Offer30% off your first 3 months on any paid plan with SHOTZ30, applied at checkoutEnds in
shotz
A shot in the style Veo 3.1 makesBest with audio
Google · AI video generator

Veo 3.1

Veo 3.1 is Google’s video model for dialogue and sound in one take: people speak, and the room sounds right. Clips of 4 to 8 seconds, up to 4K, from a prompt or a start frame.

Made by
Google
Length
4 to 8 seconds
Starts from
A prompt or a start frame
Sound
Generated with the clip
Cost
200 credits for a 5 second clip

What it’s good at.

Lines that sync

Write what someone says in quotes and Veo makes the voice and the lips together.

Sound that fits

Footsteps, traffic, room tone. The audio is made with the picture, not added after.

Up to 4K

Choose 720p, 1080p or 4K. Above 720p every clip is 8 seconds.

Good forTalking headsDialogueAdsShort filmsUGC-style clips

How to use Veo 3.1 on Shotz.

  1. 1Describe the shotWrite what happens, or start from a photo or a frame of your own footage.
  2. 2Pick Veo 3.1It’s already picked when you start here. Choose the length, the shape and how many takes.
  3. 3Cut it inKeep the take you like and drop it into an edit with your footage, captions and music.
A prompt to try

Close-up of a barista behind the counter, she looks up and says “Same as yesterday?” with a small smile, espresso machine hissing behind her

Use this prompt →
Tips for Veo 3.1
  • Put spoken lines in quotes and say who says them.
  • Describe the sound you want as well as the picture.
  • Keep it to one beat. Veo makes up to 8 seconds, so plan cuts in the editor.

Veo 3.1 and the other video models.

Every one is on the same plan and the same credits, so you can try a prompt on a few and keep the best take.

ModelBest forLengthSoundCredits
Veo 3.1Dialogue and sound in one take4–8s200
Seedance 2.5Best value, up to 30 seconds in one shot4–30s40
Kling 3.0Fast action and people moving3–15s70
HappyHorse 1.1The top-ranked video model right now3–10s80
Wan 3.0Up to 30 seconds at 1080p, with audio2–30s60
MiniMax H32K video from text or keyframes3–10s—60
Grok Imagine 1.5Fast, with synced audio3–10s50
FLUX 3 VideoVideo with native audio5–10s60

Questions.

What is Veo 3.1?

Veo 3.1 is Google’s video model for dialogue and sound in one take: people speak, and the room sounds right. Clips of 4 to 8 seconds, up to 4K, from a prompt or a start frame.

Can Veo 3.1 make people talk?

Yes. Put the line in quotes in your prompt and say who speaks it. The voice, lip movement and background sound are made together in one take.

How much does Veo 3.1 cost?

200 credits for a 5 second clip on Shotz. Pro is $29 a month with 2,500 credits, enough for about 12 5 second clips on Veo 3.1. You can try it with the 50 free credits on the Free plan.

Do I need a Google account to use Veo 3.1?

No. Veo 3.1 runs inside Shotz on your Shotz credits, along with every other model. One sign-in, one bill.

Can I use Veo 3.1 for commercial work?

Yes. Everything you make on a paid Shotz plan can be used commercially.

What happens after I generate with Veo 3.1?

Your take lands in Create and your Library. Add it to an edit and cut it with your own footage, captions and music, then export up to 4K with no watermark.

Make it with Veo 3.1.

Then cut it with your own footage, in the same place.

Start free