music-seperator-demucs
Separate vocals and instrument stems from audio files with Demucs CLI. Use when the user asks for vocal extraction, accompaniment generation, stem splitting, batch separation, output format conversion (wav/flac/mp3), or Demucs performance/memory tuning on CPU/GPU. Also trigger when the user mentions demucs or demucas.
Why use this skill?
Use the Demucs skill in OpenClaw to easily split music into vocal and instrumental stems. Supports batch processing, custom formats, and GPU acceleration.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/chinesemisaka/music-seperator-demucsWhat This Skill Does
The music-seperator-demucs skill provides a powerful command-line interface wrapper for Demucs, a state-of-the-art deep learning model designed for music source separation. This tool allows the OpenClaw agent to intelligently dissect audio files, isolating vocals, drums, bass, and other instrumental components into distinct tracks. By leveraging advanced AI-driven stem separation, the skill enables users to create high-quality remixes, karaoke backing tracks, or analyze complex musical compositions with ease. Whether you are dealing with professional studio recordings or casual voice memos, this skill automates the heavy lifting of audio engineering through simple natural language commands.
Installation
To integrate this capability into your OpenClaw environment, execute the following command in your terminal or via the agent's command interface:
clawhub install openclaw/skills/skills/chinesemisaka/music-seperator-demucs
Ensure that you have FFmpeg installed and accessible in your system PATH, as the tool relies on it for decoding and encoding various audio formats. If you are working within a Python virtual environment, verify that the demucs.exe executable is correctly linked or accessible in your Scripts directory.
Use Cases
This skill is highly versatile for musicians, producers, and data researchers. Use it to:
- Generate karaoke versions of songs by removing vocal stems.
- Isolate specific instruments for transcription or practice.
- Convert batch collections of audio files into specific formats like FLAC or MP3 with custom bitrates.
- Optimize processing workflows by adjusting GPU/CPU allocation and segment chunking for long audio files.
- Automate audio cleanup pipelines by piping file paths through the agent for organized folder exports.
Example Prompts
- "Demucs, please split my song 'studio_session.wav' into four stems and save the output in the D:\MusicExports folder."
- "Can you extract only the vocals from 'track_01.mp3' and ensure the output is a high-quality FLAC file?"
- "I'm running out of memory during separation; can you rerun the process on 'live_recording.wav' using CPU mode and a smaller segment size of 4?"
Tips & Limitations
To maximize performance, always consider your hardware constraints. For low-RAM systems, utilize the --segment flag with a lower value and --no-split only if processing very short clips. If you experience non-ASCII path errors on Windows, move your source files to a temporary directory with simple naming conventions. Always prefer absolute file paths to avoid directory ambiguity during automated tasks. Note that higher quality settings like --shifts significantly increase processing time, so balance your need for precision against project deadlines.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-chinesemisaka-music-seperator-demucs": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution