ai-music

Generate vocal songs, instrumentals, jingles, and game loops via smart model routing across ElevenLabs and ACE Step.

- Routes to ElevenLabs AI Music (premium 44.1 kHz stereo, $0.0083/s) for polished commercial vocal hooks, or ACE Step base ($0.0002/s) and ACE Step 1.5 (50+ language vocal support) for cost-sensitive batches and multilingual launches

- Includes audio-inpaint (regenerate a time-bounded section) and audio-outpaint (extend a track before or after) for editing existing tracks

- Automatically selects the right model based on user intent: premium vs cost-sensitive, multilingual, vocal vs instrumental, generate vs edit

- Ships documented prompting patterns and exact runcomfy run invokes for each model and endpoint

AI Music

Generate AI music on RunComfy through one CLI - vocal songs, instrumentals, jingles, game loops, multilingual covers. This skill picks the right model from the RunComfy catalog based on the user's actual intent and ships the documented prompting patterns + the exact runcomfy run invoke for each.

runcomfy.com · Audio models · CLI docs

Install this skill

npx skills add agentspace-so/runcomfy-agent-skills --skill ai-music -g

Powered by the RunComfy CLI

Step 1 - install (one of, see the runcomfy-cli skill for details):