Music Faculty — Expression

Generate songs, instrumentals, or melodies from text prompts via ElevenLabs Music API.

45|5|Updated Feb 12, 2026
One-click install
npx skills add https://github.com/acnlabs/OpenPersona --skill music-faculty-expression
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Music Faculty — Expression
Source: https://github.com/acnlabs/OpenPersona/tree/main/layers/faculties/music
Command: npx skills add https://github.com/acnlabs/OpenPersona --skill music-faculty-expression

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, and includes scripts (resource) components.

What problem does it solve?

Create evocative, on-demand music from simple text prompts so personas can express emotion, set mood, or accompany conversations without manual composition work.

Core Features & Use Cases

  • Text-to-music generation: Turn a short description into a finished audio file (song or instrumental) using ElevenLabs Music API.
  • Two generation modes: Quick simple mode for fast compositions and Plan mode for structured sections, lyrics, and precise control.
  • Format, duration, and delivery: Choose output format and duration, save locally, or send via OpenClaw for integrated sharing during interactions.
  • Use Case: Compose a 30-second ambient piano piece to comfort a user during a late-night chat or set a persona-specific musical theme.

Quick Start

Compose a soft ambient piano piece about watching stars alone at 3am.

Frequently Asked Questions about Music Faculty — Expression

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate original music from text prompts?

You can generate original music by providing a short text prompt to the ElevenLabs Music API, which produces a finished audio file. This supports songs, instrumentals, and mood-driven soundtracks without manual composition.

Can I control song duration and output format for generated audio?

Yes, you can control output format and duration for your generated music. Plan mode provides structured sections, lyrics, and precise control, while simple mode offers fast compositions for immediate text-to-audio results.

Do I need an ElevenLabs Music API key to compose songs?

Yes, ElevenLabs Music API access is required to generate audio. You must authenticate with the API to process text prompts and retrieve the generated music files or stream the audio output.

What is the difference between simple mode and plan mode for songwriting?

Simple mode creates fast compositions from basic text prompts, while Plan mode structures sections and lyrics for precise control. Plan mode suits persona-driven composition tasks like setting poems to music or creating specific soundtracks.

How do I share generated instrumentals during conversations?

You can deliver generated audio via OpenClaw for integrated sharing during interactions. After the audio generation completes, OpenClaw routes the output to accompany conversations or send persona-specific musical themes.

What are the limitations of text-to-music generation with the ElevenLabs Music API?

Generation quality depends on prompt clarity and API capabilities. Complex compositions with specific instrumental layering may require Plan mode, and streaming endpoints or local saves are needed to retain output files.