AI models

Veo 3.1: Google's video model with sound, in Soundverse

Pick Veo 3.1, Veo 3.1 Fast or Veo 3.1 Lite in AI Video Generator, or ask Agent One for it by name. Describe the shot or start from an image, and get a 4, 6 or 8 second clip, with sound on by default.

Veo 3.1 is Google's video model with native sound, and in Soundverse it turns a text prompt, a first and last frame, or up to three reference images into a 4, 6 or 8 second clip at 720p or 1080p. Two lighter tiers sit beside it: Veo 3.1 Fast for quicker, lower-cost renders, and Veo 3.1 Lite for the lowest-cost renders, which always include audio. It's built for musicians, creators and marketers who want cinematic shots for releases, teasers and social posts.

How it works

  1. Pick a Veo 3.1 tier

    Open AI Video Generator under Create in AI Tools and choose Veo 3.1, Veo 3.1 Fast or Veo 3.1 Lite in the Model dropdown. In AI Studio, right-click a video lane and choose Generate Video for the same options.

  2. Describe the shot

    Write the subject, action, camera and mood, and put any sound or dialogue in sentences of their own. Enhance can polish the prompt once you've written it.

  3. Add images if you like

    Turn on Use first / last frame to start and end on images from your Library. On Veo 3.1, you can instead add up to three reference images to keep a character or object consistent, at 16:9 and 8 seconds.

  4. Set the output and generate

    Choose 4, 6 or 8 seconds, 720p or 1080p (1080p needs 8 seconds), 16:9 or 9:16, and, on Veo 3.1 or Veo 3.1 Fast, whether to generate audio, then click Generate in Chat. The clip arrives in your chat and in Videos in your Library.

Why use Veo 3.1

Three tiers, one model family

Use Veo 3.1 for the highest-quality renders and reference images, Veo 3.1 Fast for quicker, lower-cost drafts, and Veo 3.1 Lite when cost matters most.

Sound from the same render

Veo 3.1 and Veo 3.1 Fast generate a soundtrack with the clip unless you turn Generate audio off, which also lowers the cost. Veo 3.1 Lite always generates audio.

A subject that stays the same

Give Veo 3.1 up to three reference images of a character or object to keep that subject consistent through the shot.

Ready for music videos

AI Music Video Generator can film every scene of a video on Veo 3.1. On Auto, it picks Veo 3.1 for 16:9 videos unless the singer lip-syncs.

Great for

  • Cinematic shots for a release teaser
  • Vertical 9:16 clips for Reels and Shorts
  • Animating cover art from a first frame
  • Short scenes with dialogue and sound
  • Quick, low-cost drafts on Veo 3.1 Fast
  • Widescreen scenes for a music video

Frequently asked questions

What is Veo 3.1?

Veo 3.1 is Google's video model with native sound, offered in Soundverse's AI Video Generator alongside Veo 3.1 Fast and Veo 3.1 Lite. In Soundverse, Veo 3.1 turns a prompt, a first and last frame, or up to three reference images into a 4, 6 or 8 second clip at 720p or 1080p, in 16:9 or 9:16.

How do I use Veo 3.1 in Soundverse?

Open AI Video Generator, choose Veo 3.1 in the Model dropdown, describe the shot and click Generate in Chat. You can also right-click a video lane in AI Studio and choose Generate Video, or ask Agent One by name, such as "make an 8 second clip of waves at sunset with Veo 3.1". Veo 3.1 is available on the Creator plan and above.

What's the difference between Veo 3.1, Veo 3.1 Fast and Veo 3.1 Lite?

Veo 3.1 is the highest-quality tier and the only one that takes reference images. Veo 3.1 Fast renders quicker at a lower cost, with sound optional. Veo 3.1 Lite is the lowest-cost tier and always generates audio. All three Veo 3.1 tiers make 4, 6 or 8 second clips at 720p or 1080p in 16:9 or 9:16, and all three can start on a first frame and end on a last frame.

How is Veo 3.1 different from Seedance 2.0 and Gemini Omni Flash 1.1?

Seedance 2.0, Soundverse's default video model, makes 4 to 15 second clips in six aspect ratios and takes reference video plus a vocal for lip-sync. Gemini Omni Flash 1.1 makes clips of any whole length from 3 to 10 seconds and always adds sound. Veo 3.1 sticks to 4, 6 or 8 seconds in 16:9 or 9:16, with sound you can switch off, and takes reference images only at 16:9 and 8 seconds.

How long can a Veo 3.1 video be?

Each Veo 3.1 run makes one clip of exactly 4, 6 or 8 seconds, and 1080p is only available at 8 seconds; Veo 3.1 doesn't render 4K. For a single clip of up to 30 seconds, pick Seedance 2.5 instead. For a full video set to a song, choose Veo 3.1 in AI Music Video Generator, which films every scene on Veo 3.1 and cuts the scenes to the music.

Is Veo 3.1 free?

No. Veo 3.1, Veo 3.1 Fast and Veo 3.1 Lite are available on the Creator plan and above, and each run uses tokens from your plan. The cost depends on the tier, the clip length and the output settings, and AI Video Generator shows the estimate before you generate. You can sign up for Soundverse free and explore the core tools before you upgrade.

Can Veo 3.1 lip-sync a character to my song?

No. Veo 3.1 doesn't take reference audio or reference video, so Veo 3.1 can't make a character lip-sync to your vocal in AI Video Generator. For that, pick Seedance 2.0 or Seedance 2.5 and add a portrait as a reference image and the vocal as reference audio, or open Lip Sync. A clean vocal from Stem Separator syncs more reliably than a full mix.

Can I use Veo 3.1 videos commercially?

Veo 3.1 runs on paid Soundverse plans, and paid plans add a commercial license; the Pricing page lists what each plan covers. You need the rights to any image you add as a frame or reference, and you should only show a face you own or have permission to use. Veo 3.1's safety filter can also block a video whose prompt involves real people, public figures, brand names or song lyrics.

Ready to film with Veo 3.1?

Open AI Video Generator, pick Veo 3.1, Veo 3.1 Fast or Veo 3.1 Lite in the Model dropdown, and describe your first shot.