mcpField
M
music

music

github.com/calesthioCreative & media73.0k1.1k installsUpdated 1d ago
Repository

About music

music is a skill for generating music through the ElevenLabs API from text prompts or structured composition plans. It supports instrumental tracks and songs with lyrics, with methods for composing, planning, and returning audio with metadata.

Key features

  1. 01Generate music from text prompts
  2. 02Create and edit composition plans
  3. 03Compose audio with detailed metadata
  4. 04Upload audio for supported inpainting workflows

Use cases

  1. 01Create an instrumental track from a description
  2. 02Plan and refine a longer orchestral composition

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/calesthio/openmontage --skill music

After installing, type/musicin Claude Code to confirm it loaded.

Bundled filesreferences/api_reference.mdreferences/installation.md

Details

From the project README

ElevenLabs Music Generation

Generate music from text prompts - supports instrumental tracks, songs with lyrics, and fine-grained control via composition plans.

Setup: See Installation Guide. For JavaScript, use @elevenlabs/* packages only.

Quick Start

Python
from elevenlabs import ElevenLabs

client = ElevenLabs()

audio = client.music.compose(
    prompt="A chill lo-fi hip hop beat with jazzy piano chords",
    music_length_ms=30000
)

with open("output.mp3", "wb") as f:
    for chunk in audio:
        f.write(chunk)
JavaScript
import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";
import { createWriteStream } from "fs";

const client = new ElevenLabsClient();
const audio = await client.music.compose({
  prompt: "A chill lo-fi hip hop beat with jazzy piano chords",
  musicLengthMs: 30000,
});
audio.pipe(createWriteStream("output.mp3"));
cURL
curl -X POST "https://api.elevenlabs.io/v1/music" \
  -H "xi-api-key: $ELEVENLABS_API_KEY" -H "Content-Type: application/json" \
  -d '{"prompt": "A chill lo-fi beat", "music_length_ms": 30000}' --output output.mp3

Methods

MethodDescription
music.composeGenerate audio from a prompt or composition plan
music.composition_plan.createGenerate a structured plan for fine-grained control
music.compose_detailedGenerate audio + composition plan + metadata
music.uploadUpload an audio file for later inpainting workflows and optionally extract its composition plan

See API Reference for full parameter details.

music.upload is available to enterprise clients with access to the inpainting feature.

Composition Plans

For granular control, generate a composition plan first, modify it, then compose:

plan = client.music.composition_plan.create(
    prompt="An epic orchestral piece building to a climax",
    music_length_ms=60000
)

# Inspect/modify styles and sections
print(plan.positiveGlobalStyles)  # e.g. ["orchestral", "epic", "cinematic"]

audio = client.music.compose(
    composition_plan=plan,
    music_length_ms=60000
)

Content Restrictions

  • Cannot reference specific artists, bands, or copyrighted lyrics
  • bad_prompt errors include a prompt_suggestion with alternative phrasing
  • bad_composition_plan errors include a composition_plan_suggestion

Error Handling

try:
    audio = client.music.compose(prompt="...", music_length_ms=30000)
except Exception as e:
    print(f"API error: {e}")

Common errors: 401 (invalid key), 422 (invalid params), 429 (rate limit).

References

Comments

Markdown supported