Multimodal Live API

import asyncio
from google import genai

client = genai.Client(api_key="GEMINI_API_KEY", http_options={'api_version': 'v1alpha'})
model = "gemini-2.0-flash-exp"

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

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        while True:
            message = input("User> ")
            if message.lower() == "exit":
                break
            await session.send(input=message, end_of_turn=True)

            async for response in session.receive():
                if response.text is not None:
                    print(response.text, end="")

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

import asyncio
import wave
from google import genai

client = genai.Client(api_key="GEMINI_API_KEY", http_options={'api_version': 'v1alpha'})
model = "gemini-2.0-flash-exp"

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

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        wf = wave.open("audio.wav", "wb")
        wf.setnchannels(1)
        wf.setsampwidth(2)
        wf.setframerate(24000)

        message = "Hello? Gemini are you there?"
        await session.send(input=message, end_of_turn=True)

        async for idx,response in async_enumerate(session.receive()):
            if response.data is not None:
                wf.writeframes(response.data)

            # Comment this out to print audio data info
            # if response.server_content.model_turn is not None:
            #      print(response.server_content.model_turn.parts[0].inline_data.mime_type)

        wf.close()

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"],
}

config = types.LiveConnectConfig(
    response_modalities=["TEXT"],
    tools=[set_light_values]
)

async with client.aio.live.connect(model=model, config=config) as session:
    await session.send(input="Turn the lights down to a romantic level", end_of_turn=True)

    async for response in session.receive():
        print(response.tool_call)

async for response in session.receive():
    if response.server_content.interrupted is not None:
        # The generation was interrupted

{
  "model": string,
  "generationConfig": {
    "candidateCount": integer,
    "maxOutputTokens": integer,
    "temperature": number,
    "topP": number,
    "topK": integer,
    "presencePenalty": number,
    "frequencyPenalty": number,
    "responseModalities": [string],
    "speechConfig": object
  },
  "systemInstruction": string,
  "tools": [object]
}

{
  "setup": BidiGenerateContentSetup,
  "clientContent": BidiGenerateContentClientContent,
  "realtimeInput": BidiGenerateContentRealtimeInput,
  "toolResponse": BidiGenerateContentToolResponse
}

async with client.aio.live.connect(model='...', config=config) as session:
    await session.send(input='Hello world!', end_of_turn=True)
    async for message in session.receive():
        print(message)

{
  "setupComplete": BidiGenerateContentSetupComplete,
  "serverContent": BidiGenerateContentServerContent,
  "toolCall": BidiGenerateContentToolCall,
  "toolCallCancellation": BidiGenerateContentToolCallCancellation
}