Google's video model and the most expensive lane here, which is the honest headline: you pick Veo when the shot has to be right rather than cheap. It generates sound with the picture, and it accepts either a first and last frame to interpolate between or a small set of ingredient images to keep a look consistent.
Which plan: Included from Starter.
Dialogue, ambience and effects are generated with the frames rather than dubbed over them.
Give it where the shot starts and where it ends and it works out the movement between.
A small set of stills keeps a character, a product or a palette steady across the clip.
Direct the shot and its sound as separate parts of the scene.
A ceramic artist places a blue bowl on a wooden shelf. The camera tracks the hands in close-up. With sound enabled: a soft ceramic tap and quiet room ambience.
Read the prompting tutorial. Select this model before using Enhance prompt to apply its guidance to your draft.
Sources: Google Veo prompting guide.
| Setting | Details |
|---|---|
| Made by | |
| Runs | Text to video, with native audio |
| Frame control | First and last frame, or ingredient images |
| Reference images | Up to 3 |
| Opens at | Starter |
A lighthouse keeper climbing a spiral stair at dawn, lantern swinging, the sea booming somewhere below, camera following one step behind
Open Google Veo 3.1 in the studio — Choose the model and review your prompt and quote before generating.
Yes, natively — the sound is produced with the picture rather than added afterwards.
It bills at a much higher rate per second than the other lanes here, and we pass that through rather than hiding it. The price you see in the prompt bar before you press Generate is the price you pay.
Yes — attach a first and a last frame and Veo interpolates the movement between them. Alternatively, attach up to three ingredient images to keep a look consistent without pinning the framing.