These are reusable fill-in-the-blank skeletons for Veo 3.1. Anything in [BRACKETS] is a slot you replace — swap [subject], [action], [setting], [camera move], and [lighting] for your scene, then delete the brackets. Keep the word order, because the Subject + Action + Setting + Camera + Lighting + Audio sequence is what makes Veo follow the shot. Every template ends with an audio slot — dialogue in quotes, an SFX line, or ambient sound — since native synced audio is Veo's signature. Set aspect ratio, resolution, and duration in the app; the notes like (16:9, 1080p, 8s) are reminders, not text to paste. New to this? Start with the 35 best Veo prompts or the Veo prompt cheat sheet.
Cinematic shots
Director-style skeletons for narrative and hero shots. One clear action, one camera move, one lighting term per fill.
1. Establishing hero shot
[subject] [action] in [setting] at [time of day]. Extreme wide shot, [camera move] to reveal the full scene. [lighting] lighting, [film/style reference] look, shallow depth of field. Ambient: [ambient sound]. SFX: [key sound].Fill in: [subject], [action], [setting], [time of day], [camera move], [lighting], [film/style reference], [ambient sound], [key sound]. (16:9, 4K, 8s)
2. Emotional close-up
Close-up of [subject]'s face as they [subtle action / expression]. [setting] in the background, softly out of focus. Slow push-in, static aside from the push. [lighting] lighting, 85mm, film grain. [subject] says quietly, "[dialogue line]" Ambient: [ambient sound]. (no subtitles, no on-screen text)Fill in: [subject], [subtle action / expression], [setting], [lighting], [dialogue line], [ambient sound]. (16:9, 1080p, 6s)
3. Moody tracking shot
[subject] [walks/runs] through [setting] as [environmental detail] surrounds them. Medium shot, steadicam tracking alongside at a constant distance. Low-key [lighting] lighting, practical [light source], anamorphic look. Ambient: [ambient sound]. SFX: [footstep/impact sound].Fill in: [subject], [walks/runs], [setting], [environmental detail], [lighting], [light source], [ambient sound], [footstep/impact sound]. (16:9, 1080p, 8s)
Product & ads
Clean, controllable skeletons for commercial video. For accuracy, upload the item as a reference with Ingredients to Video before filling these in — see Veo prompts for product & ad video.
4. Product hero on a surface
A [product] rests on [surface], [product detail / texture] catching the light. [setting], [time of day] light. Close-up, slow arc orbiting the product. [lighting] lighting, softbox fill, shallow depth of field. SFX: [product sound]. Ambient: [subtle ambient].Fill in: [product], [surface], [product detail / texture], [setting], [time of day], [lighting], [product sound], [subtle ambient]. (16:9, 4K, 6s)
5. Product in use
A [person] [uses the product] in [setting]. Medium shot, static locked-off camera. [lighting] lighting, high-key, clean commercial look. [person] says, "[one-line benefit / tagline]" SFX: [product-in-use sound]. Ambient: [ambient sound]. (no subtitles, no on-screen text)Fill in: [person], [uses the product], [setting], [lighting], [one-line benefit / tagline], [product-in-use sound], [ambient sound]. (16:9, 1080p, 8s)
6. Unboxing / reveal
A pair of hands opens [packaging] to reveal a [product] inside. Overhead top-down shot, slow push-in on the reveal. [lighting] lighting, softbox, [color/mood] palette. SFX: [packaging sound], then [product settle sound]. Ambient: [ambient sound].Fill in: [packaging], [product], [lighting], [color/mood], [packaging sound], [product settle sound], [ambient sound]. (16:9, 1080p, 8s)
7. Liquid / pour macro
[liquid] pours into [container] and swirls, [bubbles/steam/condensation] forming. Extreme close-up, static camera. [lighting] lighting, backlight rim light, high-speed slow-motion feel. SFX: [pour sound], [liquid settle sound]. Ambient: [ambient sound].Fill in: [liquid], [container], [bubbles/steam/condensation], [lighting], [pour sound], [liquid settle sound], [ambient sound]. (16:9, 4K, 6s)
Talking avatar & dialogue
Skeletons built around Veo's synced speech. Keep the [dialogue line] to one short sentence — a clip is only 4-8 seconds. More at Veo prompts for talking characters & dialogue.
8. Presenter to camera
A [presenter description] looks directly at the camera in [setting]. Medium shot, static locked-off camera. [lighting] lighting, softbox key, clean background. [presenter] says, "[dialogue line]" Ambient: [room tone]. (no subtitles, no on-screen text)Fill in: [presenter description], [setting], [lighting], [dialogue line], [room tone]. (16:9, 1080p, 8s)
9. Two-person conversation
[person A] and [person B] talk across [location]. Over-the-shoulder shot on [person B], static camera. [lighting] lighting, shallow depth of field. [person A] says, "[line A]" [person B] replies, "[line B]" Ambient: [ambient sound]. (no subtitles, no on-screen text)Fill in: [person A], [person B], [location], [lighting], [line A], [line B], [ambient sound]. (16:9, 1080p, 8s)
10. Talking-head explainer
A [expert/character] gestures while explaining [topic] in [setting]. Medium close-up, subtle slow push-in. [lighting] lighting, practical [light source] behind. [expert] says, "[dialogue line]" Ambient: [ambient sound]. (no subtitles, no on-screen text)Fill in: [expert/character], [topic], [setting], [lighting], [light source], [dialogue line], [ambient sound]. (16:9, 1080p, 8s)
11. Character reaction line
[character] reacts to [event / off-screen thing] with [emotion]. Close-up, handheld with slight natural shake. [lighting] lighting, [color/mood] tone. [character] exclaims, "[short reaction line]" SFX: [reaction sound]. Ambient: [ambient sound]. (no subtitles, no on-screen text)Fill in: [character], [event / off-screen thing], [emotion], [lighting], [color/mood], [short reaction line], [reaction sound], [ambient sound]. (16:9, 1080p, 6s)
B-roll & nature
Atmosphere and cutaway skeletons — great for openers and transitions. Pair with the finished set in Veo prompts for cinematic b-roll.
12. Landscape reveal
[natural landscape] stretches to the horizon as [weather/atmosphere] moves across it. Extreme wide shot, slow crane rising to reveal scale. [lighting] lighting, volumetric light, 35mm. Ambient: [nature ambient — wind, water, birdsong]. SFX: [distant sound].Fill in: [natural landscape], [weather/atmosphere], [lighting], [nature ambient], [distant sound]. (16:9, 4K, 8s)
13. Texture / detail cutaway
Extreme close-up of [natural texture / detail] as [tiny motion] happens. Static camera, macro focus. [lighting] lighting, shallow depth of field, film grain. SFX: [micro sound]. Ambient: [ambient sound].Fill in: [natural texture / detail], [tiny motion], [lighting], [micro sound], [ambient sound]. (16:9, 4K, 6s)
14. Urban b-roll
[city detail — traffic, crowd, signage] moves through [urban setting] at [time of day]. Wide shot, slow tracking dolly past the scene. [lighting] lighting, practical neon, anamorphic flares. Ambient: [city ambient]. SFX: [urban sound].Fill in: [city detail], [urban setting], [time of day], [lighting], [city ambient], [urban sound]. (16:9, 1080p, 8s)
15. Time-of-day mood shot
[setting] bathed in [time of day] light as [subtle environmental motion] drifts through frame. Medium wide shot, static locked-off camera. [lighting] lighting, [color/mood] palette. Ambient: [ambient sound].Fill in: [setting], [time of day], [subtle environmental motion], [lighting], [color/mood], [ambient sound]. (16:9, 1080p, 6s)
Action & movement
High-energy skeletons. Keep it to one action and one move — stacked moves make Veo's motion shaky.
16. Chase / pursuit
[subject] [runs/rides/drives] fast through [setting], dodging [obstacles]. Full shot, tracking alongside at speed. [lighting] lighting, motion blur, [film/style reference] look. SFX: [motion sound], [impact sound]. Ambient: [ambient sound].Fill in: [subject], [runs/rides/drives], [setting], [obstacles], [lighting], [film/style reference], [motion sound], [impact sound], [ambient sound]. (16:9, 1080p, 8s)
17. Vehicle reveal
A [vehicle] [emerges/accelerates] out of [setting] toward camera at [time of day]. Full shot, dolly out as it approaches. [lighting] lighting, backlight, anamorphic flares. SFX: [engine sound], [tire/wind sound]. Ambient: [ambient sound].Fill in: [vehicle], [emerges/accelerates], [setting], [time of day], [lighting], [engine sound], [tire/wind sound], [ambient sound]. (16:9, 4K, 8s)
18. Sports / athletic move
[athlete] performs [athletic action] in [setting]. Medium shot, whip pan following the peak of the motion. [lighting] lighting, high-speed slow-motion feel, shallow depth of field. SFX: [effort sound], [impact sound]. Ambient: [crowd/ambient sound].Fill in: [athlete], [athletic action], [setting], [lighting], [effort sound], [impact sound], [crowd/ambient sound]. (16:9, 1080p, 6s)
Vertical social 9:16
Phone-first skeletons framed for the vertical crop — subject centered, action reading top-to-bottom. Great for YouTube Shorts & Reels.
19. Vertical talking hook
A [creator] looks straight into the camera in [setting], framed vertically waist-up. Static locked-off camera. [lighting] lighting, bright and clean. [creator] says with energy, "[hook line]" Ambient: [room tone]. (no subtitles, no on-screen text)Fill in: [creator], [setting], [lighting], [hook line], [room tone]. (9:16, 1080p, 8s)
20. Vertical product demo
Hands present a [product] and [demonstrate one feature], framed vertically. Medium close-up, slow push-in. [lighting] lighting, high-key, [color/mood] background. SFX: [product sound]. A voice says, "[one-line pitch]" Ambient: [ambient sound]. (no subtitles, no on-screen text)Fill in: [product], [demonstrate one feature], [lighting], [color/mood], [product sound], [one-line pitch], [ambient sound]. (9:16, 1080p, 8s)
21. Vertical POV moment
POV shot of [experience — walking into, holding, tasting something] in [setting], framed vertically. Handheld with natural motion. [lighting] lighting, [time of day], film grain. SFX: [POV sound]. Ambient: [ambient sound].Fill in: [experience], [setting], [lighting], [time of day], [POV sound], [ambient sound]. (9:16, 1080p, 6s)
22. Vertical trend transition
[subject] does [action], then a quick whip pan transitions to [second subject / second look], framed vertically. Whip pan, single continuous move. [lighting] lighting, [color/mood] palette, punchy contrast. SFX: [whoosh sound], [beat-drop sound]. Ambient: [ambient sound].Fill in: [subject], [action], [second subject / second look], [lighting], [color/mood], [whoosh sound], [beat-drop sound], [ambient sound]. (9:16, 1080p, 6s)
That is 22 skeletons across six use cases. Keep the audio line every time, hold to one camera move per fill, and set your ratio, resolution, and length in the app — never in the prompt text. When a fill starts to feel natural, study the polished versions in the 35 best Veo prompts and tighten your realism with how to prompt Veo for realistic video.
Frequently Asked Questions
How do the [brackets] work?
Each [BRACKET] is a slot you replace with your own detail. Swap [subject], [action], [setting], [camera move], [lighting], and the audio slots for your scene, then delete the brackets. Keep the sentence structure intact — that ordering is what makes Veo follow the shot reliably.
Do I keep the audio line in every template?
Yes. Native synced audio is Veo 3.1's signature feature, so every template ends with a dialogue, SFX, or ambient slot. Even a simple ambient line like "Ambient: quiet room tone" improves realism. Put spoken lines in quotation marks and keep them to one or two short sentences per clip.
Where do I set aspect ratio, resolution, and duration?
In the app or API before you generate — the Gemini app, Flow, or Vertex AI. The settings notes like (16:9, 1080p, 8s) are reminders, not text to paste. Veo has no inline flags like Midjourney's --ar, so writing "8 seconds" inside the prompt does nothing.
Why does each template use only one camera move?
Stacking moves — a pan that also dollies and cranes — makes Veo's motion unstable and shaky. Each template gives you one [camera move] slot on purpose. Pick a single move per shot and let it breathe across the 4-8 second clip.
How do I keep a character or product consistent across templates?
Use Ingredients to Video: upload up to three reference images of your character, product, or style and Veo carries them across shots. For exact start and end poses, use Frames to Video to supply a first and/or last frame. This matters most for the product and talking-avatar templates.
Should I add "no subtitles" to the templates?
Add (no subtitles, no on-screen text) whenever you don't want captions burned into the frame, since Veo sometimes adds them on its own — especially on dialogue clips. Several templates include the tag already; drop it into any template that produces speech.
How long should the dialogue in a template be?
Short. A Veo clip is only 4, 6, or 8 seconds, which is roughly one or two brief lines. Overwriting dialogue makes the delivery rushed and the lip-sync worse. Fill the [dialogue line] slot with a single natural sentence and let the visuals do the rest.
Can I combine templates into a longer video?
Yes. Generate each template as its own shot, then use scene extension (Extend) to continue from the last frames, or edit the clips together in Flow or any editor. Keeping the same [lighting] and [setting] values across templates makes the cuts feel like one continuous scene.