Why choose it
- Animate, first/last, and references
- Up to 4K output
- Optional generated audio
Original model creator
Veo 3.1
A premium text-and-image video model for cinematic shots, guided frames, references, optional audio, and up to 4K output.
Loading Veo 3.1 sample
Official sampleSourced output
Official sample · Results vary by prompt and settings
See the model move.
Direct answer
When should you use Veo 3.1?
Veo 3.1 is a strong choice when the shot needs to feel directed rather than merely animated. Start from text, animate one image, direct a first and last frame, or use up to three references while combining camera language and optional audio for polished campaign footage.
Best for
Cinematic campaign shots, product worlds, and scenes where motion and audio should be planned together.
Technical readout
The supported shot envelope.
- Duration
- 4, 6, or 8 seconds
- Resolution
- 720p, 1080p, or 4K
- Aspect ratio
- 16:9 or 9:16
- Audio
- Optional generated audio
What to consider
- Supports 16:9 and 9:16
- Reference mode uses an 8-second shot
Prompt direction
How to prompt Veo 3.1
Describe the subject, action, camera move, lighting, and sound as separate beats in one concise shot direction.
Start a Veo 3.1 promptQuestions, answered
Veo 3.1 FAQ
What is Veo 3.1 best for?
Veo 3.1 is best suited to cinematic, directed shots where camera movement, scene composition, and optional sound all matter.
Can Veo 3.1 animate images?
Yes. Video Lab supports a starting image, first and last frames, or up to three reference images with Veo 3.1.
Does Veo 3.1 generate audio?
Audio is optional. Turn it on when the scene benefits from ambient sound, effects, or speech generated with the video.
Change the lens
Compare Veo 3.1 with another model.
Independent testGoogleOriginal model creatorGemini Omni Flash
A fast multimodal model for concise text-, image-, or reference-led clips with native audio.See model
Official sample
ByteDanceOriginal model creatorSeedance 2.5
A next-generation text-and-image video model with native audio, 30-second shots, first/last frames, and deep reference control.See model
Independent testByteDanceOriginal model creatorSeedance 2.0
A flexible text-and-image model with first/last-frame direction, up to nine references, broad formats, and optional audio.See modelGoogle lens selected
Direct your first Veo 3.1 shot.
Write the prompt, choose supported controls, and see the exact credit quote before you generate.
Open Veo 3.1 in Video Lab