Keep this page open while you write Veo 3.1 prompts. It has the exact vocabulary the model understands — shot sizes, camera moves, lighting terms, and the native-audio syntax that makes Veo generate synced dialogue and sound. Every table is copy-paste ready, and the settings section tells you what belongs in the app rather than the prompt. For full walkthroughs, see the 35 best Veo prompts and how to prompt Veo for realistic video.

Advertisement

The 6-part shot formula

Veo responds best when you write like a director handing a crew a shot brief — one flowing paragraph, then the audio lines. Every strong shot breaks into six beats, in this order. The last one, audio, is what sets Veo apart from older models.

BeatWhat to write
SubjectWho or what is on screen — specific appearance, wardrobe, materials.
ActionOne clear motion. Not three actions stitched together.
SettingPlace plus time of day.
CameraShot size plus one movement.
Lighting/StyleMood, lighting term, optional lens or film reference.
AudioDialogue in quotes, then SFX: and Ambient: lines.

Stack the first five beats into one paragraph, add the audio lines beneath, and set duration, resolution, and aspect ratio in the app before you generate. Grab terms from the tables below and drop them straight in. See Veo prompt templates for fill-in-the-blank skeletons built on this exact formula.

Shot sizes

Shot size controls how much of the subject and setting is visible. Pick one per shot and name it explicitly.

TermWhat it framesUse for
Extreme wide shotSubject tiny against a huge environmentEstablishing scale, landscapes, openers
Wide shotFull subject plus surrounding spaceShowing action and location together
Full shotSubject head to toe, little backgroundFull-body movement, dance, sport
Medium shotWaist upDialogue, everyday action, product use
Close-upHead and shouldersEmotion, reaction, spoken lines
Extreme close-upEyes, hands, or a small detail fills the frameTension, texture, tiny mechanisms
Over-the-shoulderForeground shoulder/head, subject beyondConversations, listener's POV
MacroExtreme magnification of a surface or objectProduct texture, food, water droplets
POVCamera is the subject's eyesImmersive first-person action

Camera moves — one per shot

Use exactly one move per shot. Stacking moves — a pan that also dollies and cranes — makes Veo's motion unstable and shaky. Need a second move? Make it a second clip and join them with Extend.

MoveEffectWhen to use
Static / locked-offNo camera motion at allDialogue, calm product shots, stillness
PanPivots horizontally from a fixed pointRevealing a wide space, following lateral movement
TiltPivots vertically from a fixed pointRevealing height — a building, a tall subject
Dolly in / outPhysically moves toward or away from subjectBuilding intensity (in) or releasing it (out)
Tracking / truckingMoves alongside a moving subjectFollowing a walk, run, or vehicle at constant distance
Crane / jibRises or descends smoothly, often changing angleGrand reveals, rising above a scene
Arc / orbitCircles around the subjectHero shots, product turnarounds
Push-inSlow, subtle move closer without a full dollyQuiet emotional emphasis
Pull-backSlow move away to reveal contextEnding a scene, revealing scale
Whip panVery fast horizontal pan, motion-blurredEnergetic transitions, action beats
HandheldSlight natural shake, human-operated feelDocumentary realism, urgency
SteadicamSmooth floating motion through spaceWalking shots that need polish, not shake

Lighting & lens

Pair one lighting term with one lens or style term for a consistent, filmic look. Two is plenty — more and Veo starts averaging them out.

TermLook
Golden hourWarm, low-angle sun, long soft shadows
Blue hourCool twilight tones just after sunset
High-keyBright, even, low-contrast — commercial, upbeat
Low-keyDark, high-contrast, moody shadows
SoftboxDiffused, flattering studio light
Practical lightsIn-scene sources — lamps, neon, candles
Volumetric lightVisible beams and haze — fog, dust, god rays
Backlight / rim lightLight behind subject, glowing edge outline
Shallow depth of fieldSharp subject, soft blurred background
Wide-angle 24mmExpansive, slightly exaggerated perspective
35mmNatural, documentary feel
85mmCompressed, flattering portrait feel
AnamorphicWidescreen look with horizontal lens flares
Film grainSubtle texture, analog feel
Advertisement

Native audio syntax

This is Veo 3.1's headline feature: it generates dialogue, sound effects, and ambient sound synced to the video. Write each layer as its own line beneath the visual paragraph. Keep dialogue short — a clip is only 4-8 seconds, so aim for one or two brief lines.

LayerSyntaxWhat to write
DialogueIn quotation marksThe barista says, "One oat flat white, coming up." — attribute the speaker, keep it to a line or two.
Sound effectsSFX: prefixSFX: espresso machine hissing, cups clinking. — name each discrete sound.
AmbientAmbient: prefixAmbient: quiet café murmur, soft jazz. — the background bed of the scene.
No captions(no subtitles, no on-screen text)Add at the end when you don't want Veo to burn captions over the dialogue.

Output settings

These are chosen in the Gemini app, Flow, or the Gemini API and Vertex AI before you generate — not written into the prompt text. Veo has no inline parameters like Midjourney's --ar, so typing a duration or aspect ratio in the prompt does nothing.

SettingOptionsNote
Duration4s, 6s, or 8s per generationUse Extend (scene extension) to chain clips — it seeds the next clip from the last frames.
Resolution720p, 1080p, 4K (3840×2160)Veo 3.1 was first to true 4K. Draft low, render the final take at 4K.
Aspect ratio16:9 (landscape), native 9:16 (vertical)16:9 for YouTube and widescreen; 9:16 for Shorts, Reels, TikTok.
Ingredients to VideoUp to ~3 reference imagesKeep a character, product, or style consistent across shots.
Frames to VideoFirst and/or last frameLock the exact start and end of a clip — great for product accuracy.

Example prompts

Five complete Veo shots built from the tables above. Each ends with a plain settings note in parentheses — a reminder of what to pick in the app, not text to paste into the prompt.

1. Product close-up with dialogue

A barista sets a ceramic cup on a wooden counter and pushes it toward the camera, steam curling upward. Cozy café interior, early morning light through a tall window. Close-up, slow push-in. Golden hour lighting, shallow depth of field, 85mm.
The barista says, "One oat flat white, coming up."
SFX: espresso machine hissing, cup settling on wood.
Ambient: quiet café murmur, soft jazz.
(no subtitles, no on-screen text)

Best for: product and café ads where the spoken line sells it. (16:9, 1080p, 8s)

2. Walking city scene

A woman in a red raincoat walks briskly down a rain-slicked sidewalk at night, weaving between umbrellas. Downtown street, neon signs reflecting in puddles. Wide shot, steadicam tracking alongside her. Low-key lighting, practical neon, film grain.
SFX: footsteps splashing on wet pavement, distant car horn.
Ambient: steady rain, muffled city traffic.

Why it works: one action, one move, and an ambient bed that grounds the whole shot. (9:16, 1080p, 8s)

3. Nature establishing shot

A lone hiker crosses a ridgeline as morning fog drifts through the valley below. Mountain range at sunrise. Extreme wide shot, slow crane rising to reveal the full valley. Golden hour lighting, volumetric light through the fog, 24mm.
SFX: wind gusting across the ridge, a single crow call.
Ambient: distant birdsong, faint river below.

Best for: openers and travel content — render this one at 4K. (16:9, 4K, 8s)

4. Two-person dialogue

Two friends sit across a small table, one leaning in as the other reacts. Warm bistro interior, afternoon light through a large window. Over-the-shoulder shot, static locked-off camera. High-key lighting, softbox fill, shallow depth of field.
She says, "You actually did it — you quit today?" He grins and nods, "This morning."
SFX: cutlery clinking, a chair scraping nearby.
Ambient: low bistro chatter, warm background music.
(no subtitles, no on-screen text)

Why it works: two short lines fit an 8-second clip, and the audio layers carry the scene. (16:9, 1080p, 8s)

5. Action reveal

A vintage motorcycle roars out of a tunnel onto an open desert highway at dusk. Empty desert road, blue hour sky fading to orange at the horizon. Full shot, dolly out as the bike accelerates toward camera. Backlight from the setting sun, anamorphic flares, film grain.
SFX: engine roar building, gravel kicking up under the tires.
Ambient: open desert wind, faint highway hum.

Best for: high-energy hero shots and title sequences. (16:9, 4K, 6s)

Want more finished examples before you start? Browse the 35 best Veo prompts or grab ready-made skeletons from Veo prompt templates.

Frequently Asked Questions

Does Veo make sound?

Yes. Veo 3.1 generates native synced audio — dialogue, sound effects, and ambient sound — together with the video. Describe each layer in the prompt: dialogue in quotation marks, then SFX: and Ambient: lines. This synced audio is Veo's headline feature versus older models.

How long can a Veo clip be, and how do I make it longer?

Each Veo generation is 4, 6, or 8 seconds. For longer sequences, use scene extension (Extend), which seeds the next clip from the last frames of the previous one. Do not write a duration like "10 seconds" inside the prompt text — length is an app or API setting.

Does Veo output 4K?

Yes. Veo 3.1 supports 720p, 1080p, and true 4K (3840×2160) — it was the first mainstream model with real 4K output. Many creators draft at 720p or 1080p and re-render the final take at 4K to save time and credits.

Can Veo make vertical 9:16 video?

Yes. Veo 3.1 supports native 9:16 (vertical) as well as 16:9 (landscape). Choose the aspect ratio as an app or API setting before you generate — it is not written into the prompt text.

Can I set clip length in the prompt text?

No. Veo has no inline parameters like Midjourney's --ar. Duration, resolution, and aspect ratio are chosen as settings in the Gemini app, Flow, or the Gemini API and Vertex AI before you generate. Typing "8 seconds, 4K" inside the prompt is ignored.

How many camera moves should one shot have?

One. Pick a single move per shot from the camera moves table. Stacking moves — a pan that also dollies and cranes — makes Veo's motion unstable and shaky. If you need a second move, make it a second clip and stitch with Extend.

How do I stop Veo burning subtitles into the video?

Add (no subtitles, no on-screen text) to the end of the prompt. Veo sometimes renders captions over dialogue, and this tag tells it to leave the frame clean so you can add your own text in editing.

How do I keep a character or product consistent across shots?

Use Ingredients to Video: upload up to about three reference images (a character, a product, a style) so Veo carries them across shots. Use Frames to Video to lock a specific first and/or last frame. Both are especially useful for product accuracy and multi-shot sequences.

Advertisement