Why film the hook here
The cafe hook trades action for permission. Nothing has to happen — you are sitting somewhere people sit to talk, so a forty-second monologue does not need justifying the way it would in a bedroom. That makes it the right room for the prompts that carry an argument rather than a punchline.
It is also the only setting in this set with a table in every shot, and a table is what makes a hands-in-frame product hold physically possible without a second person. Half the cafe prompts below are built on that: the cup down, the thing picked up, the knowing look.
The trade is that everyone films in cafes, so the differentiator is not the room, it is the pace. The clips that work here are slower than the rest of this set — a pause before the line, a look off-camera, a sip. Shoot them at kitchen speed and they read as generic.
- A table stabilises both the phone and your hands, which is what makes the POV product hold in this room look deliberate instead of shaky.
- Ambient chatter under the dialogue signals a real place. It is one of the few background sounds that adds credibility rather than costing it.
- Sitting down changes your delivery. The same script read standing sounds like an announcement and read at a table sounds like a confession.
What has to be in frame
Set this up once and every prompt below works without redressing the room between takes.
- A cup that is visibly in use — foam collapsed, spoon on the saucer, not a fresh untouched pour.
- A table edge in the bottom of frame so the viewer knows where you are before you speak.
- Enough depth behind you that the background falls away — a window, the counter, the far wall. A blank wall two feet back kills the room.
- A laptop only if the clip is about the laptop. Otherwise it turns a personal hook into a work clip.
- Nothing branded facing the lens — turn the cup, move the napkin.
- Your own hands free at least once in the clip so you can gesture.
Shooting notes for cafe
Light
Sit beside the window, not in front of it and not under the ceiling spots. Side light from a window gives you the soft falloff that makes the shot look shot rather than snapped; overhead cafe lighting puts shadows straight under your eyes.
Framing
Arm's length, phone slightly above eye level, tilted down a few degrees. Include the table edge and the cup. This is the one setting where you want visible background depth — a tight face crop wastes the location you came for.
Motion
Hold it. Cafe clips are the exception to lean-it-on-something — the small handheld drift of a real arm is what stops a seated static shot from reading like a video call.
Sound
Coffee grinders are unusable and unpredictable. Record a spare take of every line, because you will lose one to a grinder and you will not hear it happen while you are talking.
The two lines every prompt shares
Each scene below is the part that changes. These two lines are the same across the whole set, so they are written once here rather than repeated on every card — append both when you copy a prompt.
Base style line
Vertical phone UGC, authentic skin texture, natural light, slight handheld motion.
Clean plate line
Clean plate only: no on-screen text, no captions, no watermarks, no logos, no UI overlays.
One more exclusion for cafe
Also exclude other customers' faces. In a real cafe this is a consent problem as much as a composition one; shoot with a wall or a window behind you rather than the room.
7 hooks with a line to say
Each one is a scene, a suggested opening line and the finished clip it produced. Shoot it, or paste the prompt and generate it.
- 1
Cafe Drink Deadpan
A person takes a sip of a generic coffee or beverage at a cafe, then looks at the camera with a completely deadpan, unimpressed expression.
Say this
“Tried the new drink. It's... a drink. Yeah.”
deadpantasting-reactionFull prompt to copy+
A person takes a sip of a generic coffee or beverage at a cafe, then looks at the camera with a completely deadpan, unimpressed expression. Vertical phone UGC, authentic skin texture, natural light, slight handheld motion. Clean plate only: no on-screen text, no captions, no watermarks, no logos, no UI overlays.
- 2
Cafe Emotional Moment
A person at a cafe table looks into the camera, a soft smile on their face and eyes glistening with happy tears.
Say this
“Wow, this hit different. Totally unexpected.”
crying-happytalking-head reactionFull prompt to copy+
A person at a cafe table looks into the camera, a soft smile on their face and eyes glistening with happy tears. Vertical phone UGC, authentic skin texture, natural light, slight handheld motion. Clean plate only: no on-screen text, no captions, no watermarks, no logos, no UI overlays.
- 3
Cafe Laughing Out Loud
A person sits at a cafe table, genuinely laughing while looking at their phone, held in a selfie position.
Say this
“I just saw something SO funny, I had to share. This is gold!”
laughingtalking-head reactionFull prompt to copy+
A person sits at a cafe table, genuinely laughing while looking at their phone, held in a selfie position. Vertical phone UGC, authentic skin texture, natural light, slight handheld motion. Clean plate only: no on-screen text, no captions, no watermarks, no logos, no UI overlays.
- 4
Cafe Phone Shock
POV of hands holding a generic smartphone at a cafe table, the screen display causing a subtle, shocked reaction as the viewer looks down.
Say this
“I just saw this and now I can't unsee it. Seriously.”
shockedPOV-hands product holdFull prompt to copy+
POV of hands holding a generic smartphone at a cafe table, the screen display causing a subtle, shocked reaction as the viewer looks down. Vertical phone UGC, authentic skin texture, natural light, slight handheld motion. Clean plate only: no on-screen text, no captions, no watermarks, no logos, no UI overlays.
- 5
Cafe Smug Satisfaction
A person sips coffee at a cafe, then subtly shows a plain smartphone screen with a slightly smug, knowing smile, filmed from a POV perspective.
Say this
“They said it couldn't be done, but I just proved them wrong.”
smugPOV-hands product holdFull prompt to copy+
A person sips coffee at a cafe, then subtly shows a plain smartphone screen with a slightly smug, knowing smile, filmed from a POV perspective. Vertical phone UGC, authentic skin texture, natural light, slight handheld motion. Clean plate only: no on-screen text, no captions, no watermarks, no logos, no UI overlays.
- 6
Cafe Thoughtful Pause
A young woman sits at a cafe table, looking thoughtfully off-camera, as if considering a profound idea.
Say this
“I've been doing it wrong this whole time. Mind blown.”
thoughtfultalking-head reactionFull prompt to copy+
A young woman sits at a cafe table, looking thoughtfully off-camera, as if considering a profound idea. Vertical phone UGC, authentic skin texture, natural light, slight handheld motion. Clean plate only: no on-screen text, no captions, no watermarks, no logos, no UI overlays.
- 7
Cafe Thoughts Unfold
A person sits at a cafe table, looking off-camera with a thoughtful expression, occasionally nodding slightly.
Say this
“I just realized something about my daily routine... mind blown.”
thoughtfultalking-head reactionFull prompt to copy+
A person sits at a cafe table, looking off-camera with a thoughtful expression, occasionally nodding slightly. Vertical phone UGC, authentic skin texture, natural light, slight handheld motion. Clean plate only: no on-screen text, no captions, no watermarks, no logos, no UI overlays.
7 reaction beats, no script attached
These come from the premade hook library inside the app. They store an expression and a scene rather than a line, which is the right way round when you already know what you want to say and need a face to say it over.
Contemplative
Staring into her coffee cup with a contemplative faraway expression.
Crying
A single tear rolling down her cheek as she stares quietly at her phone, cappuccino untouched in front of her.
Laughing
Laughing warmly at something just off-camera, latte in front of her.
Surprised
Eyebrows shooting up in pleasant surprise at her laptop screen, latte in front of her.
Surprised (M)
A man in his late twenties, eyebrows raised in genuine surprise looking up from his laptop, espresso in front of him.
Thoughtful
Holding a cappuccino in both hands, looking softly into the camera as if mid-conversation.
Vlog (M)
Selfie-style vertical phone footage addressing the camera at a cafe table, cappuccino in frame, authentic vlog feel.
What this set covers
The emotional and shot-format spread across the scripted cafe hooks. Gaps here are real gaps — the set reports what the room actually produced rather than filling every cell.
Emotion
- Thoughtful
- 2
- Crying Happy
- 1
- Deadpan
- 1
- Laughing
- 1
- Shocked
- 1
- Smug
- 1
Format
- Talking Head Reaction
- 4
- POV Hands Product Hold
- 2
- Tasting Reaction
- 1
A three-clip cafe run
One table, one sitting, three clips that cut together — and enough coverage that you are not relying on a single take surviving the grinder.
- 1
Open mid-thought
Already talking when the clip starts, looking slightly off-camera. Starting on a sentence already in progress removes the half-second of setup that most talking-head clips lose people on.
- 2
Bring the hands in
Cup down, pick the thing up, look at it, then back to the lens. This is where a product enters a cafe clip without becoming an advert.
- 3
Land on the look
Stop talking. Hold the expression — smug, unimpressed, quietly pleased — for a beat longer than feels natural. The silence at the end is what makes it loop.
What goes wrong in this setting
- Sitting with the window directly behind you, which turns a well-lit room into a silhouette.
- Filming at a table with no depth behind it. The location is the reason to be here; a blank wall throws it away.
- Talking over the ambient noise instead of under it. Cafe clips work quiet — project and it sounds like a piece to camera in a food court.
- Holding the cup the entire clip. Put it down so your hands are free for at least one gesture.
Workflows that fit these hooks
Neura is the coffee-adjacent build with the full prompt set published, and the matcha routine is the closest thing in the workflow library to a drink-led lifestyle clip. The panel reel is there for a different reason: it is the workflow to read if you want to cut one of these cafe hooks against reaction footage.
NEURA — Coffee vs Brain
AI anime explainer ad — a cute story of how caffeine wakes up your brain, told inside a tiny neuron-city, doubling as an ad for the NEURA coffee brand. Sleepy blob citizens, purple adenosine "monsters", and golden caffeine heroes battle for the brain's docking ports across 18 clean anime clips. ~68s vertical reel with energetic narrator voiceover.
Morning Matcha Routine
UGC-style wellness reel — a clean-girl creator walks through her actual morning matcha ritual, then cuts to a cozy animated hero shot of the finished iced latte.
Viral Panel & Reaction Reel
A 4-scene viral hook video. Scene 1-2: A professional panel expert discusses her before/after results with a product, denying she's gatekeeping. Scene 3-4: An influencer films a selfie-POV reaction, holding the product and confirming the expert's claims.
Finishing the clip
A hook is the first two seconds, not the post. These are the steps between a raw cafe clip and something you can publish.
Who this setting is for
Frequently asked questions
Do I need permission to film in a cafe?+
Ask. Most independent places are fine with a phone at a table and firm about tripods, lights and anything that occupies space. If you are filming the cafe itself as the subject rather than yourself, that is a different conversation and it should happen before you set up.
Why do half these prompts have no hook line?+
The set merges two sources. The prompts marked as reaction clips came from the in-app hooks library, which stores an expression and a scene but no script — they are meant to be paired with whatever line you are already writing. The ones with a suggested line came from a set where the line was written alongside the scene.
Is a laptop in frame a good idea?+
Only if the clip is about work or a screen. A laptop reframes a cafe from a social setting into an office and quietly changes what the viewer expects you to talk about. If the hook is personal, close it.
How long should a cafe hook clip be?+
Longer than the rest of this set. The room buys you patience, so the pause before the line is doing work — cutting it to match a kitchen clip's pace throws away the only advantage the setting has.
Can these be generated rather than filmed?+
Yes. Every scene line below is written as a generation prompt. Combine it with the base style line and the clean-plate line, and the output is a vertical clip in the same shape as the preview on the card.
Other settings
Morning bedroom
The highest-intimacy room in the set. Soft light, no makeup, a product opened in bed — this is where a hook stops feeling like an ad and starts feeling like a text from a friend.
Selfie vlog
No location, no props, no excuse — just a face and a first sentence. The hardest format in this set and the one that travels furthest when it lands.
Outdoor street
Motion the viewer can feel. A moving background does a job no static room can — it makes a clip feel like it is going somewhere before you have said what.
Generate these hooks in Versely
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.