skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

elevenlabs-music

Generates original music from text prompts via the ElevenLabs API through the inference.sh CLI.

Updated Jul 28, 2026
Search Tags:#audio#music generation#elevenlabs#soundtrack#text-to-music#ai music#jingle
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill elevenlabs-music-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: elevenlabs-music
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/elevenlabs-music
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill elevenlabs-music-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating original, royalty-free music for videos, podcasts, games, and ads normally requires composers, licensing fees, or stock music searches. This Skill generates custom music tracks directly from text descriptions using the ElevenLabs music model. ## Core Features & Use Cases - Text-to-Music Generation: Describe genre, mood, instruments, and tempo in a prompt to produce an original track. - Custom Duration Control: Generate clips from 5 seconds up to 10 minutes, suitable for jingles, loops, or full soundtracks. - Use Case: A video editor needs a 45-second epic orchestral score for a trailer. They run one CLI command with a descriptive prompt and receive a royalty-free track ready for commercial use. ## Quick Start Ask the AI to generate a 60-second lo-fi study music track using the elevenlabs music skill.

Frequently Asked Questions about elevenlabs-music

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

FAQPage Schema
How do I generate music from a text prompt with ElevenLabs?▼

Run belt app run elevenlabs/music with a JSON input containing a prompt describing genre, mood, and instruments. The CLI returns a generated audio track matching your description.

What is the maximum music length ElevenLabs can generate?▼

The duration_seconds parameter accepts values from 5 to 600 seconds, so tracks can be up to 10 minutes long. The default duration is 30 seconds if not specified.

Can I use ElevenLabs generated music commercially?▼

Yes, the generated music is royalty-free and cleared for commercial use, making it suitable for ads, videos, games, and podcasts without additional licensing fees.

How do I combine generated music with a voiceover?▼

Generate the music track and the TTS voiceover separately, then merge them using the infsh/media-merger app by passing both media URLs as input.

What do I need installed before running the music generation command?▼

You need the inference.sh belt CLI installed and authenticated via belt login. Install instructions are provided in the linked cli-install guide from the inference-sh skills repository.

Related Skills

Explore More Design & Creative Skills→
inference-shinference-sh
723

elevenlabs-music

Generates original music from text prompts via the ElevenLabs API through the inference.sh CLI.

Official
Basic
inference-shinference-sh
723

ai-podcast

Generates multi-speaker talking head podcast videos via portrait, TTS, avatar, and merge pipeline.

Official
Advanced
wells1137wells1137
25

AudioMind

Route TTS, music, and SFX tasks through ElevenLabs and fal.ai.

Community
Advanced
inference-shinference-sh
688

ai-music-generation

Generates AI music and songs from text prompts using Diffrythm or Tencent Song Generation.

Official
Basic