Generate and edit AI music via RunComfy with selected audio models.
npx skills add https://github.com/runcomfy-com/skills --skill ai-music
Please help me install this Agent Skill. Skill: ai-music Source: https://github.com/runcomfy-com/skills/tree/main/ai-music Command: npx skills add https://github.com/runcomfy-com/skills --skill ai-music
Generate and edit music quickly without choosing the right vendor model or learning multiple different request formats.
Ask the agent to create an upbeat indie-pop anthem with a female lead vocal and section markers, then save the generated audio to your output folder.
High-intent search queries and answers about installing and using this skill.
AI music generation with vocals is handled by routing your text prompt, tags, or lyrics to the appropriate model like ElevenLabs or ACE Step. The system automatically selects a premium model for vocal tracks and outputs the generated audio file directly to your specified directory.
Audio inpainting allows you to repair specific time ranges in existing tracks using the ACE Step audio-inpaint feature. By defining the time boundaries in your JSON input, the model regenerates only the targeted section while preserving the rest of the audio file.
Extending an existing audio track is achieved through audio outpainting with the ACE Step model. This feature generates new audio segments before or after your original track, allowing you to seamlessly lengthen background music or instrumental sections without manual editing.
Cost-sensitive background music generation is fully supported by automatically routing requests to appropriate instrumental models. This ensures you can generate AI music for background tracks efficiently, balancing output quality and resource costs based on your specified intent.
The RunComfy CLI is required to invoke the AI music generation and editing processes. You must execute a CLI command with a JSON input specifying your prompt, tags, or lyrics, which then leverages the allowlisted model API to produce the audio output.
ElevenLabs is integrated for text-to-music generation, specifically routed for premium vocal songs. You provide your prompt or lyrics via the RunComfy CLI JSON input, and the system handles the API invocation to produce the audio file.
doany-aiRoute user requests to RunComfy models for t2v, i2v, and extend video workflows.
doany-aiGenerate songs and instrumental tracks from text prompts via RunComfy CLI.
runcomfy-comGenerate and edit music tracks via StepFun-AI ACE Step on RunComfy.
prime-skillsGenerate, repair, and extend music via RunComfy CLI with structured JSON inputs.
