Live API

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

client = genai.Client(api_key="GEMINI_API_KEY")
model = "gemini-2.0-flash-live-001"

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())

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

client = genai.Client(api_key="GEMINI_API_KEY")
model = "gemini-2.0-flash-live-001"

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

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

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

        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())

from google.genai import types

config = {
    "system_instruction": types.Content(
        parts=[
            types.Part(
                text="You are a helpful assistant and answer in a friendly tone."
            )
        ]
    ),
    "response_modalities": ["TEXT"],
}

from google.genai import types

config = types.LiveConnectConfig(
    response_modalities=["AUDIO"],
    speech_config=types.SpeechConfig(
        language_code="de-DE",
    )
)

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

client = genai.Client(api_key="GEMINI_API_KEY")
model = "gemini-2.0-flash-live-001"

# 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": ["TEXT"], "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}]})

        async for chunk in session.receive():
            if chunk.server_content:
                if chunk.text is not None:
                    print(chunk.text)
            elif chunk.tool_call:
                function_responses = []
                for fc in 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)


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

  # 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

# Non-blocking function definitions
  function_response = types.FunctionResponse(
      id=fc.id,
      name=fc.name,
      response={
          "result": "ok",
          "scheduling": "INTERRUPT" # Can also be WHEN_IDLE or SILENT
      }
  )

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

client = genai.Client(api_key="GEMINI_API_KEY")
model = "gemini-2.0-flash-live-001"

tools = [{'code_execution': {}}]
config = {"response_modalities": ["TEXT"], "tools": tools}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        prompt = "Compute the largest prime palindrome under 100000."
        await session.send_client_content(turns={"parts": [{"text": prompt}]})

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

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

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

client = genai.Client(api_key="GEMINI_API_KEY")
model = "gemini-2.0-flash-live-001"

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

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

                # 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)

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

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

1. Compute the largest prime palindrome under 100000.
2. Then use Google Search to look up information about the largest earthquake in California the week of Dec 5 2024?
3. Turn on the lights

Thanks!
"""

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

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

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

# 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(api_key="GEMINI_API_KEY")
model = "gemini-2.0-flash-live-001"

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())

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,
        }
    }
}

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())
    # ...

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}")

from google.genai import types

config = types.LiveConnectConfig(
    response_modalities=["AUDIO"],
    context_window_compression=(
        # Configures compression with default parameters.
        types.ContextWindowCompressionConfig(
            sliding_window=types.SlidingWindow(),
        )
    ),
)

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

client = genai.Client(api_key="GEMINI_API_KEY")
model = "gemini-2.0-flash-live-001"

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())

async for response in session.receive():
    if response.go_away is not None:
        # The connection will soon be terminated
        print(response.go_away.time_left)

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

from google.genai import types

config = types.LiveConnectConfig(
    response_modalities=["AUDIO"],
    media_resolution=types.MediaResolution.MEDIA_RESOLUTION_LOW,
)