Live API

# Test file: https://storage.googleapis.com/generativeai-downloads/data/16000.wav
# Install helpers for converting files: pip install librosa soundfile

import asyncio
import io
from pathlib import Path
from google import genai
from google.genai import types
import soundfile as sf
import librosa

client = genai.Client(
    vertexai=True,
    project=GOOGLE_CLOUD_PROJECT,
    location=GOOGLE_CLOUD_LOCATION,
)
model = "gemini-live-2.5-flash"
config = {"response_modalities": ["TEXT"]}

async def main():
    async with client.aio.live.connect(model=model, config=config) as session:

        buffer = io.BytesIO()
        y, sr = librosa.load("sample.wav", sr=16000)
        sf.write(buffer, y, sr, format="RAW", subtype="PCM_16")
        buffer.seek(0)
        audio_bytes = buffer.read()

        # If already in correct format, you can use this:
        # audio_bytes = Path("sample.pcm").read_bytes()

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

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

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

import asyncio
import numpy as np
from IPython.display import Audio, Markdown, display
from google import genai
from google.genai.types import (
  Content,
  LiveConnectConfig,
  HttpOptions,
  Modality,
  Part,
  SpeechConfig,
  VoiceConfig,
  PrebuiltVoiceConfig,
)

client = genai.Client(
  vertexai=True,
  project=GOOGLE_CLOUD_PROJECT,
  location=GOOGLE_CLOUD_LOCATION,
)

voice_name = "Aoede"

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

async with client.aio.live.connect(
  model="gemini-live-2.5-flash",
  config=config,
) as session:
  text_input = "Hello? Gemini are you there?"
  display(Markdown(f"**Input:** {text_input}"))

  await session.send_client_content(
      turns=Content(role="user", parts=[Part(text=text_input)]))

  audio_data = []
  async for message in session.receive():
      if (
          message.server_content.model_turn
          and message.server_content.model_turn.parts
      ):
          for part in message.server_content.model_turn.parts:
              if part.inline_data:
                  audio_data.append(
                      np.frombuffer(part.inline_data.data, dtype=np.int16)
                  )

  if audio_data:
      display(Audio(np.concatenate(audio_data), rate=24000, autoplay=True))
    

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"

config = {
    "response_modalities": ["AUDIO"],
    "input_audio_transcription": {},
    "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.input_transcription:
                print("Input transcript:", response.server_content.input_transcription.text)
            if response.server_content.output_transcription:
                print("Output transcript:", response.server_content.output_transcription.text)

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

      

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

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

# Connect to the server
async with connect(SERVICE_URL, additional_headers=headers) as ws:
    # Setup the session
    await ws.send(
        json.dumps(
            {
                "setup": {
                    "model": "gemini-2.0-flash-live-preview-04-09",
                    "generation_config": CONFIG,
                    'input_audio_transcription': {},
                    'output_audio_transcription': {}
                }
            }
        )
    )

    # Receive setup response
    raw_response = await ws.recv(decode=False)
    setup_response = json.loads(raw_response.decode("ascii"))

    # Send text message
    text_input = "Hello? Gemini are you there?"
    display(Markdown(f"**Input:** {text_input}"))

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

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

    responses = []
    input_transcriptions = []
    output_transcriptions = []

    # 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

        if (input_transcription := server_content.get("inputTranscription")) is not None:
            if (text := input_transcription.get("text")) is not None:
                input_transcriptions.append(text)
        if (output_transcription := server_content.get("outputTranscription")) is not None:
            if (text := output_transcription.get("text")) is not None:
                output_transcriptions.append(text)

        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

    if input_transcriptions:
        display(Markdown(f"**Input transcription >** {''.join(input_transcriptions)}"))

    if responses:
        # Play the returned audio message
        display(Audio(np.concatenate(responses), rate=24000, autoplay=True))

    if output_transcriptions:
        display(Markdown(f"**Output transcription >** {''.join(output_transcriptions)}"))