music-to-video

Convert a music track into a beat-synced video with lyric, slideshow, or kinetic typography treatments.

13|17|Updated Jan 30, 2025
One-click install
npx skills add https://github.com/CodeWithSally/CodeWithSally-Apex-English --skill music-to-video-codewithsally
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: music-to-video
Source: https://github.com/CodeWithSally/CodeWithSally-Apex-English/tree/main/Sessions/ClaudeCode/Session007/.agents/skills/music-to-video
Command: npx skills add https://github.com/CodeWithSally/CodeWithSally-Apex-English --skill music-to-video-codewithsally

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Creating a video that stays synchronized to a music track normally requires manual beat-marking and frame-by-frame editing. This Skill analyzes a track once, derives a deterministic beat grid and energy map, and orchestrates the planning, building, assembly, and rendering of a complete beat-synced video. ## Core Features & Use Cases - Deterministic audio analysis: A single analyzer script produces an audiomap.json with tempo, beat grid, onsets, drum classification, rolls, energy phases, and key moments that drive all visual timing. - Template and motion-primitive system: Per-frame groups are built from a catalog of beat-synced templates or free-composed motion primitives, with optional user images/videos cut onto the same beat grid. - End-to-end pipeline: A gated six-step workflow covers setup, analysis, storyboard planning, parallel per-frame composition building, index assembly, verification, and MP4 rendering. - Use Case: Provide a music file and a few product photos, and receive a rendered MP4 promo where every cut, reveal, and transition lands exactly on the track's beats and drops. ## Quick Start Turn the attached song into a 30-second beat-synced promo video using these photos, rendered in 1920x1080.

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 track?

Provide a music file or a video to extract audio from, and the workflow analyzes the track into a beat grid, plans frames against that grid, builds each frame as a composition, and renders a final MP4. User-supplied images or videos are cut onto the same beat anchors.

What audio analysis libraries are used for beat detection?

The analyzer uses librosa for beat tracking and onset detection, numpy for numerical processing, and soundfile for audio decoding, with ffmpeg handling format conversion. It produces a deterministic audiomap.json with tempo, onsets, drum classification, rolls, and energy phases.

Can I use my own images and videos in the generated video?

Yes, supplied media is staged into the project and cut onto the same beat grid using beat_cut, ken_burns, or bg_under_text treatments. Assets are optional since typography templates alone can carry a complete video.

Does beat-synced cutting work with calm or ambient music?

On calm music the detected beat grid is treated as unreliable, 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 onset density and roll detection, not from BPM alone.

What video formats and resolutions does the output support?

The output is an MP4 rendered at 30 fps, with landscape 1920x1080 as the default canvas. Portrait 1080x1920 and square 1080x1080 formats are also supported by setting the canvas in the storyboard frontmatter.