Say It, Then See It Appear
A voice-input launch film turns repeated typing across apps into three visible dictation payoffs.
Field notes / why it works
A waiting chat cursor and a recognizable typing complaint establish the problem by 1.8 seconds, then three app contexts make the repetition concrete by 9.9 seconds. The black question card and key press around 11.8–13.6 seconds reset attention before speech visibly fills an email, chat reply, and three-point document by 37.4 seconds.
Plate 01 / The format in one breath
An interface-led feature launch starts with a familiar small annoyance: the user knows the message but has to type it. It repeats the annoyance across apps, interrupts with a one-word question, then proves the new voice action through email, chat, and document examples before a spare brand card.
Why it works
- The claim becomes legible in the first 1.8 s: a waiting chat cursor and the line “You already know what you want to say” create immediate recognition.
- The repeated task gets three visual contexts by 9.9 s, so the feature feels broadly useful before it is introduced.
- The payoff is observable: at 13.6–20.9 s, speech fills an email reply; at 22.4–24.5 s, it fills chat; at 29.2–37.4 s, it creates a three-item document.
Plate 02 / Format card
| Reference | |
|---|---|
| Platform · aspect · length | X · 1280×720, 16:9, 30 fps · 46.5 s |
| Pace | 4 measured shots, 3 cuts, 3.9 cuts/min; 8 internal picture steps, 14.2 total changes/min; mean shot 11.63 s |
| Script | 79 recognized words; 108 wpm across runtime, 145 wpm while speaking; 8 short sentences; four “you” uses per roughly 79 words |
| Voice | Low-register, calm adult narrator; conversational, lightly emphatic, with room for pauses |
| On screen | Nearly all designed desktop UI; a brief live-action keyboard insert around 13.6 s; no talking head |
| Captions | Small white full-sentence subtitles centered near the bottom; no karaoke or highlight words |
| Sound | Continuous tonal electronic bed detected; no distinct effect is documented; measured −13.1 LUFS integrated, +0.8 dBFS true peak |
| Structure | Friction → repetition → “why?” turn → three product proofs → minimal end card, 38.8–46.5 s |
Tools you'll need: Remotion for motion graphics · ElevenLabs or a recorded voice · a licensed or generated music track · partly
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 framePro
- 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 prompt