Text, captions and code on screen

Ask for “embedded captions, keywords highlighted in the accent color” and you get a sensible default. This page is the catalog behind that ask: the named components you can pin instead, by tone, so the highlight color and the animation are a decision, not a default.

​

What caption styles do and when they trigger

Caption components are drop-in snippets that render animated on-screen text — one visual identity per component, animating per word or per line. Prompts trigger this layer when you ask for captions, subtitles, kinetic text, lyric-style words, or word-by-word titles inside a composition you’re building. Describe the energy of the captions and the agent picks matching typography, size, and animation; name a component to lock the look.

​

Tone → caption component

​

Text-effect components

Three Text Effects components do one focused job rather than caption a whole track:

​

Example prompts

30-second vertical explainer. Add caption-highlight captions, TikTok-style — the visible line stays up, one word highlighted at a time.

Rendered from the prompt above, unedited.

Hype captions with caption-kinetic-slam: one full-screen word per beat, alternating slam-in direction.

Rendered from the prompt above with an authored 24-word line, unedited.

Neon music-video captions using caption-neon-glow. Make brand names larger with an accent color and highlight the numbers differently.

Rendered from the prompt above, unedited — the brand renders 1.4x in magenta, numbers in amber, distinct from the default cyan.

Fill the hero word “STONE” with texture-mask-text using the rock texture.

​

Knobs

• Tone picks typography, size, and animation — Hype (heavy, 72–96px, scale-pop) through Storytelling (serif, 44–56px, slow fade). See the caption-tone table in vocabulary.
• Per-word emphasis. “Make brand names larger with accent color,” “highlight numbers differently,” “add bounce to emotional keywords” all work — several components key off this: caption-editorial-emphasis drives a dramatic size contrast on emphasis words, caption-particle-burst fires on keywords, and the neon components carry keyword accent colors.
• Texture variable. caption-texture ships lava, marble, metal, wood, concrete, and rock — name the one you want.
• Word list. morph-text cycles an editable list; quote the words in order.
• Format. Full-screen single-word styles (caption-kinetic-slam) and TikTok-style highlights (caption-highlight) are built for vertical / social framing — say “vertical” or “9:16” so sizing and safe areas match.

​

Failure modes

Don’t stack a heavy effect on every word. Caption components already animate per word; layering another emphasis on top of that competes and turns illegible. Emphasize only the keywords.

• Avoid: make every word explode with particles
• Instead: caption-particle-burst, firing only on the keywords

Don’t mix caption styles in one section. One identity per composition (or per section) reads as designed; two competing styles read as a mistake.

• Avoid: use caption-neon-glow and caption-matrix-decode together
• Instead: pick one; switch styles only across a clear section break

Don’t reach for these on talking-head footage. These are composition snippets, not the matting/occlusion pipeline — dropped onto an untouched MP4, a caption sits in front of the speaker, never behind. (The capstone thread below shows caption-kinetic-slam reading behind a subject, which is not a contradiction: that composition mattes the footage itself first, so the cutout is a separate layer the type can pass under. The limitation is about the snippet alone, not the technique.)

• Avoid: add caption-highlight to my interview.mp4
• Instead: caption interview.mp4 with the words set behind the speaker (see captions and talking heads)

Don’t match a hype style to calm content. A high-energy caption on a corporate explainer fights the tone; let the tone table pick the identity.

• Avoid: glitchy RGB captions (on a wellness brand piece)
• Instead: clean captions with caption-clip-wipe

Don’t invent caption names. Only the components in the Captions and Text Effects groups exist.

• Avoid: add typewriter-bounce captions
• Instead: describe the tone (“tutorial, monospace, typewriter”) or name a real component

In a real film. This clause from a longer HyperFrames film produced the shot below. You can lift the wording for your own video:

THEN they speak, and the main keywords of their own line — derived from the clip’s transcription — land word-synced as huge display text BEHIND the cutout, each keyword slamming in on its spoken moment with the subject’s silhouette occluding it (the two-layer text-behind-subject plate); style the keyword type by adapting a bold catalog caption component (caption-kinetic-slam or similar) at display scale.

That clause, rendered: the shot cut from the finished film.

​

Code on screen

A PR video can name code-diff for a single beat. The rest of that catalog covers typing, diffing, highlighting, scrolling, and picking a terminal or editor theme by name, for the moments a walkthrough needs to slow down and let the code itself carry the scene. Code is the one subject where the framework does the hard part for you. The Code Animations blocks handle syntax highlighting, caret tracking, diff coloring, and camera moves deterministically — you describe the walkthrough, name the block, and paste your snippet. This page is the vocabulary for doing that well; for turning a real pull request into a code-change video, see Code and PRs. Everything here follows the one-shot skeleton: route, spec, beats, copy, technique, negatives. The “technique” slot is where you name the block, and the “copy” slot is where your code goes — quoted exactly, because unquoted code gets paraphrased into something that won’t compile.

​

Pick the motion by what the viewer should learn

Each Code Animations block answers a different “what is the viewer supposed to notice.” Map the intent to the block: The first four are the workhorses of a code walkthrough — they keep the code readable and the viewer oriented. Everything below them trades legibility for motion: they look great as an opener or a hero moment, but they trade legibility for motion, so don’t ask them to carry an explanation.

​

Prompting a typing reveal

code-typing reveals code character by character with a caret that tracks the frontier — no CSS animation, so it seeks cleanly. Give it the exact code and a pace; the agent re-bakes the block’s syntax tokens to your snippet.

6-second 1920x1080 video. A dark editor types this snippet, character by character, caret tracking the frontier, then holds on the blinking cursor for the final second:

export async function render(comp: Composition) {
  await comp.seek(0);
  return comp.capture();
}

Use the code-typing registry block. No narration, no image or media files.

Rendered from the prompt above, unedited. Quote the code as a literal block. Prose descriptions of code get paraphrased.

• Avoid: type out a function that seeks to zero and captures
• Instead: paste the actual snippet in a fenced block — it renders verbatim

Give the caret somewhere to rest. Compositions hold their final state, so if you don’t ask for a hold the last frame is a frozen full snippet — the dead-motion tell.

• Avoid: types the code and ends
• Instead: types the code, then holds on the blinking cursor for the final second

​

Prompting a diff or a highlight

For “here’s what changed,” hand code-diff the before and after and let it color the delta. For “look at this line,” give code-highlight the full context and name the target line.

6-second 1920x1080 video. Show this edit to api.ts as a colored diff — the removed line collapses in red, the added line expands in green: removed: const res = await fetch(url) added: const res = await fetch(url, { signal }) Use the code-diff registry block. No audio.

Rendered from the prompt above, unedited.

5-second 1920x1080 video. Show a 12-line config file; a highlight band sweeps to line 7 (timeout: 30_000) while the surrounding lines dim. Hold with line 7 lit and the cursor blinking. Use the code-highlight registry block. No audio.

Rendered from the prompt above, unedited — the agent authors plausible surrounding config lines; paste all 12 if the exact file matters. Name the target line unambiguously. The block dims context around one line — tell it which.

• Avoid: highlight the important line
• Instead: highlight line 7 (timeout: 30_000)

​

Prompting a scroll-through

code-scroll moves the camera down a long file to bring a target line to center and spotlights it — the block for walking real modules, not toy snippets.

6-second 1920x1080 video. Scroll a ~60-line source file so line 44 (return dedupeFrames(frames)) arrives at center and gets spotlighted; ease the scroll and let it settle without snapping. Use the code-scroll registry block. No audio.

Rendered from the prompt above, unedited. Ask the scroll to ease and settle, not snap. A linear scroll that stops dead reads mechanical.

• Avoid: scroll straight to the line
• Instead: ease the scroll and let it settle — pair with the motion grammar

​

Choosing a theme by name

VS Code workbench themes — full editor chrome (activity bar, sidebar, tabs, terminal, status bar). Say “monokai” or “visual studio dark”: Rendered from the prompt above, unedited. Match the theme to the surface you’re claiming to show. A terminal command in a VS Code editor chrome reads wrong; a source file in Terminal.app reads wrong.

• Avoid: monokai theme typing a shell command
• Instead: apple terminal homebrew profile typing a shell command

​

Pairing with a pull request

When the code you’re animating comes from a real PR, don’t hand-write the beats — point the agent at the PR and it reads the diff and composes code-diff, code-highlight, and code-scroll around the actual changed hunks. Use the blocks on this page directly when you’re illustrating a concept; hand over the PR when you’re narrating a specific change set.

​

Where to go next

• Anatomy of a one-shot prompt — the skeleton every prompt above uses.
• Copy-paste examples — full prompts you can adapt.
• Code and PRs — turning a GitHub PR into a code-change video.
• Ask for smooth motion and transitions — the hold-and-settle rules the code blocks still need from you.

In a real film. This clause from a longer HyperFrames film produced the shot below. You can lift the wording for your own video:

Type (0–7s). Black-on-charcoal close-up: a cursor types real HyperFrames markup character by character — <div class="clip" data-start="0" data-duration="4"> and a gsap.timeline({ paused: true }) line. As the typed line completes, the text’s baseline extends and becomes the wire — the underline literally grows into the timeline and the camera begins its dolly along it. The typed div folds into a compact clip chip (persistent element 3) that drops onto the wire. Kinetic display type states “WRITE HTML.” as the travel begins.

That clause, rendered: the shot cut from the finished film.

​

Overlays and lower thirds

On talking-head footage, lower-thirds and card overlays are designed as bespoke cards synced to that transcript. This is the reverse case: ready-made lower-third and social-overlay blocks you drop into a composition you’re building from scratch, no existing footage required. Same vocabulary, pointed at a scene instead of a shot.

​

What overlays do and when they trigger

Overlays are timed blocks that sit on top of your footage or scene — a lower third that names a speaker, a broadcast ticker, or a replica social-media card. Because each is a timed clip, prompts trigger this layer when you ask to add something at a moment: “add a lower third at 0:03 with the name and title,” “show an animated tweet during the intro,” “put a Spotify now-playing card in the corner.” Give the timestamp, the copy, and the tone; the agent places the block on a track above the footage. Two groups:

• Lower thirds — name/title identifiers for speakers, interviews, podcasts, and news.
• Social overlays — animated replicas of platform UI (posts, cards, notifications, follow prompts).

​

Brand tone → lower third

Lower thirds split into cards (a filled shape behind the text) and cardless (text with a rule or sweep, designed to overlay live footage without boxing it in).

​

Use → social overlay

Each social overlay is a self-contained animated card with editable placeholder content.

​

Example prompts

Quote the exact copy — unquoted names and titles get paraphrased (see anatomy).

Add a lower third at 0:03 for 5 seconds, on a track above the footage, with lt-clean-bar. Name: “Dana Ríos”. Title: “Head of Design”.

Rendered from the prompt above over stand-in footage, unedited.

Podcast clip. Bring in lt-bold-block when the guest starts talking, holding 5 seconds — name “MARCUS LEE”, tag “GUEST” — brand accent #FF5A1F.

During the intro, show an x-post card with the quote “we shipped it in a weekend” and 12.4K likes, then slide it out before the demo.

Rendered from the prompt above over stand-in scenes, unedited — the card’s built-in like-tap ticks 12.4K → 12.5K.

Transparent overlay only — a spotify-card now-playing widget animating in, bottom-left. Export as transparent WebM so I can drop it over footage in my editor.

MP4 preview of the transparent WebM over a checkerboard — the delivered file carries real VP9 alpha (verified via ALPHA_MODE + alphaextract).

​

Knobs

• Timing. “at 0:03,” “for 4 seconds,” “slide it out before the demo” set the block’s start and duration — an overlay is a timed clip, so it needs both.
• Copy. Quote every editable field: name, title, handle, headline, metrics, ticker text. The blocks ship with placeholder content you replace.
• Track placement. Overlays go on a track above the footage so they composite on top; say “over the footage” if you’re layering onto an existing clip.
• Brand accent. Give a hex or brand color — most lower thirds carry an accent bar, tab, or block that takes it.
• Card vs cardless. State it when it matters, or let the tone table decide.
• Transparent output. For use in an external NLE, render the overlay on its own as a transparent WebM — see rendering and output.

​

Common mistakes

Don’t leave the copy unquoted. Unquoted names and titles get paraphrased; quoted text renders verbatim.

• Avoid: add a lower third with the speaker's name and role
• Instead: lt-clean-bar — name: "Dana Ríos", title: "Head of Design"

Don’t omit the timestamp. An overlay is a timed clip; without a start (and ideally a duration) the agent has to guess when it appears and how long it holds.

• Avoid: put a lower third somewhere in the intro
• Instead: lower third at 0:03, holding 4 seconds

Don’t let the overlay render behind the footage. It has to sit on a track above the clip, or the video covers it.

• Avoid: add the tweet card to the video (ambiguous layering)
• Instead: x-post card on a track above the footage, top-right

Don’t over-spec real account data. These are stylized replicas with editable placeholders — provide the copy you want shown, not a live URL to scrape.

• Avoid: pull my actual Spotify page
• Instead: spotify-card: track "Midnight City", artist "M83"

Don’t invent overlay names. Only the blocks in the Social Overlays and Lower Thirds groups exist.

• Avoid: add a linkedin-post overlay
• Instead: pick a real block, or describe the card and let the agent build a custom one in a freeform composition

In a real film. This clause from a longer HyperFrames film produced the shot below. You can lift the wording for your own video:

[…] as the camera arrives and BEFORE the person speaks, the framework mattes the footage — the background peels away via background removal, sliding off along the travel direction and leaving the cutout standing alone on the brand ground. […] A designed lower-third chip renders behind the subject.

That clause, rendered: the shot cut from the finished film.