Live API によるインタラクティブな会話

"""
# Installation
# on linux
sudo apt-get install portaudio19-dev

# on mac
brew install portaudio

python3 -m venv env
source env/bin/activate
pip install google-genai
"""

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

CHUNK=4200
FORMAT=pyaudio.paInt16
CHANNELS=1
RECORD_SECONDS=5
MODEL = 'gemini-live-2.5-flash'
INPUT_RATE=16000
OUTPUT_RATE=24000

client = genai.Client(
    vertexai=True,
    project=GOOGLE_CLOUD_PROJECT,
    location=GOOGLE_CLOUD_LOCATION,
)
config = {
    "response_modalities": ["AUDIO"],
    "input_audio_transcription": {},  # Configure input transcription
    "output_audio_transcription": {},  # Configure output transcription
}

async def main():
    print(MODEL)
    p = pyaudio.PyAudio()
    async with client.aio.live.connect(model=MODEL, config=config) as session:
        #exit()
        async def send():
            stream = p.open(
                format=FORMAT, channels=CHANNELS, rate=INPUT_RATE, input=True, frames_per_buffer=CHUNK)
            while True:
                frame = stream.read(CHUNK)
                await session.send(input={"data": frame, "mime_type": "audio/pcm"})
                await asyncio.sleep(10**-12)
        async def receive():
            output_stream = p.open(
                format=FORMAT, channels=CHANNELS, rate=OUTPUT_RATE, output=True, frames_per_buffer=CHUNK)
            async for message in session.receive():
                if message.server_content.input_transcription:
                  print(message.server_content.model_dump(mode="json", exclude_none=True))
                if message.server_content.output_transcription:
                  print(message.server_content.model_dump(mode="json", exclude_none=True))
                if message.server_content.model_turn:
                    for part in message.server_content.model_turn.parts:
                        if part.inline_data.data:
                            audio_data=part.inline_data.data
                            output_stream.write(audio_data)
                            await asyncio.sleep(10**-12)
        send_task = asyncio.create_task(send())
        receive_task = asyncio.create_task(receive())
        await asyncio.gather(send_task, receive_task)

asyncio.run(main())
      

# Set model generation_config
CONFIG = {"response_modalities": ["AUDIO"]}

headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {bearer_token[0]}",
}

async def main() -> None:
    # Connect to the server
    async with connect(SERVICE_URL, additional_headers=headers) as ws:

        # Setup the session
        async def setup() -> None:
            await ws.send(
                json.dumps(
                    {
                        "setup": {
                            "model": "gemini-live-2.5-flash",
                            "generation_config": CONFIG,
                        }
                    }
                )
            )

            # Receive setup response
            raw_response = await ws.recv(decode=False)
            setup_response = json.loads(raw_response.decode("ascii"))
            print(f"Connected: {setup_response}")
            return

        # Send text message
        async def send() -> bool:
            text_input = input("Input > ")
            if text_input.lower() in ("q", "quit", "exit"):
                return False

            msg = {
                "client_content": {
                    "turns": [{"role": "user", "parts": [{"text": text_input}]}],
                    "turn_complete": True,
                }
            }

            await ws.send(json.dumps(msg))
            return True

        # Receive server response
        async def receive() -> None:
            responses = []

            # Receive chucks of server response
            async for raw_response in ws:
                response = json.loads(raw_response.decode())
                server_content = response.pop("serverContent", None)
                if server_content is None:
                    break

                model_turn = server_content.pop("modelTurn", None)
                if model_turn is not None:
                    parts = model_turn.pop("parts", None)
                    if parts is not None:
                        for part in parts:
                            pcm_data = base64.b64decode(part["inlineData"]["data"])
                            responses.append(np.frombuffer(pcm_data, dtype=np.int16))

                # End of turn
                turn_complete = server_content.pop("turnComplete", None)
                if turn_complete:
                    break

            # Play the returned audio message
            display(Markdown("**Response >**"))
            display(Audio(np.concatenate(responses), rate=24000, autoplay=True))
            return

        await setup()

        while True:
            if not await send():
                break
            await receive()
      

await main()
      

config = LiveConnectConfig(
    response_modalities=["AUDIO"],
    speech_config=SpeechConfig(
        voice_config=VoiceConfig(
            prebuilt_voice_config=PrebuiltVoiceConfig(
                voice_name=voice_name,
            )
        ),
        language_code="en-US",
    ),
)
      

config = LiveConnectConfig(
    response_modalities=["TEXT"],
    realtime_input_config=RealtimeInputConfig(
        automatic_activity_detection=AutomaticActivityDetection(
            disabled=False,  # default
            start_of_speech_sensitivity=StartSensitivity.START_SENSITIVITY_LOW, # Either START_SENSITIVITY_LOW or START_SENSITIVITY_HIGH
            end_of_speech_sensitivity=EndSensitivity.END_SENSITIVITY_LOW, # Either END_SENSITIVITY_LOW or END_SENSITIVITY_HIGH
            prefix_padding_ms=20,
            silence_duration_ms=100,
        )
    ),
)

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

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

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

    response = []
    async for message in session.receive():
        if message.server_content.interrupted is True:
            # The model generation was interrupted
            response.append("The session was interrupted")

        if message.text:
            response.append(message.text)

    display(Markdown(f"**Response >** {''.join(response)}"))
      

config = types.LiveConnectConfig(
      temperature=0.7,
      response_modalities=['TEXT'],
      system_instruction=types.Content(
          parts=[types.Part(text='test instruction')], role='user'
      ),
      context_window_compression=types.ContextWindowCompressionConfig(
          trigger_tokens=1000,
          sliding_window=types.SlidingWindow(target_tokens=10),
      ),
  )
      

session.send_client_content(
      turns=types.Content(
          role="system", parts=[types.Part(text="new system instruction")]
      ),
      turn_complete=False
  )
      

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

client = genai.Client(
    vertexai=True,
    project=GOOGLE_CLOUD_PROJECT,
    location=GOOGLE_CLOUD_LOCATION,
)
model = "gemini-live-2.5-flash"

async def main():
    print(f"Connecting to the service with handle {previous_session_handle}...")
    async with client.aio.live.connect(
        model=model,
        config=types.LiveConnectConfig(
            response_modalities=["AUDIO"],
            session_resumption=types.SessionResumptionConfig(
                # The handle of the session to resume is passed here,
                # or else None to start a new session.
                handle=previous_session_handle
            ),
        ),
    ) as session:
        while True:
            await session.send_client_content(
                turns=types.Content(
                    role="user", parts=[types.Part(text="Hello world!")]
                )
            )
            async for message in session.receive():
                # Periodically, the server will send update messages that may
                # contain a handle for the current state of the session.
                if message.session_resumption_update:
                    update = message.session_resumption_update
                    if update.resumable and update.new_handle:
                        # The handle should be retained and linked to the session.
                        return update.new_handle

                # For the purposes of this example, placeholder input is continually fed
                # to the model. In non-sample code, the model inputs would come from
                # the user.
                if message.server_content and message.server_content.turn_complete:
                    break

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

types.LiveConnectConfig(
            response_modalities=["AUDIO"],
            session_resumption=types.SessionResumptionConfig(
                transparent=True,
    ),
)