lexigram-multimedia-music

Music generation for the Lexigram Framework — local and API-based backends (local-http, stability-audio, ace-step, stable-audio-open).

Overview

lexigram-multimedia-music generates music and sound from a text prompt. The default backend calls a local HTTP reference server (http://localhost:5003) so the package works out of the box with no API keys; hosted backends (Stability Audio) and in-process reference servers (ACE-Step, Stable Audio Open) are selectable via config.

Full documentation: docs.lexigram.dev

Install

uv add lexigram-multimedia-music
# Optional extras
uv add "lexigram-multimedia-music[stability-audio]"    # Stability Audio API
uv add "lexigram-multimedia-music[ace-step-server]"    # local ACE-Step server (torch)
uv add "lexigram-multimedia-music[stable-audio-open-server]"  # local Stable Audio Open server (torch)

Quick Start

from lexigram import Application
from lexigram.di.module import Module, module
from lexigram.multimedia.music import AudioMusicModule
from lexigram.contracts.multimedia import MusicProvider, MusicRequest


@module(imports=[AudioMusicModule.configure()])
class AppModule(Module):
    pass


async def main() -> None:
    async with Application.boot(modules=[AppModule]) as app:
        music = await app.container.resolve(MusicProvider)
        result = await music.generate(MusicRequest(prompt="upbeat synthwave, 120 bpm"))
        if result.is_ok():
            asset = result.unwrap()  # MediaAsset — audio bytes or URI


if __name__ == "__main__":
    import asyncio

    asyncio.run(main())

Configuration

Zero-config usage: Call AudioMusicModule.configure() with no arguments to use the local-http backend at http://localhost:5003.

Option 1 — YAML file

# application.yaml
multimedia:
  music:
    backend: "ace-step"

Option 2 — Profiles + Environment Variables

export LEX_PROFILE=production
export LEX_MULTIMEDIA_MUSIC__BACKEND=ace-step

Option 3 — Python

from lexigram.multimedia.music import AudioMusicModule
from lexigram.multimedia.music.config import MusicConfig

AudioMusicModule.configure(config=MusicConfig(backend="ace-step"))

Config reference

Module Factory Methods

Key Features

• Four backends — local-http, stability-audio, ace-step, stable-audio-open
• Reference servers — lexigram-music-ace-step-serve and lexigram-music-stable-audio-open-serve console scripts run each local model server
• Result-based — generate() -> Result[MediaAsset, MultimediaError]; errors are domain values, not exceptions

Testing

from lexigram import Application
from lexigram.multimedia.music import AudioMusicModule

async def test_boot():
    async with Application.boot(modules=[AudioMusicModule.stub()]) as app:
        assert app.container is not None

Key Source Files