music-to-video

Generates beat-synced videos from music tracks using audio analysis and HTML compositions.

Updated Sep 6, 2026
One-click install
npx skills add https://github.com/AbuBakar125-co/Resturant_web --skill music-to-video-abubakar125-co
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: music-to-video
Source: https://github.com/AbuBakar125-co/Resturant_web/tree/main/agent/skills/music-to-video
Command: npx skills add https://github.com/AbuBakar125-co/Resturant_web --skill music-to-video-abubakar125-co

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 with a music track requires manual beat detection, timeline editing, and frame-by-frame alignment. This Skill automates the entire pipeline: it analyzes a music track once, cuts it into frames at real musical changes, plans per-frame visual treatments, and renders a finished MP4 where every cut lands on the beat grid. ## Core Features & Use Cases - Deterministic audio analysis: A Python script (librosa-based) produces a canonical audiomap.json with tempo, beat grid, drum classification, energy phases, rolls, silences, and key moments — the single timing source for the whole video. - Structured multi-step workflow: Six gated steps (setup, analyze, skeleton, plan, build, assemble, render) with validation scripts, a storyboard format, and per-frame sub-agent dispatch for parallel composition building. - Template and motion-primitive catalogs: Typography-first templates and motion primitives cover lyric videos, slideshows, and kinetic promos; user-supplied images/videos are cut onto the same beat grid, and a complete video needs zero assets. - Use Case: Give the Skill a music file and ask for a 30-second kinetic promo; it analyzes the track, plans frames at drops and surges, builds HTML compositions, and renders a beat-synced MP4. ## Quick Start Turn my music track into a beat-synced lyric video and render the final 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 track?

Provide a music file (or a video to extract audio from) and the Skill runs a six-step pipeline: analyze the track into an audiomap.json, cut it into frames at musical changes, plan per-frame treatments, build HTML compositions, assemble the index, and render the final MP4.

What audio analysis libraries does the beat detection use?

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 outputs tempo, beat grid, drum classification, energy phases, rolls, and key moments as deterministic JSON.

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

Yes, user-supplied images and videos are staged into the project and cut onto the same beat grid as asset treatments. Treatments include beat_cut for rhythmic sections, ken_burns for calm passages, and bg_under_text for dimmed backgrounds behind typography.

Does the beat grid work on calm or ambient music?

The beat grid is reliable only on genuinely rhythmic music; on calm tracks the detected BPM is a metronome the tracker imposed. The workflow detects this case and paces visuals by phrases and energy envelopes instead of hard beat cuts.

What Python dependencies are required to run the audio analyzer?

The analyzer requires Python 3 with librosa, numpy, and soundfile installed, plus ffmpeg and ffprobe on the system PATH for audio decoding. Install the Python packages with pip before running the analysis script.