Video generation

Veo 3.1

by Google

Google's cinematic video model, with sound generated in the same pass.

Veo 3.1 is Google's flagship video model. Its signature is native audio: ambient sound, effects and speech are generated together with the picture, so a clip arrives ready to post rather than silent. Output is 720p or 1080p in 4, 6 or 8-second lengths, from a text prompt or a first/last frame.

It is priced at a flat per-second rate regardless of resolution, which makes 1080p the obvious choice. Reach for it when the clip needs to feel like a finished piece of film — lifestyle scenes, brand moments, anything with atmosphere.

AI MODEL PRICING

From $0.52

per second

Generate in Zalify Canvas

Veo 3.1 pricing on Zalify

Veo 3.1 is billed per second of finished video. The rate depends only on the resolution tier you choose — aspect ratio, prompt length and the number of reference images don't change the price.

ResolutionPrice per second
720p$0.52
1080p$0.52

What a typical render costs

4-second clip at 720p

$2.08

6-second clip at 720p

$3.12

8-second clip at 720p

$4.16

4-second clip at 1080p

$2.08

6-second clip at 1080p

$3.12

8-second clip at 1080p

$4.16

Specifications

Provider

Google

Resolution tiers

720p · 1080p

Aspect ratios

9:16 · 16:9

Clip length

4 / 6 / 8 seconds

Generation modes

Text to video · Image to video (first / last frame)

Native audio

Yes

Where Veo 3.1 shines

  • Native audio generated with the video — no separate sound pass

  • Strong cinematic lighting, camera moves and physical realism

  • Same price at 720p and 1080p

  • Reliable first/last-frame control for product shots

Best for

Brand and lifestyle videos with sound
Landing-page hero clips
Short ads that need atmosphere, not just motion
Image-to-video from a styled product photo

Frequently asked questions

Other video models

Try Veo 3.1 in Zalify Canvas

Start free, add balance when you need it, and generate with every model from one canvas — no per-model subscriptions.