A professional-grade AI music generation tool that leverages the ACE-Step V1.5 API to create full songs, vocals, and instrumentals from text prompts.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install acestep
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install acestep using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is ACE-Step Music Generation Skill?
The ACE-Step skill is a robust integration designed for the Openclaw Skills ecosystem, enabling users to generate high-quality music through simple command-line interactions. By utilizing the ACE-Step V1.5 API, this skill supports advanced audio manipulation including text-to-music, audio continuation, and audio repainting. It is built to handle everything from quick instrumental inspiration to full song production with structured lyrics and specific vocal styles.
This skill functions as a bridge between AI agents and the ACE-Step engine, ensuring that music production becomes a seamless part of a developer's workflow. Whether you are running a local service or connecting to the official cloud API, this entry in the Openclaw Skills directory provides the necessary scripts and configurations to automate complex audio tasks with precision.
ACE-Step Music Generation Skill Use Cases
- Generating full-length songs with vocals from text descriptions and structured lyrics.
- Creating custom background tracks for multimedia projects with specific BPM and key requirements.
- Automating the production of music videos by integrating with complementary Openclaw Skills.
- Rapidly prototyping different musical genres and styles for creative exploration.
- Remixed existing audio or extending tracks through AI-driven audio continuation.
How ACE-Step Music Generation Skill Works
- The user provides a prompt containing musical style, mood, or specific lyrics through the acestep.sh script.
- The skill validates the environment, ensuring dependencies like curl and jq are present and the API service is healthy.
- For vocal-heavy requests, the skill follows a songwriting workflow to structure lyrics and select optimal BPM and duration.
- The script sends the request to the ACE-Step API using either sync completion or async polling mode.
- Upon completion, the skill automatically downloads and organizes the resulting MP3 files and metadata JSON into the project root.
ACE-Step Music Generation Skill Setup
To get started with this skill within the Openclaw Skills framework, follow these steps:
# Navigate to the skill directory
cd .claude/skills/acestep/
# Check API health and dependencies
./scripts/acestep.sh health
# (Optional) Set your official ACE-Step API key
./scripts/acestep.sh config --set api_key YOUR_API_KEY
# Generate a test track
./scripts/acestep.sh generate -c "lo-fi hip hop, chill" --duration 60
Ensure that you have curl and jq installed on your system for the script to function correctly.
ACE-Step Music Generation Skill Data Schema & Taxonomy
The skill organizes all generated assets within an acestep_output directory at the project root for easy access. The data is organized as follows:
| File | Description |
|---|---|
<job_id>.json |
Contains all generation metadata, including actual synthesized lyrics, BPM, and model info. |
<job_id>_1.mp3 |
The primary high-quality audio output file. |
scripts/config.json |
Stores local configuration for API URLs, modes, and default generation parameters. |
When using this within Openclaw Skills, the JSON metadata allows for reproducible results by saving the exact seed and prompt used by the AI.
ACE-Step Music Generation Skill Advanced Features
- Support for 5Hz LM Thinking mode for higher quality musical compositions.
- Multi-modal API support including OpenRouter-compatible completion and native async polling.
- Deep integration with transcription and MV rendering skills for end-to-end media production.
- Batch generation support to produce multiple variations of a single musical prompt.
- Flexible configuration hierarchy allowing for temporary command-line overrides or permanent settings.
SKILL.md
Loading
Related Openclaw Skills
ACE-Step Songwriting Guide
A professional music creation guide for writing lyrics, captions, and technical parameters for the ACE-Step engine.
Seoul Subway Assistant
A comprehensive bilingual tool for querying real-time Seoul Subway arrivals, route optimizations, and station facility data without requiring an API key.
Company Investment Research Framework
A multi-dimensional analytical framework that enables AI agents to transform raw corporate data into structured, high-quality investment research reports.
Qwen-Image-Plus (Sophnet) Image Generation
A specialized tool for generating high-fidelity images via the Sophnet Qwen-Image-Plus API with automatic status polling.
med-info
A specialized tool for fetching authoritative, label-backed medication answers with traceable identifiers and regulatory safety context.
Duola Lobster Agent
An institutional-grade execution playbook for the Duola Polymarket copy-trading CLI within agent workflows.
METADATA
Featured*
