Tool use with Live API

透過工具，Live API 不僅能進行對話，還能在現實世界中執行動作，並在維持即時連線的同時，擷取外部情境資訊。您可以使用 Live API 定義工具，例如函式呼叫和 Google 搜尋。

支援的工具總覽

以下簡要介紹 Live API 模型可用的工具：

工具 gemini-2.5-flash-native-audio-preview-09-2025
搜尋 是
函式呼叫 是
Google 地圖 否
程式碼執行 否
網址內容 否

函式呼叫

Live API 支援函式呼叫，就像一般內容生成要求一樣。透過函式呼叫，Live API 可以與外部資料和程式互動，大幅擴充應用程式的功能。

您可以將函式宣告定義為工作階段設定的一部分。收到工具呼叫後，用戶端應使用 session.send_tool_response 方法，以 FunctionResponse 物件清單回應。

詳情請參閱函式呼叫教學課程。

Python

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

client = genai.Client()

model = "gemini-2.5-flash-native-audio-preview-09-2025"

# Simple function definitions
turn_on_the_lights = {"name": "turn_on_the_lights"}
turn_off_the_lights = {"name": "turn_off_the_lights"}

tools = [{"function_declarations": [turn_on_the_lights, turn_off_the_lights]}]
config = {"response_modalities": ["AUDIO"], "tools": tools}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        prompt = "Turn on the lights please"
        await session.send_client_content(turns={"parts": [{"text": prompt}]})

        wf = wave.open("audio.wav", "wb")
        wf.setnchannels(1)
        wf.setsampwidth(2)
        wf.setframerate(24000)  # Output is 24kHz

        async for response in session.receive():
            if response.data is not None:
                wf.writeframes(response.data)
            elif response.tool_call:
                print("The tool was called")
                function_responses = []
                for fc in response.tool_call.function_calls:
                    function_response = types.FunctionResponse(
                        id=fc.id,
                        name=fc.name,
                        response={ "result": "ok" } # simple, hard-coded function response
                    )
                    function_responses.append(function_response)

                await session.send_tool_response(function_responses=function_responses)

        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';  // npm install wavefile
const { WaveFile } = pkg;

const ai = new GoogleGenAI({});
const model = 'gemini-2.5-flash-native-audio-preview-09-2025';

// Simple function definitions
const turn_on_the_lights = { name: "turn_on_the_lights" } // , description: '...', parameters: { ... }
const turn_off_the_lights = { name: "turn_off_the_lights" }

const tools = [{ functionDeclarations: [turn_on_the_lights, turn_off_the_lights] }]

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

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;
      } else if (message.toolCall) {
        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 = 'Turn on the lights please';
  session.sendClientContent({ turns: inputTurns });

  let turns = await handleTurn();

  for (const turn of turns) {
    if (turn.toolCall) {
      console.debug('A tool was called');
      const functionResponses = [];
      for (const fc of turn.toolCall.functionCalls) {
        functionResponses.push({
          id: fc.id,
          name: fc.name,
          response: { result: "ok" } // simple, hard-coded function response
        });
      }

      console.debug('Sending tool response...\n');
      session.sendToolResponse({ functionResponses: functionResponses });
    }
  }

  // Check again for new messages
  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);  // output is 24kHz
  fs.writeFileSync('audio.wav', wf.toBuffer());

  session.close();
}

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

main();

模型可以根據單一提示產生多個函式呼叫，以及串連輸出內容所需的程式碼。這段程式碼會在沙箱環境中執行，產生後續的 BidiGenerateContentToolCall 訊息。

非同步函式呼叫

根據預設，函式呼叫會依序執行，也就是說，系統會暫停執行作業，直到每個函式呼叫的結果都可用為止。這可確保系統依序處理函式，也就是說，函式執行期間，您無法繼續與模型互動。

如果不想封鎖對話，可以要求模型非同步執行函式。如要這麼做，請先在函式定義中新增 behavior：

Python

# Non-blocking function definitions
turn_on_the_lights = {"name": "turn_on_the_lights", "behavior": "NON_BLOCKING"} # turn_on_the_lights will run asynchronously
turn_off_the_lights = {"name": "turn_off_the_lights"} # turn_off_the_lights will still pause all interactions with the model

JavaScript 

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

// Non-blocking function definitions
const turn_on_the_lights = {name: "turn_on_the_lights", behavior: Behavior.NON_BLOCKING}

// Blocking function definitions
const turn_off_the_lights = {name: "turn_off_the_lights"}

const tools = [{ functionDeclarations: [turn_on_the_lights, turn_off_the_lights] }]

NON-BLOCKING 可確保函式以非同步方式執行，同時您可繼續與模型互動。

接著，您需要使用 scheduling 參數，告知模型收到 FunctionResponse 時的行為。你可以選擇：

  • 中斷正在執行的動作，並立即告知你收到的回覆 (scheduling="INTERRUPT")，
  • 請等待裝置完成目前執行的作業 (scheduling="WHEN_IDLE")，

  • 或者不採取任何行動，稍後在討論中使用該知識 (scheduling="SILENT")

Python

# for a non-blocking function definition, apply scheduling in the function response:
  function_response = types.FunctionResponse(
      id=fc.id,
      name=fc.name,
      response={
          "result": "ok",
          "scheduling": "INTERRUPT" # Can also be WHEN_IDLE or SILENT
      }
  )

JavaScript 

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

// for a non-blocking function definition, apply scheduling in the function response:
const functionResponse = {
  id: fc.id,
  name: fc.name,
  response: {
    result: "ok",
    scheduling: FunctionResponseScheduling.INTERRUPT  // Can also be WHEN_IDLE or SILENT
  }
}

您可以在工作階段設定中啟用「以 Google 搜尋為基礎」。這有助於提高 Live API 的準確度，並避免產生幻覺。詳情請參閱基礎教學課程。

Python

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

client = genai.Client()

model = "gemini-2.5-flash-native-audio-preview-09-2025"

tools = [{'google_search': {}}]
config = {"response_modalities": ["AUDIO"], "tools": tools}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        prompt = "When did the last Brazil vs. Argentina soccer match happen?"
        await session.send_client_content(turns={"parts": [{"text": prompt}]})

        wf = wave.open("audio.wav", "wb")
        wf.setnchannels(1)
        wf.setsampwidth(2)
        wf.setframerate(24000)  # Output is 24kHz

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

                # The model might generate and execute Python code to use Search
                model_turn = chunk.server_content.model_turn
                if model_turn:
                    for part in model_turn.parts:
                        if part.executable_code is not None:
                            print(part.executable_code.code)

                        if part.code_execution_result is not None:
                            print(part.code_execution_result.output)

        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';  // npm install wavefile
const { WaveFile } = pkg;

const ai = new GoogleGenAI({});
const model = 'gemini-2.5-flash-native-audio-preview-09-2025';

const tools = [{ googleSearch: {} }]
const config = {
  responseModalities: [Modality.AUDIO],
  tools: tools
}

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;
      } else if (message.toolCall) {
        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 = 'When did the last Brazil vs. Argentina soccer match happen?';
  session.sendClientContent({ turns: inputTurns });

  let turns = await handleTurn();

  let combinedData = '';
  for (const turn of turns) {
    if (turn.serverContent && turn.serverContent.modelTurn && turn.serverContent.modelTurn.parts) {
      for (const part of turn.serverContent.modelTurn.parts) {
        if (part.executableCode) {
          console.debug('executableCode: %s\n', part.executableCode.code);
        }
        else if (part.codeExecutionResult) {
          console.debug('codeExecutionResult: %s\n', part.codeExecutionResult.output);
        }
        else if (part.inlineData && typeof part.inlineData.data === 'string') {
          combinedData += atob(part.inlineData.data);
        }
      }
    }
  }

  // Convert the base64-encoded string of bytes into a Buffer.
  const buffer = Buffer.from(combinedData, 'binary');

  // The buffer contains raw bytes. For 16-bit audio, we need to interpret every 2 bytes as a single sample.
  const intArray = new Int16Array(buffer.buffer, buffer.byteOffset, buffer.byteLength / Int16Array.BYTES_PER_ELEMENT);

  const wf = new WaveFile();
  // The API returns 16-bit PCM audio at a 24kHz sample rate.
  wf.fromScratch(1, 24000, '16', intArray);
  fs.writeFileSync('audio.wav', wf.toBuffer());

  session.close();
}

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

main();

結合多種工具

您可以在 Live API 中結合多種工具，進一步提升應用程式的功能：

Python

prompt = """
Hey, I need you to do two things for me.

1. Use Google Search to look up information about the largest earthquake in California the week of Dec 5 2024?
2. Then turn on the lights

Thanks!
"""

tools = [
    {"google_search": {}},
    {"function_declarations": [turn_on_the_lights, turn_off_the_lights]},
]

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

# ... remaining model call

JavaScript 

const prompt = `Hey, I need you to do two things for me.

1. Use Google Search to look up information about the largest earthquake in California the week of Dec 5 2024?
2. Then turn on the lights

Thanks!
`

const tools = [
  { googleSearch: {} },
  { functionDeclarations: [turn_on_the_lights, turn_off_the_lights] }
]

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

// ... remaining model call

後續步驟