Three ways to ask your TV for more
A cinematic TV assistant launch that proves three everyday uses through dialogue, readable answers, and lived results.
Field notes / why it works
The first 10.3 seconds use a tiny glowing symbol and a growing TV outline to introduce the capability before cutting to people. Three requests at roughly 0:12, 0:30, and 0:44 each lead to a visible answer and outcome; the neighborhood response at 0:49.8–0:50.4 is a replay peak. The format moves from choosing entertainment to cooking to a consequential move, broadening the value without a narrator.
Plate 01 / The format in one breath
A widescreen product announcement turns three ordinary questions into short, observable product outcomes. It opens with a restrained brand promise, then alternates between a warm home scene, a voice request, the interface's answer, and the person's response. The last card generalizes the three examples into a larger promise.
Why it works
- The first 10.3 s makes the premise legible through a glowing assistant mark and the words “biggest screen” before the first live-action cut.
- Three use cases widen relevance: choosing a show at 0:12–0:25, cooking at 0:30–0:41, and moving to a city at 0:43–0:52.
- Each spoken request leads to a visible answer: a show card near 0:20, recipe cards near 0:39, and neighborhood recommendations near 0:50. The 0:49.8–0:50.4 answer is one of the replay peaks.
Plate 02 / Format card
| Platform · aspect · length | YouTube · 16:9 · 59.1 s · measured file 640×360 at 23.98 fps |
| Pace | 26 detected shots; 25 cuts, or 25.4/min. Seven uncertain changes make a 25.4–32.5/min range. Mean shot 2.27 s; median 1.5 s. Four internal steps; about 29.5 picture changes/min. |
| Script | 121 machine-transcribed words; 160 wpm overall and 242 wpm while speaking. Several lines are misrecognized, so use the UI frames to confirm meaning. Three questions; short dialogue turns. |
| Voice | Multiple conversational adult voices plus a calm synthetic assistant response (inferred from dialogue/UI). No continuous narrator. |
| On screen | Approximately 45% home live action, 30% TV/interface and demonstration imagery, 25% logo and type animation (estimated from sheets and shot durations). |
| Captions | Small white dialogue inside a dark rounded query pill; response text is part of the TV UI. Large opening and closing title cards replace editorial subtitles. |
| Sound | Continuous soft tonal/music-like bed; roughly 121 BPM detection, uncertain. Dialogue, UI response, and brief TV show audio carry the examples. Measured −25.2 LUFS integrated, −6.2 dBFS true peak. |
| Structure | Brand promise → entertainment request/proof → cooking request/proof → neighborhood request/proof → closing promise. No spoken CTA; description links to product. |
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