Music-to-Video Skill for Muse
Turn your music track into a beat-synced lyric video, slideshow, or kinetic promo.
- What
- Turn your music track into a beat-synced lyric video, slideshow, or kinetic promo.
- Cost
- Free
- Needs
- Python 3 with pip (librosa, numpy, soundfile) for the local beat analysis; Node.js with npx for the HyperFrames CLI; your own audio file or a video to pull audio from (required to render anything). Optional: a media-provider account only if you want the skill to generate background music instead of using your own track.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Turn one music track into a complete beat-synced video — lyric video, slideshow, or kinetic promo. It runs an agentic workflow with user checkpoints: analyze the track with a single local beat analyzer (`analyze-beatgrid.py`), cut it into frames at real musical changes, approve a storyboard, build each frame as a web composition with one worker per frame, then assemble and render the final MP4. No assets required — typography and templates carry a complete video; any images or videos you supply get cut onto the same beat grid. Discovered via skills.sh. Honest note: the heavy lifting (beat analysis, rendering) runs locally and free — but audio track *generation* routes through media providers that may need sign-in; and the skill assumes the HyperFrames ecosystem (CLI + companion skills) around it. Skill Harbor never reviews the code, review it yourself before use. Not verified.
Curated by Skill Harbor — free, open-source skill (Apache-2.0) by @heygen-com.
Version:
Install
Prerequisites: Python 3 with pip (librosa, numpy, soundfile) for the local beat analysis; Node.js with npx for the HyperFrames CLI; your own audio file or a video to pull audio from (required to render anything). Optional: a media-provider account only if you want the skill to generate background music instead of using your own track. Install "Music-to-Video Skill for Muse" for me. Turn a music track into a complete beat-synced video — lyric video, slideshow, or kinetic promo — from local beat analysis to the rendered MP4. Repository: https://github.com/heygen-com/hyperframes/blob/main/skills/music-to-video/SKILL.md 1. Fetch the SKILL.md file plus its helper files (scripts/beat analyzer, references/ templates and guides) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code; credentials only via the secure vault. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "music-to-video". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. install the Python packages, provide my audio track). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.