Back to templates
Kinetic typography spoken-word HTML film "BUILD THE FLOOR" made with Opus 5.5
Prompt from @gdgtify on X · ♥ 10
OtherClaude OpusKinetic type
Watch the video 
Why it works
- Each word takes an architectural role (lintel, suspended load, support, opening, platform), so the structure of the frame carries the speech's meaning.
- Phrases are revealed in spoken reading order, so the audience can read each line before it becomes architecture.
- A planned 400ms stillness at the moment of levelling makes the alignment feel earned.
- The closing platform is built from the earlier structural words, so the final declaration rests on what was constructed before it.
- Restrained palette and type roles (serif for speech, heavy grotesque for load-bearing words, monospace for timing marks) keep the monument-like tone consistent.
Reference prompt
Remix template
Create a 20.00-second kinetic spoken-word film titled “[PRODUCT].” Treat this as an original miniature speech staged entirely through typography. Every line changes the architecture of the frame. The final declaration must stand on something the earlier words physically constructed.
Deliver one self-contained HTML file, 1080×1080, targeting 60fps, using SVG and/or Canvas. Embed all required assets.
ART DIRECTION: Background #102820. Paper #F4E9D5. Structural accent #F2B544. A literary editorial world with the scale and confidence of a public monument. Use a high-contrast serif for the speech, a heavy grotesque for load-bearing words, and a restrained monospace for small timing marks. No distressed protest-poster clichés, megaphones, flags, crowds, microphones, or stock footage.
ORIGINAL SPEECH: Write five short lines in exact order, built only from [FEATURES]. Do not attribute the words to any real person. No extra slogans. The complete speech must be understandable without audio.
CENTRAL VISUAL RULE: Assign each key word an architectural role: a lintel, a suspended load, a support, an opening, and a platform. These roles must emerge from the actual letterforms, not from separate illustrations placed behind text.
STORYBOARD:
0.00–3.00: The first line sits in a narrow opening beneath a massive lintel word. The opening slowly compresses while the line stays readable. Pressure comes from layout, not camera shake.
3.00–6.50: Reveal the second line in phrase groups. The suspended-load word lowers on two fine vertical rules that become cables. A baseline bends under the load using controlled vector deformation.
6.50–10.00: A support word enters vertically and rotates into place, lifting one end of the baseline. A counter in a letter becomes an aperture that reveals the next composition.
10.00–12.50: A second support arrives and the tilted structure levels. Use a brief stillness at the moment of perfect horizontal alignment.
12.50–16.00: Earlier structural words assemble into a platform. The final line settles onto it. Emphasis comes through shared alignment and scale, never a separate flashy effect.
16.00–18.00: Hold the complete declaration. A slight release of tension travels through the supporting rules. No new text, no restless motion.
18.00–20.00: The camera tracks beneath the completed platform. Its underside fills the frame and becomes the opening lintel. Under full occlusion, return hidden elements to their initial positions and reveal the exact opening composition.
CHOREOGRAPHY: Do not force the speech onto a dance beat. Build a cue sheet from phrases, pauses, and emphasis. Phrase reveals follow reading order. Include at least one 400ms moment of absolute stillness. Use critically damped motion for settling loads. Use controlled elastic deformation for the baseline only.
TYPE IMPLEMENTATION: Use actual glyph paths for structural words. Preserve counters and legibility during deformation. For transitions between unrelated words, use occlusion or matched structural edges; do not interpolate arbitrary path points. Keep the currently spoken phrase readable before it becomes architecture.
ENGINEERING: Implement window.seek(t) as a deterministic scene renderer. No accumulated physics, autonomous CSS transitions, or changing random values. Use time-remapping curves and analytic transforms. Use a 20-second periodic timeline with render(0)=render(20). Provide fixed-step access at n/60 for 1200 export frames. Audio is optional and off by default; no browser speech synthesis or autoplay dependency.
QUALITY GATE: Inspect eight representative frames. Check that the speech reads in the correct order, that no structure destroys a line before it can be read, and that the final platform is visibly assembled from earlier elements. Return the complete HTML implementation.Customize this prompt for my productOnly your product name is required. Nothing is uploaded.