete) {
        done = true;
      }
    }
    return turns;
  }

  const session = await ai.live.connect({
    model: model,
    callbacks: {
      onopen: function () {
        console.debug('Opened');
      },
      onmessage: function (message) {
        responseQueue.push(message);
      },
      onerror: function (e) {
        console.debug('Error:', e.message);
      },
      onclose: function (e) {
        console.debug('Close:', e.reason);
      },
    },
    config: config,
  });

  const inputTurns = 'Hello how are you?';
  session.sendClientContent({ turns: inputTurns });

  const turns = await handleTurn();

  for (const turn of turns) {
    if (turn.serverContent && turn.serverContent.outputTranscription) {
      console.debug('Received output transcription: %s\n', turn.serverContent.outputTranscription.text);
    }
  }

  session.close();
}

async function main() {
  await live().catch((e) => console.error('got error', e));
}

main();

您可以在設定設定檔中傳送 input_audio_transcription，啟用音訊輸入的轉錄功能。

Python

import asyncio
from pathlib import Path
from google import genai
from google.genai import types

client = genai.Client()
model = "gemini-live-2.5-flash-preview"

config = {
    "response_modalities": ["TEXT"],
    "input_audio_transcription": {},
}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        audio_data = Path("16000.pcm").read_bytes()

        await session.send_realtime_input(
            audio=types.Blob(data=audio_data, mime_type='audio/pcm;rate=16000')
        )

        async for msg in session.receive():
            if msg.server_content.input_transcription:
                print('Transcript:', msg.server_content.input_transcription.text)

if __name__ == "__main__":
    asyncio.run(main())

JavaScript

import { GoogleGenAI, Modality } from '@google/genai';
import * as fs from "node:fs";
import pkg from 'wavefile';
const { WaveFile } = pkg;

const ai = new GoogleGenAI({});
const model = 'gemini-live-2.5-flash-preview';

const config = {
  responseModalities: [Modality.TEXT],
  inputAudioTranscription: {}
};

async function live() {
  const responseQueue = [];

  async function waitMessage() {
    let done = false;
    let message = undefined;
    while (!done) {
      message = responseQueue.shift();
      if (message) {
        done = true;
      } else {
        await new Promise((resolve) => setTimeout(resolve, 100));
      }
    }
    return message;
  }

  async function handleTurn() {
    const turns = [];
    let done = false;
    while (!done) {
      const message = await waitMessage();
      turns.push(message);
      if (message.serverContent && message.serverContent.turnComplete) {
        done = true;
      }
    }
    return turns;
  }

  const session = await ai.live.connect({
    model: model,
    callbacks: {
      onopen: function () {
        console.debug('Opened');
      },
      onmessage: function (message) {
        responseQueue.push(message);
      },
      onerror: function (e) {
        console.debug('Error:', e.message);
      },
      onclose: function (e) {
        console.debug('Close:', e.reason);
      },
    },
    config: config,
  });

  // Send Audio Chunk
  const fileBuffer = fs.readFileSync("16000.wav");

  // Ensure audio conforms to API requirements (16-bit PCM, 16kHz, mono)
  const wav = new WaveFile();
  wav.fromBuffer(fileBuffer);
  wav.toSampleRate(16000);
  wav.toBitDepth("16");
  const base64Audio = wav.toBase64();

  // If already in correct format, you can use this:
  // const fileBuffer = fs.readFileSync("sample.pcm");
  // const base64Audio = Buffer.from(fileBuffer).toString('base64');

  session.sendRealtimeInput(
    {
      audio: {
        data: base64Audio,
        mimeType: "audio/pcm;rate=16000"
      }
    }
  );

  const turns = await handleTurn();

  for (const turn of turns) {
    if (turn.serverContent && turn.serverContent.outputTranscription) {
      console.log("Transcription")
      console.log(turn.serverContent.outputTranscription.text);
    }
  }
  for (const turn of turns) {
    if (turn.text) {
      console.debug('Received text: %s\n', turn.text);
    }
    else if (turn.data) {
      console.debug('Received inline data: %s\n', turn.data);
    }
    else if (turn.serverContent && turn.serverContent.inputTranscription) {
      console.debug('Received input transcription: %s\n', turn.serverContent.inputTranscription.text);
    }
  }

  session.close();
}

async function main() {
  await live().catch((e) => console.error('got error', e));
}

main();

串流音訊和視訊

變更語音和語言

Live API 模型各自支援不同的語音集合。半級聯網支援 Puck、Charon、Kore、Fenrir、Aoede、Leda、Orus 和 Zephyr。原生音訊支援的清單更長 (與 TTS 模型清單相同)。您可以在 AI Studio 中聆聽所有語音。

如要指定語音，請在 speechConfig 物件中設定語音名稱，做為工作階段設定的一部分：

Python

config = {
    "response_modalities": ["AUDIO"],
    "speech_config": {
        "voice_config": {"prebuilt_voice_config": {"voice_name": "Kore"}}
    },
}

JavaScript

const config = {
  responseModalities: [Modality.AUDIO],
  speechConfig: { voiceConfig: { prebuiltVoiceConfig: { voiceName: "Kore" } } }
};

generateContent

Live API 支援多種語言。

如要變更語言，請在 speechConfig 物件中設定語言代碼，做為工作階段設定的一部分：

Python

config = {
    "response_modalities": ["AUDIO"],
    "speech_config": {
        "language_code": "de-DE"
    }
}

JavaScript

const config = {
  responseModalities: [Modality.AUDIO],
  speechConfig: { languageCode: "de-DE" }
};

原生音訊功能

下列功能僅適用於原生音訊。如要進一步瞭解原生音訊，請參閱「選擇模型和音訊產生方式」一文。

如何使用原生音訊輸出

如要使用原生音訊輸出，請設定其中一個原生音訊模型，並將 response_modalities 設為 AUDIO。

如需完整範例，請參閱「收發語音」。

Python

model = "gemini-2.5-flash-preview-native-audio-dialog"
config = types.LiveConnectConfig(response_modalities=["AUDIO"])

async with client.aio.live.connect(model=model, config=config) as session:
    # Send audio input and receive audio

JavaScript

const model = 'gemini-2.5-flash-preview-native-audio-dialog';
const config = { responseModalities: [Modality.AUDIO] };

async function main() {

  const session = await ai.live.connect({
    model: model,
    config: config,
    callbacks: ...,
  });

  // Send audio input and receive audio

  session.close();
}

main();

情緒感知對話

這項功能可讓 Gemini 根據輸入內容的措辭和語氣調整回覆風格。

如要使用情感對話，請將 API 版本設為 v1alpha，並在設定訊息中將 enable_affective_dialog 設為 true：

Python

client = genai.Client(http_options={"api_version": "v1alpha"})

config = types.LiveConnectConfig(
    response_modalities=["AUDIO"],
    enable_affective_dialog=True
)

JavaScript

const ai = new GoogleGenAI({ httpOptions: {"apiVersion": "v1alpha"} });

const config = {
  responseModalities: [Modality.AUDIO],
  enableAffectiveDialog: true
};

請注意，情緒對話目前僅支援原生音訊輸出模型。

主動音訊

啟用這項功能後，Gemini 可主動決定不回應不相關的內容。

如要使用此功能，請將 API 版本設為 v1alpha，並在設定訊息中設定 proactivity 欄位，然後將 proactive_audio 設為 true：

Python

client = genai.Client(http_options={"api_version": "v1alpha"})

config = types.LiveConnectConfig(
    response_modalities=["AUDIO"],
    proactivity={'proactive_audio': True}
)

JavaScript

const ai = new GoogleGenAI({ httpOptions: {"apiVersion": "v1alpha"} });

const config = {
  responseModalities: [Modality.AUDIO],
  proactivity: { proactiveAudio: true }
}

請注意，目前只有原生音訊輸出模型支援主動式音訊。

原生音訊輸出，含思考時間

原生音訊輸出功能支援思考功能，可透過單獨的模型 gemini-2.5-flash-exp-native-audio-thinking-dialog 使用。

如需完整範例，請參閱「收發語音」。

Python

model = "gemini-2.5-flash-exp-native-audio-thinking-dialog"
config = types.LiveConnectConfig(response_modalities=["AUDIO"])

async with client.aio.live.connect(model=model, config=config) as session:
    # Send audio input and receive audio

JavaScript

const model = 'gemini-2.5-flash-exp-native-audio-thinking-dialog';
const config = { responseModalities: [Modality.AUDIO] };

async function main() {

  const session = await ai.live.connect({
    model: model,
    config: config,
    callbacks: ...,
  });

  // Send audio input and receive audio

  session.close();
}

main();

語音活動偵測 (VAD)

語音活動偵測 (VAD) 可讓模型辨識使用者說話的時間。這對於建立自然對話至關重要，因為這樣一來，使用者就能隨時中斷模型。

VAD 偵測到中斷時，系統會取消並捨棄目前的生成作業。只有已傳送至用戶端的資訊會保留在工作階段記錄中。接著，伺服器會傳送 BidiGenerateContentServerContent 訊息來回報中斷情形。

接著，Gemini 伺服器會捨棄任何待處理的函式呼叫，並傳送 BidiGenerateContentServerContent 訊息，其中包含已取消呼叫的 ID。

Python

async for response in session.receive():
    if response.server_content.interrupted is True:
        # The generation was interrupted

        # If realtime playback is implemented in your application,
        # you should stop playing audio and clear queued playback here.

JavaScript

const turns = await handleTurn();

for (const turn of turns) {
  if (turn.serverContent && turn.serverContent.interrupted) {
    // The generation was interrupted

    // If realtime playback is implemented in your application,
    // you should stop playing audio and clear queued playback here.
  }
}

自動語音偵測

根據預設，模型會自動對連續音訊輸入串流執行 VAD。您可以使用設定配置的 realtimeInputConfig.automaticActivityDetection 欄位設定 VAD。

如果音訊串流暫停超過一秒 (例如因為使用者關閉麥克風)，就應傳送 audioStreamEnd 事件，以便清除任何快取音訊。用戶端隨時可以恢復傳送音訊資料。

Python

# example audio file to try:
# URL = "https://storage.googleapis.com/generativeai-downloads/data/hello_are_you_there.pcm"
# !wget -q $URL -O sample.pcm
import asyncio
from pathlib import Path
from google import genai
from google.genai import types

client = genai.Client()
model = "gemini-live-2.5-flash-preview"

config = {"response_modalities": ["TEXT"]}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        audio_bytes = Path("sample.pcm").read_bytes()

        await session.send_realtime_input(
            audio=types.Blob(data=audio_bytes, mime_type="audio/pcm;rate=16000")
        )

        # if stream gets paused, send:
        # await session.send_realtime_input(audio_stream_end=True)

        async for response in session.receive():
            if response.text is not None:
                print(response.text)

if __name__ == "__main__":
    asyncio.run(main())

JavaScript

// example audio file to try:
// URL = "https://storage.googleapis.com/generativeai-downloads/data/hello_are_you_there.pcm"
// !wget -q $URL -O sample.pcm
import { GoogleGenAI, Modality } from '@google/genai';
import * as fs from "node:fs";

const ai = new GoogleGenAI({});
const model = 'gemini-live-2.5-flash-preview';
const config = { responseModalities: [Modality.TEXT] };

async function live() {
  const responseQueue = [];

  async function waitMessage() {
    let done = false;
    let message = undefined;
    while (!done) {
      message = responseQueue.shift();
      if (message) {
        done = true;
      } else {
        await new Promise((resolve) => setTimeout(resolve, 100));
      }
    }
    return message;
  }

  async function handleTurn() {
    const turns = [];
    let done = false;
    while (!done) {
      const message = await waitMessage();
      turns.push(message);
      if (message.serverContent && message.serverContent.turnComplete) {
        done = true;
      }
    }
    return turns;
  }

  const session = await ai.live.connect({
    model: model,
    callbacks: {
      onopen: function () {
        console.debug('Opened');
      },
      onmessage: function (message) {
        responseQueue.push(message);
      },
      onerror: function (e) {
        console.debug('Error:', e.message);
      },
      onclose: function (e) {
        console.debug('Close:', e.reason);
      },
    },
    config: config,
  });

  // Send Audio Chunk
  const fileBuffer = fs.readFileSync("sample.pcm");
  const base64Audio = Buffer.from(fileBuffer).toString('base64');

  session.sendRealtimeInput(
    {
      audio: {
        data: base64Audio,
        mimeType: "audio/pcm;rate=16000"
      }
    }

  );

  // if stream gets paused, send:
  // session.sendRealtimeInput({ audioStreamEnd: true })

  const turns = await handleTurn();
  for (const turn of turns) {
    if (turn.text) {
      console.debug('Received text: %s\n', turn.text);
    }
    else if (turn.data) {
      console.debug('Received inline data: %s\n', turn.data);
    }
  }

  session.close();
}

async function main() {
  await live().catch((e) => console.error('got error', e));
}

main();

有了 send_realtime_input，API 就會根據 VAD 自動回應音訊。send_client_content 會依序將訊息新增至模型內容，而 send_realtime_input 則會犧牲確定性排序，以提升回應速度。

自動 VAD 設定

如要進一步控制 VAD 活動，您可以設定下列參數。詳情請參閱 API 參考資料。

Python

from google.genai import types

config = {
    "response_modalities": ["TEXT"],
    "realtime_input_config": {
        "automatic_activity_detection": {
            "disabled": False, # default
            "start_of_speech_sensitivity": types.StartSensitivity.START_SENSITIVITY_LOW,
            "end_of_speech_sensitivity": types.EndSensitivity.END_SENSITIVITY_LOW,
            "prefix_padding_ms": 20,
            "silence_duration_ms": 100,
        }
    }
}

JavaScript

import { GoogleGenAI, Modality, StartSensitivity, EndSensitivity } from '@google/genai';

const config = {
  responseModalities: [Modality.TEXT],
  realtimeInputConfig: {
    automaticActivityDetection: {
      disabled: false, // default
      startOfSpeechSensitivity: StartSensitivity.START_SENSITIVITY_LOW,
      endOfSpeechSensitivity: EndSensitivity.END_SENSITIVITY_LOW,
      prefixPaddingMs: 20,
      silenceDurationMs: 100,
    }
  }
};

停用自動 VAD

或者，您也可以在設定訊息中將 realtimeInputConfig.automaticActivityDetection.disabled 設為 true，停用自動語音偵測功能。在這個設定中，用戶端負責偵測使用者的語音，並在適當時間傳送 activityStart 和 activityEnd 訊息。在這個設定中不會傳送 audioStreamEnd。而是會在任何中斷的串流上標示 activityEnd 訊息。

Python

config = {
    "response_modalities": ["TEXT"],
    "realtime_input_config": {"automatic_activity_detection": {"disabled": True}},
}

async with client.aio.live.connect(model=model, config=config) as session:
    # ...
    await session.send_realtime_input(activity_start=types.ActivityStart())
    await session.send_realtime_input(
        audio=types.Blob(data=audio_bytes, mime_type="audio/pcm;rate=16000")
    )
    await session.send_realtime_input(activity_end=types.ActivityEnd())
    # ...

JavaScript

const config = {
  responseModalities: [Modality.TEXT],
  realtimeInputConfig: {
    automaticActivityDetection: {
      disabled: true,
    }
  }
};

session.sendRealtimeInput({ activityStart: {} })

session.sendRealtimeInput(
  {
    audio: {
      data: base64Audio,
      mimeType: "audio/pcm;rate=16000"
    }
  }

);

session.sendRealtimeInput({ activityEnd: {} })

符記數

您可以在傳回的伺服器訊息的 usageMetadata 欄位中，找到已使用的符記總數。

Python

async for message in session.receive():
    # The server will periodically send messages that include UsageMetadata.
    if message.usage_metadata:
        usage = message.usage_metadata
        print(
            f"Used {usage.total_token_count} tokens in total. Response token breakdown:"
        )
        for detail in usage.response_tokens_details:
            match detail:
                case types.ModalityTokenCount(modality=modality, token_count=count):
                    print(f"{modality}: {count}")

JavaScript

const turns = await handleTurn();

for (const turn of turns) {
  if (turn.usageMetadata) {
    console.debug('Used %s tokens in total. Response token breakdown:\n', turn.usageMetadata.totalTokenCount);

    for (const detail of turn.usageMetadata.responseTokensDetails) {
      console.debug('%s\n', detail);
    }
  }
}

媒體解析度

您可以將 mediaResolution 欄位設為工作階段設定的一部分，藉此指定輸入媒體的媒體解析度：

Python

from google.genai import types

config = {
    "response_modalities": ["AUDIO"],
    "media_resolution": types.MediaResolution.MEDIA_RESOLUTION_LOW,
}

JavaScript

import { GoogleGenAI, Modality, MediaResolution } from '@google/genai';

const config = {
    responseModalities: [Modality.TEXT],
    mediaResolution: MediaResolution.MEDIA_RESOLUTION_LOW,
};

限制

規劃專案時，請考量 Live API 的下列限制。

回應模式

您只能在工作階段設定中為每個工作階段設定一個回應模式 (TEXT 或 AUDIO)。設定這兩項元素會導致設定錯誤訊息。也就是說，您可以設定模型以文字或音訊回應，但在同一個工作階段中，無法同時使用這兩種回應方式。

用戶端驗證

根據預設，Live API 只提供伺服器對伺服器驗證。如果您是使用用戶端對伺服器方法實作 Live API 應用程式，就必須使用暫時性權杖來降低安全性風險。

工作階段持續時間

僅音訊的會議時長上限為 15 分鐘，而音訊加視訊的會議時長上限為 2 分鐘。不過，您可以設定不同的工作階段管理技巧，讓工作階段時間無限延長。

脈絡窗口

工作階段的脈絡窗口限制為：

原生音訊輸出模型的 128k 符記
其他 Live API 型號的 32k 符記

支援的語言

Live API 支援下列語言。

語言	BCP-47 代碼	語言	BCP-47 代碼
德文 (德國)	`de-DE`	英文 (澳洲)*	`en-AU`
英文 (英國)*	`en-GB`	英文 (印度)	`en-IN`
英文 (美國)	`en-US`	西班牙文 (美國)	`es-US`
法文 (法國)	`fr-FR`	北印度文 (印度)	`hi-IN`
葡萄牙文 (巴西)	`pt-BR`	阿拉伯文 (一般)	`ar-XA`
西班牙文 (西班牙)*	`es-ES`	法文 (加拿大)*	`fr-CA`
印尼文 (印尼)	`id-ID`	義大利文 (義大利)	`it-IT`
日文 (日本)	`ja-JP`	土耳其文 (土耳其)	`tr-TR`
越南文 (越南)	`vi-VN`	孟加拉文 (印度)	`bn-IN`
古吉拉特文 (印度)*	`gu-IN`	卡納達文 (印度)*	`kn-IN`
馬拉地文 (印度)	`mr-IN`	馬拉雅拉姆文 (印度)*	`ml-IN`
泰米爾文 (印度)	`ta-IN`	泰盧固文 (印度)	`te-IN`
荷蘭文 (荷蘭)	`nl-NL`	韓文 (韓國)	`ko-KR`
中文 (中國)*	`cmn-CN`	波蘭文 (波蘭)	`pl-PL`
俄文 (俄羅斯)	`ru-RU`	泰文 (泰國)	`th-TH`

標有星號 (*) 的語言不適用於原生音訊。

後續步驟

請參閱「使用工具」和「工作階段管理」指南，瞭解如何有效使用 Live API。
請在 Google AI Studio 中試用 Live API。
如要進一步瞭解 Live API 模型，請參閱「模型」頁面中的 Gemini 2.0 Flash Live 和 Gemini 2.5 Flash 原生音訊。
請參閱 Live API 食譜、Live API 工具食譜和 Live API 新手指南指令碼，瞭解更多範例。