Video model · Veo 3.1 · Starter and up

Veo 3.1

Your idea. A scene in motion.

Google's most cinematic, prompt-accurate video model — up to 4K with lip-synced, generated audio. Generate on Mintdreamer alongside every other model — one subscription instead of five.

Also known as Google Veo 3.1 · veo-3.1

PLAYING Veo 3.1 · First-person view soaring low over a medieval battlefield at dawn, gliding past clashing knights in armor, fire-lit arrows whizzing overhead

End

Animate a photo

Create your account, then choose a plan. Your photo, prompt and model stay with you through payment.

Example sources: fal · prompt excerpt

Specs

Under the hood

Length: 5s default (adjustable)
Resolution: 4K
Aspect: 16:9 and more
Inputs: Prompt (required) · First frame · End frame
Audio: Native audio

Provider: Google
Price here: 400 credits per 5s clip (≈ $4.00)
Family: veo-3-1
Render time: Slow — up to a minute or more
Prompt language: Multilingual
Commercial use: Allowed — outputs are yours

How to prompt it

A prompt to start from. Make it yours.

Click an example and it lands in the box above.

What a clip costs

Length sets the price. See it at this output setting.

One credit is one cent. Failed generations do not cost credits.

Length	4KCredits · USD
4s	320$3.20
5s · default	400$4.00
6s	480$4.80
8s	640$6.40

On starter

$9first month

3,000 credits ≈ 7 clips at the default settings. Then $29/mo.

7 of 7 runs illustrated · gallery examples repeat

See all plans

Strengths and limits

Good at, and not.

Good at

cinematic motion
camera language
lip-synced audio
4K
multilingual

Watch out for

expensive
slow

Third-party standing

LMArena text-to-video · veo-3.1-audio

Board dated 2026-07-05 · checked 2026-07-22

arena.ai

Versions and family

Meet the family

The models available here, and what each is for.

Veo 3.1 · this pagecinematic motion · camera language · lip-synced audio Veo 3.1 Litecinematic motion · native audio · good cost/quality Veo 3.1 Fastcinematic motion · native audio · good cost/quality

Questions

Straight answers

Does Veo 3.1 generate audio?+

Yes — Veo 3.1 produces native, lip-synced audio together with the video: ambient sound, effects, and synced dialogue. It's one of the few models that returns a finished clip with sound rather than a silent draft.

How long are the clips and what resolution?+

Clips default to 5 seconds and are adjustable; Veo 3.1 supports up to 4K. Because it bills per second, longer clips scale in price linearly.

How much does it cost?+

About 400 credits for a 5-second clip (~$4.00), billed per second so longer clips scale linearly. One subscription covers Veo 3.1 and every other model.

Can I animate an existing image?+

Yes. Veo 3.1 supports image-to-video and first-/last-frame interpolation — give it a starting frame and a prompt to animate a key visual you already have.

Related models

You might also look at

Your idea. Start here.

The box remembers the prompt you picked above.