Voice Design prompt-to-character showcase
A feature launch that turns short voice prompts into five contrasting character performances inside a polished card system.
Field notes / why it works
The feature name appears by 0:03, then the first character voice makes the result audible before the UI explanation. From 0:09 to 0:29, repeated prompt-to-portrait reveals contrast several voice archetypes, while roughly 19 picture changes per minute keep long measured shots active. A gallery at 0:33 widens the range before a final character re-hook around 0:38 and the CTA at 0:42.
Plate 01 / The format in one breath
A polished feature announcement shows that a short written description can become a distinctive voice. It alternates a simple prompt-entry card with a character portrait performing the result, then broadens from playful examples to practical uses and an invitation to try the tool.
Why it works
- The 0:00–0:03 gradient letter and title make the feature legible before the first example.
- At 0:09–0:29, prompt cards and voiced portraits create repeated cause-and-effect proof across a sea captain, wizard, ogre, and mouse.
- A gallery at 0:33 expands the perceived range, while a final fortune teller at 0:38–0:42 refreshes attention before the spoken call to action.
Plate 02 / Format card
| Platform · aspect · length | X · 16:9 · 1280×720 · 30 fps · 49.6 s |
| Pace | 5 measured shots, 4 cuts; 4.8–12.1 cuts/min allowing uncertain changes; 19.4 picture changes/min including 12 internal steps; 9.91 s mean shot |
| Script | 110 spoken words · 143 wpm overall, 152 wpm while talking · short setup and character auditions followed by one use-case sentence and CTA |
| Voice | Clear, medium-register presenter plus contrasting character archetypes; measured pitch combines speakers and is not a single-voice target |
| On screen | Entirely designed composition: gradient fields, product-style cards, character portraits, one gallery, brief icon frame; no talking head |
| Captions | Small black sentence-case audition subtitles in rounded white bars attached to portrait cards; UI input text is separate |
| Sound | Continuous tonal, music-like bed measured between words; spoken presenter and character auditions; exact bed genre and SFX unverified |
| Structure | Brand/title → capability → repeated prompt/result proofs → use cases/gallery → final proof → CTA; payoff begins with first voiced portrait around 0:03 |
Pro / 13 plates + recipe
The first plates are open. The full dissection is Pro.
Get the timed shots, type and sound specs, and the runnable recipe.
Open the full blueprint- Plate 03 / The hook, frame by frame (first 3 seconds)Pro
- Plate 04 / Structure (beat sheet)Pro
- Plate 05 / Shot grammarPro
- Plate 06 / Visual style guidePro
- Plate 07 / Voice and deliveryPro
- Plate 08 / Sound designPro
- Plate 09 / PackagingPro
- Plate 10 / Script templatePro
- Plate 11 / Production planPro
- Plate 12 / PromptsPro
- Plate 13 / Edit recipePro
- Plate 14 / QA checklistPro
- Plate 15 / Make it yoursPro
- Recipe / runnable promptPro