Implementation:Googleapis Python genai AsyncLiveMusic Connect

Knowledge Sources	Googleapis_Python_genai
Domains	Music_Generation, Real_Time_AI, Streaming
Last Updated	2026-02-15 14:00 GMT

Overview

Concrete tool for real-time music generation via WebSocket streaming provided by the Google Gen AI SDK.

Description

The AsyncLiveMusic class provides an experimental API module for real-time music generation sessions. The AsyncMusicSession class manages individual music sessions, supporting weighted text prompts, playback control (play/pause/stop), and continuous audio output streaming. This is an experimental feature.

Usage

Import this when building applications that generate music in real-time based on text prompts, such as AI-powered music composition tools or interactive audio experiences.

Code Reference

Source Location

Repository: Googleapis_Python_genai
File: google/genai/live_music.py
Lines: 45-211 (AsyncMusicSession at L45-157, AsyncLiveMusic at L160-211)

Signature

class AsyncLiveMusic(_api_module.BaseModule):
    @asynccontextmanager
    async def connect(
        self,
        *,
        model: str,
    ) -> AsyncIterator[AsyncMusicSession]: ...

class AsyncMusicSession:
    async def set_weighted_prompts(
        self, prompts: list[types.WeightedPrompt]
    ) -> None: ...

    async def set_music_generation_config(
        self, config: types.LiveMusicGenerationConfig
    ) -> None: ...

    async def play(self) -> None: ...
    async def pause(self) -> None: ...
    async def stop(self) -> None: ...
    async def reset_context(self) -> None: ...
    async def receive(self) -> AsyncIterator[types.LiveMusicServerMessage]: ...
    async def close(self) -> None: ...

Import

from google import genai
client = genai.Client(api_key="...")
# Access via: client.aio.live.music

I/O Contract

Inputs

Name	Type	Required	Description
model	str	Yes	Model ID for music generation
prompts	list[WeightedPrompt]	For set_weighted_prompts	Text prompts with weights guiding generation
config	LiveMusicGenerationConfig	For set_music_generation_config	Music generation parameters

Outputs

Name	Type	Description
connect() yields	AsyncMusicSession	Music session context manager
receive() yields	LiveMusicServerMessage	Audio data messages from the server

Usage Examples

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

client = genai.Client(api_key="GEMINI_API_KEY")

async def main():
    async with client.aio.live.music.connect(model="lyria-realtime-exp") as session:
        # Set music prompts
        await session.set_weighted_prompts([
            types.WeightedPrompt(text="calm piano jazz", weight=1.0),
        ])

        # Start playback
        await session.play()

        # Receive audio chunks
        async for message in session.receive():
            if message.data:
                # Process audio data
                pass

asyncio.run(main())

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment