Veo 3.1
videoGoogle's Veo 3.1 video model. A short clip with sound from a prompt or from one opening picture. Fast and Lite are not offered.
What it supports
- Aspect ratios
- 16:9, 9:16
- Resolutions
- 720p, 1080p, 4k
- Duration
- 4–8s
- Audio
- Supported
What it costs
- false · 1080p
- 28 credits per second
- false · 720p
- 28 credits per second
- true · 1080p
- 58 credits per second
- true · 720p
- 58 credits per second
- false · 4k
- 60 credits per second
- true · 4k
- 86 credits per second
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
Veo 3.1 is Google's current Veo video model. It is not Veo 3, which Google has retired, and it is not Veo 3.1 Fast or Lite. Those variants are not offered here.
What it is good at
Google describes Veo 3.1 as richer native audio, from conversation to sound effects, with a stronger reading of cinematic style and better results when a clip starts from a picture. Use it for one shot that should carry its own sound.
How to use it on Visxy
Write the shot, or give one picture as the opening frame. Sound starts off until you turn it on.
Where it differs
Kling 3.0 can take a closing frame as well as an opening one. Flux 3 is Black Forest Labs' video model, also with a sound switch and a single opening picture. Veo is Google's, and it does not take a second frame.
FAQ
Does the clip include sound?
When you turn the sound switch on. It starts off.
Can I give a first and last frame?
One picture, as the opening frame. A closing frame is not on this model.
Are Fast and Lite available?
No. This page is Veo 3.1, the quality model. Google also ships Fast and Lite. They are not offered here.
Who makes it?
Google. This page is Veo 3.1. Fast and Lite are separate models, and they are not offered here.
Official sources
More video models
All video modelsSeedance 2.5
ByteDance's Seedance 2.5. A clip that can hold a whole beat of story, from a prompt or from an opening frame and an optional closing frame.
Seedance 2.0 Fast
The fast tier of ByteDance's Seedance 2.0. A prompt is always required, plus an opening frame and an optional closing frame. Sound starts off.
MiniMax H3
MiniMax's general video model. A clip from a prompt, from an opening and optional closing frame, or from several reference pictures.
Flux 3
Black Forest Labs' first Flux video model. A clip with sound from a prompt or from one opening picture. Flux 2 still makes the photographs.
Wan 2.7
Alibaba's Wan 2.7 video model. A clip from a prompt or two frames, or from reference pictures you name. Enhance is optional. There is no sound switch.
PixVerse V6
PixVerse V6. A clip from a prompt or one opening picture, with sound you can turn on, or a clip guided by several reference pictures.