Verified against Veo 3.1 · 2026-07-20
Generate a vertical short-form hook clip built to stop the scroll
A Veo 3.1 prompt for a 5-8 second vertical clip designed as the opening hook of a Reels/Shorts/TikTok-style video, with the fast, immediate camera move and native audio a scroll-stopping open needs.
The prompt
Ready to copy — highlighted parts are example details you can swap.
Subject and action: a street food vendor, flipping a pan of food into the air and catching it without looking, framed to fill most of a vertical 9:16 frame. Camera: quick whip-pan into a snap zoom on the subject's reaction, landing on a tight close-up within the first second. Environment and lighting: a busy night market stall lit by string lights, natural handheld-feel lighting, nothing that reads as a studio. Style and mood: raw, unpolished, phone-shot authenticity — no cinematic color grade. Audio: a sharp pan clang and a crowd gasp, sudden and attention-grabbing at the exact moment of the whip-pan, no music bed.
Customize the highlighted detailsoptional — the prompt above already works
Why this works
Short-form hooks live or die in the first second, so this prompt puts the payoff — a snap zoom landing on a tight close-up — inside "within the first second" as an explicit, checkable instruction rather than a vague "exciting opening." Deliberately naming the aesthetic as "raw, unpolished, phone-shot authenticity" and ruling out a cinematic grade is a real Veo 3.1 lever: without it, the model's default leans toward a smoother, more produced look that reads as an ad rather than the native, algorithm-favored short-form style it needs to blend into a feed. Tying the audio instruction to a specific diegetic sound synced to the visual beat (the pan clang landing on the whip-pan) rather than a generic music bed is what makes the native audio generation reinforce the hook instead of competing with whatever the platform's auto-captions or trending-audio overlay will add on top after upload.
What you get back
A 6-second vertical clip: the vendor tosses the pan, the camera whip-pans and snaps into a tight close-up on their face mid-catch, a loud pan clang and an off-camera crowd gasp landing exactly on the zoom, string lights blown out slightly in the background, no color grading applied.
Verified against
Veo 3.1 3.1 · 2026-07-20
Changelog
- 2026-07-20 — Published, verified against Veo 3.1.
Need this built into your business?
If a prompt isn't enough — what Scult builds, built and maintained for you — that's Scult's day job.
EXPLORE WHAT SCULT BUILDS
