VideoGoogle

Veo 3.1

Veo 3.1 is Google's quality tier for video and the model here with the best native audio, generating speech and sound with the picture. Reach for it when the clip has to be heard as well as watched.

Duration4, 6, 8s

Resolutions720p, 1080p, 4k

Aspect ratios16:9, 9:16, auto

AudioNative

Reference inputsNot supported

Make with Veo 3.1 →View pricing

Added July 2026. Included on every plan.

Why this one

What makes Veo 3.1 different

Audio is native, not bolted onDialogue, ambience and effects are generated with the picture, so they actually match what is on screen.
Google's top video qualityThe quality tier of the Veo line, which is the reason to pay more than Fast or Lite.
First and last frame controlBoth anchors are available, with the last frame requiring a first.
4k outputThe top resolution tier renders at 4k for finals.
Fixed durations that suit editingA short option ladder rather than an open range, which keeps clips cuttable.
An auto aspect optionLet the model choose the framing when you do not have a placement in mind yet.

Use cases

Best for

Talking scenes
Ads with sound
Product films
Atmospheric B roll
Trailer beats
Explainer clips

Technique

Prompt tips

Write the sound as well as the pictureName the ambience, the voice and the effects. Native audio only helps if you direct it.
Put dialogue in quotesQuoted lines read as dialogue rather than as description, which is what you want on a talking shot.
Anchor the first frame for compositionA supplied still is the most reliable route to the framing you already have.
Pick the duration deliberatelyThe options are few and they are real cut points. Choose the one your edit needs.
Keep the scene single locationVeo is strongest holding one place convincingly, not cutting between two.

Mechanism

How Veo 3.1 works

Veo generates picture and sound together from one prompt, which is why its audio lines up with on screen action instead of floating over it. You can anchor the clip with a first frame and optionally a last, and the duration comes from a short fixed ladder rather than an open range, so what comes back tends to sit cleanly in a timeline.

Getting started

How to use it on Dolly

Pick Veo 3.1Choose it in the video studio, or just ask the agent for it by name.
Write the promptDescribe what you want, and add your reference images or frames where they help.
GenerateThe exact credit cost sits on the button before you press it, and a failed run refunds automatically.

Pricing

What it costs

Every generation shows its exact credit cost on the button before you run it.

720p · 8s: 201 credits
1080p · 8s: 206 credits
4k · 8s: 298 credits

One run is about 1/6 of a Starter month.

Failed generations refund automatically. See plans

Capabilities

Specs

Resolutions: 720p, 1080p, 4k
Aspect ratios: 16:9, 9:16, auto
Durations: 4, 6, 8s
Frame inputs: first + last
Reference images: Not supported
Audio: Native
Max per run: 2

Questions

Veo 3.1 FAQ

Can I give it reference images?

No. Reference input is not available on this tier: every attempt was refused by the provider, which says references are supported on the Fast and Lite tiers only.

Does it really generate speech?

Yes, natively, with the picture. Quote the line you want in the prompt.

How long can a clip be?

It uses a short fixed duration ladder rather than a free range. Pick the option that matches your cut.

Is 4k worth it?

For finals and large placements, yes. Draft at a lower tier and re-run the prompt you like.

Veo 3.1, Fast or Lite?

This tier is the quality one and takes no references. Fast and Lite are cheaper and do accept reference images.

Ready to make with Veo 3.1?

Every model is included on every plan. The price sits on the button before you run it.

Start making →