Route music prompts to ElevenLabs or ACE Step models on RunComfy.
npx skills add https://github.com/doany-ai/skills --skill ai-music-doany-ai
Please help me install this Agent Skill. Skill: ai-music Source: https://github.com/doany-ai/skills/tree/main/ai-music Command: npx skills add https://github.com/doany-ai/skills --skill ai-music-doany-ai
Generate AI music on RunComfy via a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model for the user's actual intent — premium vocal hook, cheap background music library, multilingual pop song, repair a bad chorus, lengthen a 30 s draft into a 2 min cut — and ships each model's documented prompting patterns plus the minimal runcomfy run invocation. Triggers on generate music, make a song, AI music, background music, instrumental track, soundtrack, jingle, theme music, royalty-free music, compose, music with lyrics, extend music, fix this song, inpaint music, or any explicit ask to generate or edit music.
Provide a music prompt and optional lyrics, choose a model, and let RunComfy generate the track to the output directory.
High-intent search queries and answers about installing and using this skill.
AI music generation routes your prompt to the correct model, supporting multilingual lyrics, vocal tracks, and instrumentals with adjustable durations from 5 seconds to 5 minutes.
Generating background music is cheapest via ACE Step models, costing roughly $0.0002 to $0.0003 per second, making it about 27 times cheaper than premium vocal track generation.
Yes, you can fix or extend existing audio tracks using ACE Step audio-inpaint and audio-outpaint features. Inpainting regenerates a specific time range inside a track, while outpainting extends the audio before or after the current cut.
Yes, the generator supports premium vocal songs and jingles by routing to ElevenLabs AI Music Generation. It produces 44.1 kHz stereo vocal tracks with durations ranging from 5 seconds to 5 minutes.
You apply section markers and prompting patterns by including them directly in your music prompt. The system ships each model's documented prompting patterns, ensuring the RunComfy invocation correctly processes tags, lyrics, and time ranges.
prime-skillsGenerate songs and instrumental audio from text and lyrics via RunComfy.
GeneralReasoningExtract, normalize, and mix audio tracks from video files using FFmpeg.
prime-skillsGenerate, repair, and extend music via RunComfy CLI with structured JSON inputs.
agentspace-soRoute natural-language music requests to RunComfy text-to-audio or ACE Step endpoints.
