elevenlabs-music-generation

Generate songs and instrumental tracks from text prompts via the RunComfy CLI.

12|2|Updated Aug 12, 2026
One-click install
npx skills add https://github.com/genmedia-labs/skills --skill elevenlabs-music-generation-genmedia-labs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: elevenlabs-music-generation
Source: https://github.com/genmedia-labs/skills/tree/main/elevenlabs-music-generation
Command: npx skills add https://github.com/genmedia-labs/skills --skill elevenlabs-music-generation-genmedia-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @runcomfy/cli.

What problem does it solve? Creating original music for videos, podcasts, games, or brand assets normally requires composition skills or licensing stock tracks. This Skill lets you generate studio-quality 44.1 kHz stereo songs and instrumentals — 5 seconds to 5 minutes — directly from a text description using ElevenLabs Music on the RunComfy Model API. ## Core Features & Use Cases - Full vocal songs: Combine a style brief with lyrics and section markers ([Intro], [Verse], [Chorus], [Bridge]) for structured, multilingual vocal tracks. - Instrumental beds: Set force_instrumental to true for background music, podcast intros, game loops, and jingles with no vocals. - Duration and cost control: Set music_length_ms from 5000 to 300000 ms; draft short (~30 s) to validate direction before paying for a full-length render. - Use Case: A video creator needs a 60-second upbeat indie-pop theme song with vocals — provide the style brief and structured lyrics, and the CLI downloads the finished MP3 to the output directory. ## Quick Start Ask the agent to generate a 60-second upbeat indie-pop song with verse and chorus lyrics using ElevenLabs Music on RunComfy and save it to the ./out folder.

Frequently Asked Questions about elevenlabs-music-generation

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

FAQPage Schema
How do I generate AI music with ElevenLabs Music?▼

Run runcomfy run elevenlabs/elevenlabs/music-generation with a JSON input containing a prompt field that combines a style brief (genre, tempo, instruments, vocal type) and lyrics with section markers like [Verse] and [Chorus]. The CLI downloads the generated audio to your output directory.

How do I generate instrumental music without vocals?▼

Set force_instrumental to true in the input JSON and also state "no vocals" in the prompt text. This produces instrumental-only output suitable for background music, podcast intros, and game loops.

What is the maximum song length ElevenLabs Music can generate?▼

A single call supports music_length_ms from 5000 to 300000, meaning 5 seconds to 5 minutes of audio. For longer pieces, generate sections separately and stitch them externally.

How much does ElevenLabs Music generation cost?▼

Pricing is approximately $0.0083 per second of generated audio, so a 30-second track costs about $0.25 and a 5-minute track about $2.49. Draft at short durations to validate direction before rendering full length.

Can ElevenLabs Music clone a specific singer's voice?▼

No. The endpoint only offers force_instrumental as a vocal toggle; you cannot request specific voice identities or clone a singer. Voice cloning and text-to-speech are separate ElevenLabs capabilities not exposed through this endpoint.

Why did the runcomfy CLI exit with code 77?▼

Exit code 77 means you are not signed in or the token was rejected. Run runcomfy login to authenticate, or set the RUNCOMFY_TOKEN environment variable in CI environments.