Generate and edit AI music via the RunComfy CLI across ElevenLabs and ACE Step models.
npx skills add https://github.com/genmedia-labs/skills --skill ai-music-genmedia-labs
Please help me install this Agent Skill. Skill: ai-music Source: https://github.com/genmedia-labs/skills/tree/main/ai-music Command: npx skills add https://github.com/genmedia-labs/skills --skill ai-music-genmedia-labs
runcomfy run invocation for it. ## Core Features & Use Cases - Intent-based model routing: Classifies requests as premium vs cost-sensitive, multilingual, vocal vs instrumental, and generate vs edit, then picks ElevenLabs Music, ACE Step, or ACE Step 1.5 accordingly. - Text-to-music generation: Produces vocal songs, instrumentals, jingles, and game loops from 5 seconds to 5 minutes, with tag-driven composition and structured lyrics. - Audio editing: Regenerates a time range inside an existing track (audio-inpaint) or extends a track before/after (audio-outpaint) via ACE Step endpoints. - Use Case: A user asks for a 2-minute multilingual pop song on a budget — the Skill selects ACE Step 1.5, builds the tags and lyrics JSON, and runs runcomfy run acestep-ai/ace-step-1.5/text-to-audio to deliver the track. ## Quick Start Ask the agent to generate a 60-second upbeat indie-pop song with female vocals using the ai-music skill, and it will pick the right model and run the runcomfy CLI command for you.High-intent search queries and answers about installing and using this skill.
Install the CLI with npm i -g @runcomfy/cli, sign in with runcomfy login, then run runcomfy run <vendor>/<model>/<endpoint> with a JSON --input body containing your prompt, tags, or lyrics. The CLI polls the request and downloads the audio to your output directory.
ElevenLabs Music delivers premium 44.1 kHz stereo vocal tracks at $0.0083/s, suited for commercial and brand work. ACE Step is open-weights and roughly 27x cheaper at $0.0002/s, making it better for drafts, background music libraries, and high-volume generation.
Yes. ACE Step 1.5 supports vocal generation in over 50 languages by passing lyrics in the target language with structured [Verse]/[Chorus] markers. ElevenLabs Music also supports multilingual vocals through its single prompt field.
Use ACE Step audio-outpaint to add intro or outro sections before or after a track, or audio-inpaint to regenerate a specific time range such as a bad chorus. Both take the source audio URL plus tags describing the desired style.
Audio-inpaint only edits ranges bounded by start_time and end_time, and audio-outpaint caps total length at 4 minutes per call. ElevenLabs Music has no edit endpoints, so edits must go through ACE Step or a full regeneration.
prime-skillsGenerate, repair, and extend music via RunComfy CLI with structured JSON inputs.
refly-aiGenerates short AI-powered videos and scripts for social media platforms.
DevMatt6Automate video content creation with AI generation models and avatars.
thmtzRoute NanoClaw agent groups to a local Ollama model via configuration changes.