music-to-video

Generates beat-synced HyperFrames videos from a music track using audio analysis and per-frame compositions.

Updated Jul 16, 2026
One-click install
npx skills add https://github.com/X-manist/Cohmira --skill music-to-video-x-manist
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: music-to-video
Source: https://github.com/X-manist/Cohmira/tree/main/src/builtin-plugins/openmontage/.agents/skills/music-to-video
Command: npx skills add https://github.com/X-manist/Cohmira --skill music-to-video-x-manist

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires librosa, numpy, soundfile, and includes scripts (resource) and references (resource) components.

What problem does it solve? Turning a music track into a beat-synced video normally requires manual timeline editing, beat detection, and frame-by-frame motion design. This Skill automates that pipeline: it analyzes the audio once, plans frames against the beat grid, builds each frame as an HTML composition, and renders a final MP4. ## Core Features & Use Cases - Deterministic audio analysis: A single analyzer script produces an audiomap.json with BPM, beat grid, drum events, rolls, energy phases, and key moments that drive all visual timing. - Orchestrated multi-step workflow: Six gated steps cover setup, analysis, frame skeleton, user-approved planning, parallel per-frame sub-agent builds, assembly, and verified rendering. - Template and motion-primitive catalogs: Frames are filled from a catalog of beat-synced typography templates or free-composed motion primitives, with optional user images/videos cut in via beat-cut or ken-burns treatments. - Use Case: Give the Skill a synthwave track and ask for a 30-second promo video; it analyzes the beat grid, plans frames around drops and rolls, builds kinetic typography compositions, and renders a beat-synced MP4. ## Quick Start Use the music-to-video skill to turn my track bgm.mp3 into a beat-synced 1920x1080 video and render it to an MP4.

Frequently Asked Questions about music-to-video

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

FAQPage Schema
How do I make a beat-synced video from a music file?

Provide an audio file (or a video to extract audio from) and the skill runs analyze-beatgrid.py to produce an audiomap.json with beats, onsets, rolls, and energy phases. It then plans frames against that grid, builds each frame as an HTML composition, and renders the final MP4 with the hyperframes CLI.

What tools are needed to run the music-to-video workflow?

You need Python 3 with librosa, numpy, and soundfile for the audio analyzer, Node.js for the validation and assembly scripts, ffmpeg on PATH for audio decoding, and the hyperframes CLI (via npx) for project init, lint, validate, inspect, and render.

Can I include my own images or video clips in the generated video?

Yes. User-supplied media is staged into the project's assets directory with stage-assets.mjs and woven into frames on the same beat grid using beat-cut, ken-burns, or background-under-text treatments. Assets are optional since typography templates alone can produce a complete video.

Does beat syncing work with calm or non-rhythmic music?

Yes, but pacing changes. On calm music the detected beat grid is treated as an unreliable metronome, so frames use phrase_flow pacing driven by phrases and energy envelopes instead of hard beat cuts. The pacing decision is made per frame from rolls, density, and onset rate.

Why does the workflow pause for user approval during generation?

Two gates require user input: Step 3 approves the storyboard plan (frames, templates, copy, brand) before any building starts, and Step 6 approves the verified assembled video before rendering the final MP4. This prevents wasted rendering on unapproved plans.