Footage Inside the Letters — effect skill for headlines & callouts

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the how-to page.

Huge block letters act as windows onto playing product footage or a demo clip.

What it does

Built on Video Text by magic-ui, MIT. The write-up and recipes below are varg's.

Full-bleed heavy type on black or white; the product video plays only through the letterforms.

When: Open a launch film with the product name, or bridge into a demo by expanding the letters.

Watch out: Do not use thin fonts; strokes under ~12% of the cap height show too little footage.

Timing: Hold 1.5–2.5 s; optionally scale the type up 4–8× over 0.6 s to fall into the footage.

Also called: video text, knockout type, text mask video

In HyperFrames

npx hyperframes add texture-mask-text

Place the <video class="clip"> inside the masked wrapper; animate the wrapper scale, not the video.

In Remotion

// npx shadcn@latest add @magicui/video-text
<div style={{WebkitMaskImage:'url(#word)', maskImage:'url(#word)'}}><OffthreadVideo src={demo}/></div>

In CapCut

Put white text on black as the lower layer and the footage above it, then set the footage Blend → "Multiply" so it only shows through the letters.

Ready-made components

Where this comes from

Use when

Not for

Install

Example output

https://s3.varg.ai/how-to/previews/abc1ae7d7177/lib-magic-ui-video-text.mp4 — Preview of the Video Text component that builds this take (credit: Captured from the library’s own demo page (Magic UI), https://magicui.design/docs/components/video-text)

More headlines & callouts skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.