ace-step

Generate and edit music tracks via StepFun-AI ACE Step on RunComfy.

12|2|Updated May 18, 2026

Search Tags:#music generation #audio inpaint #audio outpaint #runcomfy cli #multilingual vocals #tag-driven composition #open-weights model

Ready to run

npx skills add https://github.com/runcomfy-com/skills --skill ace-step

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ace-step
Source: https://github.com/runcomfy-com/skills/tree/main/ace-step
Command: npx skills add https://github.com/runcomfy-com/skills --skill ace-step

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you create and edit music without manual production work by generating audio from text tags and by repairing or extending existing tracks.

Core Features & Use Cases

Tag-driven music generation: produce stereo audio using the StepFun-AI ACE Step open-weights model via the runcomfy CLI.
Multilingual vocal and structured lyrics: use ACE Step 1.5 for 50+ languages and section markers like [Verse], [Chorus], [Bridge], [Outro].
Audio inpainting and outpainting: regenerate a specific time range (inpaint) or extend a track before/after (outpaint) while keeping style consistent through tags.

Quick Start

Ask your agent to generate a short instrumental track by tags using the ace-step text-to-audio endpoint.

Frequently Asked Questions about ace-step

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate music from text tags?▼

Generate multilingual vocals and structured lyrics by using ACE Step 1.5, which supports over 50 languages and section markers like [Verse], [Chorus], and [Bridge] via runcomfy CLI.

What is audio inpainting and outpainting for music tracks?▼

Audio inpainting regenerates a specific time range of an existing track, while outpainting extends a track before or after its current length, keeping the style consistent through tags.

Do I need runcomfy CLI to use the ACE Step music generation?▼

Yes, you need runcomfy CLI access with allowed Bash(runcomfy *) tooling and exact JSON inputs to send requests to the selected StepFun-AI ACE Step endpoint for audio generation and editing.

Can I add structured lyrics with verse and chorus markers?▼

Yes, you can use ACE Step 1.5 to generate multilingual vocals with structured lyrics by adding section markers like [Verse], [Chorus], [Bridge], and [Outro] in your inputs.

What are the limitations of tag-driven music generation?▼

Tag-driven music generation requires exact JSON inputs for the selected ACE endpoint and depends on runcomfy CLI access with allowed Bash(runcomfy *) tooling to process text-to-audio workflows.