Warm off-white cards, quiet sentence-case captions in a white pill and nothing shouting: the calm explainer look. A vertical 9:16 creator kits motion graphics scene. Copy it into Claude or Claude Code, change the words and colours, and render the MP4 free.
Transcribe the clip with word-level timings and keep the words as data (every caption, keyword and cue below is timed from them).
Write the cut as data before any styling, in edit.json:
source and duration.
emphasis: the 15-20 words that carry the meaning (numbers, nouns, strong verbs). Keywords and highlights only ever come from this list.
shots: one entry per camera angle in the clip, {t, face: [x, y], pip}, where your face centre sits in source pixels, so every crop and picture-in-picture keeps your head…
beats: [{t, layout, zoom?, visual?, chapter?}], one per change on screen. Something changes every 2-5 s and never more than 6 s goes by without a change.
Keep the look in two separate files, kit.json (colours, fonts, caption size and height per layout, picture-in-picture and end-card rectangles) and kit.css. Restyling later means swapping those two files, never…
Render, then watch it through once at full size: nothing may cover your face, and every caption must land on its spoken word.
hook: frame 0 already shows your face plus a 3-8 word line, the thumbnail line rather than your first sentence. A second line, the twist, lands at about 0.7 s…
face: you, a medium shot. The default for setups.
The look
Surfaces: a warm off-white [#E8E4DA] for every graphic stage, slam card and end card. Under full-face shots a soft near-black fade (#0E0D0B) rises from the bottom third.
Type: [Inter] throughout. Big numbers 140 px weight 900 tracked -0.05em in #111; secondary lines 48 px weight 400 in warm grey #6B675F.
Hook: line 1 in white with a soft shadow over your footage; line 2 as black 92 px type on a white rounded box.
Cards: white, 30 px corners, very soft shadows (0 30px 70px at 12%), hairline dividers #EEE. Lists are numbered in light grey with a thin rule under each row. The…
Picture-in-picture: a rounded rectangle (36 px corners), top right. No rings, no outlines.
How the prompt opens
Calm and clean: warm off-white surfaces, black type, soft shadows and quiet captions that let the voice carry it. Turn [your talking-head clip] (you speaking to camera, 20-90 s, any shape) into a finished vertical short: 1080x1920, 30 fps, built in HyperFrames and rendered with npx hyperframes render. Your footage and your voice stay exactly as recorded. The design lives around you, and it changes with what you say.
The full prompt runs 744 words. Copy it from this page.
Copy the prompt into Claude, or pull the scene into Claude Code and render the MP4 on your machine: how it works.