Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
acestep 1.0.2 - Updated instructions for obtaining a free ACE-Step API key: now directs users to [acemusic.ai/api-key](https://acemusic.ai/api-key). - Clarified wording on the API key requirement and configuration process when using the official cloud API. - No functional or file changes; documentation updated for accuracy and improved guidance.
What This Skill Does
ACE-Step is a music generation skill that turns text prompts and lyrics into audio files. It supports text-to-music, instrumental generation, and vocal tracks across styles and languages. Output is saved as MP3, WAV, or FLAC files with full metadata.
Unlike general-purpose AI tools, ACE-Step combines lyric-aware synthesis with LM enhancement, letting you control BPM, key, language, and structure in a single scripted workflow.
When to use it
- Generating a background track for a video from a genre description
- Writing and producing a complete pop song with custom lyrics
- Creating an instrumental loop for a game or app
- Remixing an existing song idea by reprompting with new parameters
- Quickly exploring musical ideas with random generation mode
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Create a 90-second electronic pop song with these lyrics in English
- 1Check API health with `acestep.sh health`
- 2Run acestep-songwriting skill to finalize caption, BPM, key, and duration
- 3Call `acestep.sh generate -c "Electronic pop, energetic synths" -l "[Verse] ...full lyrics..." --duration 90 --bpm 128`
- 4Poll job status or wait for completion response
- 5Read output JSON for actual synthesized prompt and lyrics, locate MP3 in `acestep_output/`
A 90-second MP3 file saved to `acestep_output/<job_id>_1.mp3` with a matching JSON metadata file
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.