It is Google’s flagship video generation model, producing 4 or 8 second clips with natively synchronized audio from text or a start image.

Does Veo 3.1 generate sound?

Yes. Audio is generated natively and synchronized with the picture — describe the sound you want in the prompt.

How long can clips be?

Exactly 4 or 8 seconds. For longer continuous takes, use Seedance 2.5 or WAN 3.0 and reserve Veo 3.1 for the hero moments.

Can I control the first and last frame?

Yes. Veo 3.1 accepts an optional start frame, an optional end frame, or both — useful for planned transitions between two stills.

Which resolution does Made use?

Made does not expose a resolution control; clips render at the provider’s 720p default, and that is the tier Made bills at provider cost.

When should I choose another model?

Iterate on Veo 3.1 Lite at a fraction of the per-second rate, choose Veo 3.1 Native Dialogue for lip-synced talking scenes, or Kling 3 Pro for a different cinematic look.

Veo 3.1 prompts that actually ran

Every prompt below was generated with Veo 3.1 in Made, and the output next to it is what came back — not a curated stock image. Copy a prompt as a starting point, then use the guide underneath to adapt it.

Try Veo 3.1 Veo 3.1 pricing: $0.40 / second

Original results

Veo 3.1 prompts and their outputs

These examples use media produced for Made. Prompts are included when the production record allows them.

Motion study with audio

“Cinematic clip with sound: a night train crosses a stone viaduct over fog, wheels clacking, camera drifting alongside”

Image-to-video

“The astronaut walks forward through parting sunflowers, fabric rustling and birdsong audible, camera pulling back”

Creative scene

“Underwater clip with audio: a surfer duck-dives under a breaking wave, bubbles roaring past, sunlight rippling”

Astronaut in a sunflower field, a still used as a Veo 3.1 start frame

Start-frame control

“Use this image as the opening composition.”

Scene brief

“Set the scene as a still before describing its motion and sound.”

Composition brief

“Plan the shot as a still, then hand the motion to the model.”

How to write a Veo 3.1 prompt

1
Write the shot and its sound
Describe the subject, motion, camera path, and the audio the clip should carry — sound is generated natively.
2
Pin frames if needed
Add a start frame to animate a still, or a start and end frame to control the transition between two compositions.
3
Choose format and length
Pick 16:9, 9:16, or 1:1 and a duration of 4 or 8 seconds.
4
Review and refine
Check motion, audio sync, and continuity, then adjust one instruction at a time.

What Veo 3.1 responds well to

Prompt for these jobs

Cinematic realism with natively synchronized sound
Start and end frame control for planned transitions
Vertical-first social clips — 9:16 is the Made default
Physics-aware motion and coherent camera language

Check the output for

Clips are 4 or 8 seconds only; longer continuous takes need Seedance 2.5 or WAN 3.0.
Premium per-second pricing — iterate on Veo 3.1 Lite first and save this model for hero shots.
Resolution is not selectable in Made; output renders at the provider’s 720p default.

Iteration is cheap here: Veo 3.1 costs $0.40 / second at the provider's wholesale rate, so rewriting a prompt and rerunning it is a normal part of the workflow, not a budget decision. See the full Veo 3.1 pricing breakdown.

Questions, answered

Veo 3.1 prompts FAQ

Need a specific answer? Contact support

: It is Google’s flagship video generation model, producing 4 or 8 second clips with natively synchronized audio from text or a start image.

More tested prompts across all models live in the prompt library, and the full Veo 3.1 capability rundown is on the model page.