Models/Veo 3.1 Fast
Video ModelGoogle DeepMind

Veo 3.1 Fast

Google DeepMind's speed-optimised video model. Generate cinematic clips in under 30 seconds with start and end frame control.

720p – 1080p4s – 8s16:9 · 9:16Optional AudioStart + End Frame

What is Veo 3.1 Fast?

Veo 3.1 Fast is Google DeepMind's speed-optimised variant of the Veo 3.1 architecture. While its sibling Veo 3.1 focuses on maximum quality with multi-image reference support, Veo 3.1 Fast is engineered for rapid iteration — delivering cinematic results in sub-30-second generation times.

The model supports start and end frames, allowing you to anchor the beginning and end of a shot visually. This means you can direct specific transitions, controlled reveals, or any motion that needs to arrive at a defined destination frame.

Optional audio generation means you can choose to add AI-generated sound to your clip in the same pass, without switching to a separate audio tool. This makes Veo 3.1 Fast particularly effective for social content workflows where speed and audio both matter.

Sub-30s generation

Fastest in the Veo line

Up to 1080p

720p default, 1080p available

Start + End frame

Direct from A to B

Optional audio

Toggle on per generation

How to generate video with Veo 3.1 Fast on project.video

01

Open the composer

Go to your dashboard and open the generation composer. All models are available from a single unified workspace.

02

Select Veo 3.1 Fast

Click the model selector and choose Veo 3.1 Fast from the video models list. Your existing prompt stays in place.

03

Upload reference frames

Optionally drag a start frame and/or end frame. These anchor the visual context — subject, lighting, composition.

04

Set specs and generate

Choose aspect ratio (16:9 or 9:16), resolution, duration (4s/6s/8s), toggle audio, then hit generate.

Technical specs

ProviderGoogle DeepMind
ModeVideo generation
Aspect ratios16:9, 9:16
Resolutions720p, 1080p
Duration options4 seconds, 6 seconds, 8 seconds
AudioOptional (toggle per generation)
Start frameSupported (image input)
End frameSupported (image input)

Best use cases

High-volume social content

Generate 10+ variations in the time competitors produce one. Veo 3.1 Fast is the model for teams running content at scale across TikTok, Instagram, and YouTube Shorts.

Brand campaign ideation

Draft and discard quickly. Use Veo 3.1 Fast to prototype a dozen directions before committing resources to the final Veo 3.1 render.

Reference-directed transitions

Supply a start frame (current state) and end frame (target state) to generate precisely directed transitions — product reveals, before/after, scene changes.

Audio-paired short clips

Toggle audio on to generate video and sound in a single pass. Ideal for social reels, ad spots, and any content where you need both without post-production assembly.

Example prompts

Copy any of these to get started on project.video.

"Cinematic slow push-in on a black espresso cup on a marble counter, steam curling upward, soft side-lit window light, shallow depth of field, 16:9"

16:96sNo audio

"Product reveal: sleek wireless headphones rotate on a clean white plinth, studio rim lighting, subtle reflection below, premium feel"

16:98sStart frame

"Vertical social cut: person steps out of a taxi onto a rainy city street at night, neon reflections, handheld camera feel, 9:16"

9:164sAudio on

Frequently asked questions

Start generating with Veo 3.1 Fast

Switch models without re-entering your prompt. Compare Veo 3.1 Fast with any other model on project.video side by side.