การถอดเสียงสดด้วย Gemini Live API

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

client = genai.Client()
model = "gemini-3.5-transcribe-live"

config = types.LiveConnectConfig(
    response_modalities=["TEXT"],
    input_audio_transcription=types.AudioTranscriptionConfig(
        language_codes=[],  # Automatic language detection
    ),
)

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

        # Receive transcription events
        async for response in session.receive():
            server_content = response.server_content
            if server_content and server_content.input_transcription:
                print("Transcript:", server_content.input_transcription.text)

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

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

const ai = new GoogleGenAI({});
const model = 'gemini-3.5-transcribe-live';

const config = {
  responseModalities: [Modality.TEXT],
  inputAudioTranscription: {
    languageCodes: [], // Automatic language detection
  },
};

async function main() {
  const session = await ai.live.connect({
    model: model,
    config: config,
    callbacks: {
      onopen: () => console.log('Connected to Live Transcription'),
      onmessage: (message) => {
        const content = message.serverContent;
        if (content?.inputTranscription) {
          console.log('Transcript:', content.inputTranscription.text);
        }
      },
      onerror: (e) => console.error('Error:', e.message),
      onclose: (e) => console.log('Connection closed:', e.reason),
    },
  });
}

main();

const API_KEY = "YOUR_API_KEY";
const MODEL_NAME = "gemini-3.5-transcribe-live";
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: ['TEXT'],
      },
      inputAudioTranscription: {
        languageCodes: []
      }
    }
  };
  websocket.send(JSON.stringify(setupMessage));
};

websocket.onmessage = (event) => {
  const response = JSON.parse(event.data);
  const content = response.serverContent;
  if (content?.inputTranscription) {
    console.log('Transcript:', content.inputTranscription.text);
  }
};

async def receive_transcripts(session):
    async for response in session.receive():
        server_content = response.server_content
        if not server_content:
            continue

        # Real-time interim hypothesis (updates dynamically as user speaks)
        if server_content.interim_input_transcription:
            interim_text = server_content.interim_input_transcription.text
            print(f"\r[Interim] {interim_text}", end="", flush=True)

        # Finalized transcript (emitted on speech completion)
        if server_content.input_transcription:
            final_text = server_content.input_transcription.text
            print(f"\n[Final] {final_text}")

onmessage: (message) => {
  const content = message.serverContent;
  if (!content) return;

  if (content.interimInputTranscription) {
    // Update live subtitle preview on screen
    renderInterimPreview(content.interimInputTranscription.text);
  }

  if (content.inputTranscription) {
    // Append final committed transcript to chat history
    commitFinalTranscript(content.inputTranscription.text);
  }
};

websocket.onmessage = (event) => {
  const response = JSON.parse(event.data);
  const content = response.serverContent;
  if (content?.interimInputTranscription) {
    console.log('[Interim]:', content.interimInputTranscription.text);
  }
  if (content?.inputTranscription) {
    console.log('[Final]:', content.inputTranscription.text);
  }
};

# Stream a raw PCM audio chunk
await session.send_realtime_input(
    audio=types.Blob(
        data=audio_chunk_bytes,
        mime_type="audio/pcm;rate=16000"
    )
)

# Signal the end of the audio stream when finished
await session.send_realtime_input(audio_stream_end=True)

// Send base64-encoded PCM audio chunk
session.sendRealtimeInput({
  audio: {
    data: audioChunkBase64,
    mimeType: 'audio/pcm;rate=16000'
  }
});

// Signal stream end
session.sendRealtimeInput({
  audioStreamEnd: true
});

// Send base64-encoded PCM audio chunk
websocket.send(JSON.stringify({
  realtimeInput: {
    audio: {
      data: audioChunkBase64,
      mimeType: 'audio/pcm;rate=16000'
    }
  }
}));

// Signal stream end
websocket.send(JSON.stringify({
  realtimeInput: {
    audioStreamEnd: true
  }
}));

config = types.LiveConnectConfig(
    response_modalities=["TEXT"],
    input_audio_transcription=types.AudioTranscriptionConfig(
        language_codes=[],
    ),
)

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

const setupMessage = {
  setup: {
    model: 'models/gemini-3.5-transcribe-live',
    generationConfig: {
      responseModalities: ['TEXT'],
    },
    inputAudioTranscription: {
      languageCodes: [],
    },
  },
};
websocket.send(JSON.stringify(setupMessage));

config = types.LiveConnectConfig(
    response_modalities=["TEXT"],
    input_audio_transcription=types.AudioTranscriptionConfig(
        language_codes=["es-ES"],
    ),
)

const config = {
  responseModalities: [Modality.TEXT],
  inputAudioTranscription: {
    languageCodes: ['es-ES'],
  },
};

const setupMessage = {
  setup: {
    model: 'models/gemini-3.5-transcribe-live',
    generationConfig: {
      responseModalities: ['TEXT'],
    },
    inputAudioTranscription: {
      languageCodes: ['es-ES'],
    },
  },
};
websocket.send(JSON.stringify(setupMessage));

config = types.LiveConnectConfig(
    response_modalities=["TEXT"],
    input_audio_transcription=types.AudioTranscriptionConfig(
        language_codes=[],
        custom_vocabulary=["Gemini", "Kubernetes", "BigQuery"],
    ),
)

const config = {
  responseModalities: [Modality.TEXT],
  inputAudioTranscription: {
    languageCodes: [],
    customVocabulary: ['Gemini', 'Kubernetes', 'BigQuery'],
  },
};

const setupMessage = {
  setup: {
    model: 'models/gemini-3.5-transcribe-live',
    generationConfig: {
      responseModalities: ['TEXT'],
    },
    inputAudioTranscription: {
      languageCodes: [],
      customVocabulary: ['Gemini', 'Kubernetes', 'BigQuery'],
    },
  },
};
websocket.send(JSON.stringify(setupMessage));

config = types.LiveConnectConfig(
    response_modalities=["TEXT"],
    input_audio_transcription=types.AudioTranscriptionConfig(
        mode="SMART",
    ),
)

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

const setupMessage = {
  setup: {
    model: 'models/gemini-3.5-transcribe-live',
    generationConfig: {
      responseModalities: ['TEXT'],
    },
    inputAudioTranscription: {
      mode: 'SMART',
    },
  },
};
websocket.send(JSON.stringify(setupMessage));

config = types.LiveConnectConfig(
    response_modalities=["TEXT"],
    input_audio_transcription=types.AudioTranscriptionConfig(),
)

async with client.aio.live.connect(model=model, config=config) as session:
    # Stream audio chunks...
    await session.send_realtime_input(
        audio=types.Blob(data=chunk, mime_type="audio/pcm;rate=16000")
    )

    # When client-side VAD detects end of speech, send audio_stream_end:
    await session.send_realtime_input(audio_stream_end=True)

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

// Stream audio...
session.sendRealtimeInput({
  audio: { data: chunkBase64, mimeType: 'audio/pcm;rate=16000' }
});

// When client VAD detects end of speech, send audioStreamEnd:
session.sendRealtimeInput({
  audioStreamEnd: true
});

const setupMessage = {
  setup: {
    model: 'models/gemini-3.5-transcribe-live',
    generationConfig: {
      responseModalities: ['TEXT'],
    },
    inputAudioTranscription: {},
  },
};
websocket.send(JSON.stringify(setupMessage));

// Stream audio...
websocket.send(JSON.stringify({
  realtimeInput: {
    audio: { data: chunkBase64, mimeType: 'audio/pcm;rate=16000' }
  }
}));

// When client VAD detects end of speech, send audioStreamEnd:
websocket.send(JSON.stringify({
  realtimeInput: {
    audioStreamEnd: true
  }
}));

config = types.LiveConnectConfig(
    response_modalities=["TEXT"],
    realtime_input_config=types.RealtimeInputConfig(
        automatic_activity_detection=types.AutomaticActivityDetection(
            disabled=True
        )
    ),
    input_audio_transcription=types.AudioTranscriptionConfig(),
)

async with client.aio.live.connect(model=model, config=config) as session:
    # Button pressed: signal speech start
    await session.send_realtime_input(activity_start=types.ActivityStart())

    # Stream audio chunks...
    await session.send_realtime_input(audio=types.Blob(data=chunk, mime_type="audio/pcm;rate=16000"))

    # Button released: signal speech end
    await session.send_realtime_input(activity_end=types.ActivityEnd())

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

// Signal speech start
session.sendRealtimeInput({ activityStart: {} });

// Stream audio...

// Signal speech end
session.sendRealtimeInput({ activityEnd: {} });

const setupMessage = {
  setup: {
    model: 'models/gemini-3.5-transcribe-live',
    generationConfig: {
      responseModalities: ['TEXT'],
    },
    realtimeInputConfig: {
      automaticActivityDetection: {
        disabled: true,
      },
    },
    inputAudioTranscription: {},
  },
};
websocket.send(JSON.stringify(setupMessage));

// Button pressed: signal speech start
websocket.send(JSON.stringify({
  realtimeInput: {
    activityStart: {},
  },
}));

// Stream audio...
websocket.send(JSON.stringify({
  realtimeInput: {
    audio: { data: chunkBase64, mimeType: 'audio/pcm;rate=16000' },
  },
}));

// Button released: signal speech end
websocket.send(JSON.stringify({
  realtimeInput: {
    activityEnd: {},
  },
}));

import datetime
from google import genai

client = genai.Client()
expire_time = datetime.datetime.now(tz=datetime.timezone.utc) + datetime.timedelta(minutes=30)

token = client.auth_tokens.create(
    config={
        "uses": 1,
        "expire_time": expire_time,
        "live_connect_constraints": {
            "model": "gemini-3.5-transcribe-live",
            "config": {
                "response_modalities": ["TEXT"],
                "input_audio_transcription": {
                    "language_codes": [],
                },
            },
        },
    }
)

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-transcribe-live',
      config: {
        responseModalities: ['TEXT'],
        inputAudioTranscription: {
          languageCodes: [],
        },
      },
    },
  },
});

curl -X POST "https://generativelanguage.googleapis.com/v1beta/auth_tokens" \
  -H "x-goog-api-key: ${GEMINI_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "uses": 1,
    "expireTime": "YYYY-MM-DDTHH:MM:SSZ",
    "liveConnectConstraints": {
      "model": "models/gemini-3.5-transcribe-live",
      "config": {
        "responseModalities": ["TEXT"],
        "inputAudioTranscription": {
          "languageCodes": []
        }
      }
    }
  }'