Leitfaden zu den Live API-Funktionen

import asyncio
from google import genai

client = genai.Client()

model = "gemini-3.1-flash-live-preview"
config = {"response_modalities": ["AUDIO"]}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:
        print("Session started")
        # Send content...

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

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

const ai = new GoogleGenAI({});
const model = 'gemini-3.1-flash-live-preview';
const config = { responseModalities: [Modality.AUDIO] };

async function main() {

  const session = await ai.live.connect({
    model: model,
    callbacks: {
      onopen: function () {
        console.debug('Opened');
      },
      onmessage: function (message) {
        console.debug(message);
      },
      onerror: function (e) {
        console.debug('Error:', e.message);
      },
      onclose: function (e) {
        console.debug('Close:', e.reason);
      },
    },
    config: config,
  });

  console.debug("Session started");
  // Send content...

  session.close();
}

main();

# 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'
  }
});

async for response in session.receive():
    if response.server_content and response.server_content.model_turn:
        for part in response.server_content.model_turn.parts:
            if part.inline_data:
                audio_data = part.inline_data.data
                # Process or play the audio data

// Inside the onmessage callback
const content = response.serverContent;
if (content?.modelTurn?.parts) {
  for (const part of content.modelTurn.parts) {
    if (part.inlineData) {
      const audioData = part.inlineData.data;
      // Process or play audioData (base64 encoded string)
    }
  }
}

await session.send_realtime_input(text="Hello, how are you?")

session.sendRealtimeInput({
  text: 'Hello, how are you?'
});

# Assuming 'frame' is your JPEG-encoded image bytes
await session.send_realtime_input(
    video=types.Blob(
        data=frame,
        mime_type="image/jpeg"
    )
)

// Assuming 'frame' is a Buffer of JPEG-encoded image data
session.sendRealtimeInput({
  video: {
    data: frame.toString('base64'),
    mimeType: 'image/jpeg'
  }
});

turns = [
    {"role": "user", "parts": [{"text": "What is the capital of France?"}]},
    {"role": "model", "parts": [{"text": "Paris"}]},
]

await session.send_client_content(turns=turns, turn_complete=False)

turns = [{"role": "user", "parts": [{"text": "What is the capital of Germany?"}]}]

await session.send_client_content(turns=turns, turn_complete=True)

let inputTurns = [
  { "role": "user", "parts": [{ "text": "What is the capital of France?" }] },
  { "role": "model", "parts": [{ "text": "Paris" }] },
]

session.sendClientContent({ turns: inputTurns, turnComplete: false })

inputTurns = [{ "role": "user", "parts": [{ "text": "What is the capital of Germany?" }] }]

session.sendClientContent({ turns: inputTurns, turnComplete: