What problem does it solve? Choosing the right AI music model and crafting the correct API call for each one is confusing and time-consuming. This Skill routes your music request to the right RunComfy model — premium ElevenLabs generation, low-cost ACE Step, or audio inpaint/outpaint editing — and provides the exact CLI command to run. ## Core Features & Use Cases - Intent-based model routing: Classifies requests as premium vs cost-sensitive, vocal vs instrumental, generate vs edit, then picks ElevenLabs Music, ACE Step, ACE Step 1.5, audio-inpaint, or audio-outpaint. - Text-to-music generation: Create vocal songs, instrumentals, jingles, and game loops from 5 seconds to 5 minutes, with multilingual lyrics support in 50+ languages. - Audio editing: Regenerate a specific time range inside an existing track (inpaint) or extend a track before/after (outpaint) without re-rendering the whole song. - Use Case: You generated a 30-second hook but need a 2-minute track for a video. The Skill routes to ACE Step audio-outpaint, adding a 30-second intro and 60-second outro in one runcomfy run call. ## Quick Start Ask the AI to generate a 60-second upbeat indie-pop song with female vocals using the ai-music skill.
