Beverage demos obey one law: the drink must be in motion within the first two seconds. Not the person, not the pitch — the pour. This Veo 3.1 template opens mid-extraction, with a thick espresso stream already pulling into the mug, because appetite appeal is the hook and everything else is supporting material.
The setting is a deliberate choice: a work-from-home desk, not a kitchen. It places the product inside the buyer’s actual pain point — decent coffee without leaving the laptop — and sets up the money line, “a real shot of espresso at my desk in ninety seconds.” The speaker is written calm and practical, mid-task, barely looking up at first; for coffee gear, competence sells harder than enthusiasm.
Audio does half the demo’s work here, so the prompt names it precisely: the hiss-press of extraction close to the mic, the mug set down on wood. The CTA targets the wallet (“if your café budget’s being beaten out of you”) because coffee-gear buyers are almost always doing that exact math. Adapt this for cold brew, matcha kits, protein shakes, or tea — keep the first-two-seconds pour and swap the preparation sound for yours.
Subject: A man in his 30s, calm and practical, standing at a home-office desk with a compact manual espresso maker and a ceramic mug.
Action: Within the first two seconds he presses the plunger and a thick espresso stream pulls into the mug; he lifts it, sips, nods slowly, then holds the brewer up and turns it once so the camera reads its size.
Scene: A desk corner with a laptop, a notebook, and yesterday's mug pushed aside — a real work-from-home setup.
Camera: Phone propped against the monitor, static medium shot with natural micro-wobble; he leans toward the lens for the last line.
Lighting: Window daylight from behind the desk mixed with monitor glow, honest and uneven.
Style: Smartphone UGC demo, appetizing but unpolished, real crema texture visible on the shot.
Dialogue: (mid-press, barely looking up) "No machine. No pods. Just this." (sips, nods) "That's a real shot of espresso at my desk in ninety seconds. If your café budget's been getting out of hand — this fixes it."
Audio: the hiss-press of the extraction close to the mic, the mug set down on wood, room tone, phone-mic voice, no music.
Negative prompt: studio microphone, cinematic color grading, polished ad look, teleprompter delivery, barista b-roll montage, slow-motion pour, on-screen text.This is a template — your product deserves its own script. Upload a photo and PromptShot rewrites the persona, setting, and dialogue around it, for all three models at once.
Customize this for your product →FAQs
What should the first two seconds of a beverage ad show?
The liquid in motion — a pour, a pull, a swirl. Appetite appeal is the hook; the person and the pitch come after. This template opens mid-extraction for exactly that reason.
Why a desk instead of a kitchen for a coffee demo?
The desk places the product inside the buyer's real problem — good coffee without leaving work — and sets up the "at my desk in ninety seconds" line. Settings that match the use case outsell pretty backdrops.
Why does the negative prompt ban slow motion?
Slow-mo pours are the visual signature of produced commercials. Real-time extraction with honest audio keeps the clip in UGC territory, where trust — and conversion — lives.