使用 Gemini Live API 进行实时翻译

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

client = genai.Client()

model = "gemini-3.5-live-translate-preview"
config = types.LiveConnectConfig(
    response_modalities=["AUDIO"],
    input_audio_transcription=types.AudioTranscriptionConfig(),
    output_audio_transcription=types.AudioTranscriptionConfig(),
    translation_config=types.TranslationConfig(
        target_language_code="pl",
        echo_target_language=True
    )
)

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        print("Session started with translation")
        # Start receiving the translated audio stream
        async for response in session.receive():
            if response.server_content:
                if response.server_content.input_transcription:
                    print(f"Input transcript: {response.server_content.input_transcription.text}")
                if response.server_content.output_transcription:
                    print(f"Output transcript: {response.server_content.output_transcription.text}")
                if response.server_content.model_turn:
                    for part in response.server_content.model_turn.parts:
                        if part.inline_data:
                            audio_data = part.inline_data.data
                            # Play or process the translated audio chunk
                            print(f"Received audio chunk ({len(audio_data)} bytes)")

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

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

const ai = new GoogleGenAI({});
const model = 'gemini-3.5-live-translate-preview';
const config = {
    responseModalities: [Modality.AUDIO],
    inputAudioTranscription: {},
    outputAudioTranscription: {},
    translationConfig: {
        targetLanguageCode: 'pl',
        echoTargetLanguage: true
    }
};

async function main() {
  const session = await ai.live.connect({
    model: model,
    config: config,
    callbacks: {
      onopen: () => console.debug('Opened'),
      onmessage: (message) => {
        const content = message.serverContent;
        if (content?.inputTranscription) {
          console.log('Input transcript:', content.inputTranscription.text);
        }
        if (content?.outputTranscription) {
          console.log('Output transcript:', content.outputTranscription.text);
        }
        if (content?.modelTurn?.parts) {
          for (const part of content.modelTurn.parts) {
            if (part.inlineData) {
              const audioData = part.inlineData.data;
              // Play or process the translated audio chunk (base64 encoded)
              console.debug(`Received audio chunk (${audioData.length} bytes)`);
            }
          }
        }
      },
      onerror: (e) => console.debug('Error:', e.message),
      onclose: (e) => console.debug('Close:', e.reason),
    },
  });

  console.debug("Session started with translation");
}

main();

const API_KEY = "YOUR_API_KEY";
const MODEL_NAME = "gemini-3.5-live-translate-preview";
const WS_URL = `wss://generativelanguage.googleapis.com/ws/google.ai.generativelanguage.v1beta.GenerativeService.BidiGenerateContent?key=${API_KEY}`;

const websocket = new WebSocket(WS_URL);

websocket.onopen = () => {
  console.log('WebSocket Connected');

  const setupMessage = {
    setup: {
      model: `models/${MODEL_NAME}`,
      generationConfig: {
        responseModalities: ['AUDIO'],
        inputAudioTranscription: {},
        outputAudioTranscription: {},
        translationConfig: {
          targetLanguageCode: 'pl',
          echoTargetLanguage: true
        }
      }
    }
  };
  websocket.send(JSON.stringify(setupMessage));
};

websocket.onmessage = (event) => {
  const response = JSON.parse(event.data);
  if (response.serverContent) {
    const content = response.serverContent;
    if (content.inputTranscription) {
      console.log('Input transcript:', content.inputTranscription.text, `(${content.inputTranscription.languageCode})`);
    }
    if (content.outputTranscription) {
      console.log('Output transcript:', content.outputTranscription.text, `(${content.outputTranscription.languageCode})`);
    }
    if (content.modelTurn?.parts) {
      for (const part of content.modelTurn.parts) {
        if (part.inlineData) {
          const audioData = part.inlineData.data;
          // Play or process the translated audio chunk (base64 encoded)
          console.debug(`Received audio chunk (${audioData.length} bytes)`);
        }
      }
    }
  }
};

# Assuming 'chunk' is your raw PCM audio bytes
await session.send_realtime_input(
    audio=types.Blob(
        data=chunk,
        mime_type="audio/pcm;rate=16000"
    )
)

// Assuming 'chunk' is a Buffer of raw PCM audio
session.sendRealtimeInput({
  audio: {
    data: chunk.toString('base64'),
    mimeType: 'audio/pcm;rate=16000'
  }
});

// Assuming 'chunk' is a Buffer of raw PCM audio
function sendAudioChunk(chunk) {
  if (websocket.readyState === WebSocket.OPEN) {
    const audioMessage = {
      realtimeInput: {
        audio: {
          data: chunk.toString('base64'),
          mimeType: 'audio/pcm;rate=16000'
        }
      }
    };
    websocket.send(JSON.stringify(audioMessage));
  }
}

import datetime
from google import genai

now = datetime.datetime.now(tz=datetime.timezone.utc)

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

token = client.auth_tokens.create(
    config = {
        'uses': 1,
        'expire_time': now + datetime.timedelta(minutes=30),
        'live_connect_constraints': {
            'model': 'gemini-3.5-live-translate-preview',
            'config': {
                'translation_config': {
                    'target_language_code': 'pl',
                    'echo_target_language': True
                }
            }
        },
        'http_options': {'api_version': 'v1alpha'},
    }
)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});
const expireTime = new Date(Date.now() + 30 * 60 * 1000).toISOString();

const token = await client.authTokens.create({
    config: {
        uses: 1,
        expireTime: expireTime,
        liveConnectConstraints: {
            model: 'gemini-3.5-live-translate-preview',
            config: {
                responseModalities: ['AUDIO'],
                inputAudioTranscription: {},
                outputAudioTranscription: {},
                translationConfig: {
                    targetLanguageCode: 'pl',
                    echoTargetLanguage: true
                }
            }
        },
        httpOptions: {
            apiVersion: 'v1alpha'
        }
    },
});