Google · video
Veo 3.1
Google's flagship video model: lifelike motion, native dialogue and sound, up to 4K.
- Length
- 4 to 8 s
- Resolution
- 720p, 1080p, 4K
- Aspect ratio
- 16:9, 9:16
- References
- Up to 2 image files
About Veo 3.1
Veo 3.1 is Google's flagship video model, priced at $0.50 per second. It runs as text to video, image to video and start and end frame. Audio is generated with the picture rather than added afterwards, and a negative prompt, under Advanced, lets you say what to keep out of the shot.
Length runs from 4 seconds to 8 seconds and output goes up to 4K, in 16:9 and 9:16. The price is per second of video: a longer clip, 4K or sound each raise it. A typical generation takes about 2 min.
Good for
- Clips with spoken dialogue, where the voice is generated with the picture
- Turning a still into a moving shot
- A controlled transition between a start frame and an end frame
Getting good results
- Write the spoken lines in the prompt when you want dialogue; the sound is generated with the video, not added after.
- Pick 4K only when you need it: $12.00 at 4K against $8.00 for the same clip below it.
- Turning audio off lowers the bill: $4.00 against $8.00 at 720p.
Veo 3.1 questions
Does Veo 3.1 make sound?
Yes. It generates dialogue and sound together with the video; turning the audio off lowers the price.
How long can a Veo 3.1 clip be?
From 4 seconds to 8 seconds, set before you generate.
What resolutions does Veo 3.1 support?
720p, 1080p and 4K. The price is per second, and 4K costs more than the others.