Heavy all-caps pop captions, a warm dark stage and gold accents: the loud short-form look done properly. 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
Stage behind every graphic: a warm dark radial gradient (#2A2108 at the centre to #0D0D10 to #070709 at the edges). Under full-face shots a black fade rises from the bottom…
One accent, [gold #F2B53A]: highlighted words, the progress bar, list number discs, the picture-in-picture ring and the slam card background (black type on gold).
Fonts: [Montserrat] 900 for display and captions, [Inter] for body.
Hook: line 1 as black uppercase on a white rounded box (74 px); line 2 at 118 px in the accent with a heavy black stroke and a hard drop…
Cards (invoice, speech bubble, comparison columns) are white, 26 px corners, a big soft shadow, slightly tilted; big numbers at 150-170 px count up into place; a green rubber stamp…
How the prompt opens
The loud short-form look, done with discipline: huge captions, one accent colour and a layout that never sits still. 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 766 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.