Skip to content
refs
REF-1853Source onlineBlueprint rev 01

Veo 3.1 cinematic feature reveal

A 90-second AI video launch film that proves each creative feature through escalating cinematic scenes and sparse labels.

Maker @GoogleDeepMindFor Google DeepMindOriginal post ↗
Cut timeline · 12 shots01:30
00:0000:1500:3000:4501:0001:1501:30

Field notes / why it works

The first 2.75 seconds turn a grid of possibilities into one moving motocross proof while the product is named. Source cards become a unified scene at 0:18–0:23, overlapping the strongest replay peak (0:18.2–0:19.1). Fresh feature demonstrations at 0:25, 0:42, and 0:57 sustain interest without dense text.

01

Plate 01 / The format in one breath

A calm narrator introduces a creative tool, then the film lets a run of visually distinct outputs demonstrate its capabilities. It moves from a gallery and one spectacular example to increasingly specific workflows, pauses for an audio proof sequence, and closes on a simple destination card.

Why it works

  • The first 2.75 s zoom from a dark wall of many possibilities into one motocross example; the spoken product identification arrives by 1.52 s.
  • A focused example at 0:18–0:23 turns three source ingredients into one live scene. This overlaps the strongest measured replay area, 0:18.2–0:19.1.
  • The film refreshes the promise at 0:25 (extend), 0:42 (edit elements), and 0:59 (audio), while using only a few large labels. The imagery carries the explanation.
02

Plate 02 / Format card

Platform · aspect · lengthYouTube · 16:9 · 90 s · source measurement 640×360 at 30 fps
Pace12 detected shots, 11 cuts; 7.3–14 cuts/min allowing uncertain changes; 11.3 measured picture changes/min; median shot 3.69 s. One detector-defined “shot” runs 37.05 s but contains multiple visible scenes and overlays.
Script159 spoken words; 118 wpm across runtime, 164 wpm while speaking; 18 short sentences, mean 8.8 words.
VoiceLow-register, poised commercial narrator with clear, deliberate emphasis; one brief in-scene spoken line.
On screenPredominantly cinematic generated-looking scene examples and interface-like compositing; no presenter or conventional screen walkthrough.
CaptionsNo running subtitles. Large white, centered feature labels appear sparingly; dark navy brand cards.
SoundContinuous tonal cinematic music bed (measured around −20.6 dBFS), foregrounded scene audio in the audio section (inferred from imagery and narration); master −14.6 LUFS, true peak −1.0 dBFS.
Structure7 beats: introduction, source-to-scene, extension, controlled transitions, object edits, realism/audio, brand CTA at about 1:20.

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
  1. Plate 03 / The hook, frame by frame (first 3 seconds)Pro
  2. Plate 04 / Structure (beat sheet)Pro
  3. Plate 05 / Shot grammarPro
  4. Plate 06 / Visual style guidePro
  5. Plate 07 / Voice and deliveryPro
  6. Plate 08 / Sound designPro
  7. Plate 09 / PackagingPro
  8. Plate 10 / Script templatePro
  9. Plate 11 / Production planPro
  10. Plate 12 / PromptsPro
  11. Plate 13 / Edit recipePro
  12. Plate 14 / QA checklistPro
  13. Plate 15 / Make it yoursPro
  14. Recipe / runnable promptPro