Skip to content
Kenerate IconKenerate Icon
Kenerate AI
Loading your account

Veo 3.1 · 3.1 Fast · Veo 3 · up to 4K · dialogue and sound

Google Veo 3.1 — cinematic video with sound

Google DeepMind's video model makes 4, 6 or 8-second clips with dialogue, music and sound effects — up to 4K, from text, an image, first and last frames, or three reference images.

Try
Rain falls on two detectives talking in a noir alley as the camera slowly pushes in
  • Native sound and dialogue
  • Up to 4K
  • 3 reference images
  • First + last frame

Updated by the

Made with Kenerate

Quick answer

Updated

What is Veo AI?

Veo AI is Google DeepMind's family of AI video models, and Veo 3.1, released 15 October 2025, is the newest Veo: it makes 4, 6 or 8-second clips at up to 4K with dialogue, sound effects and music generated in the same pass. In Kenerate AI's studio you can run four Veo versions for text or image to video, with up to 3 reference images and 7-second extends.

Key facts

Clip lengths
4, 6 or 8 s
Top resolution
4K
Reference images
Up to 3
Sound
Dialogue + effects
Versions here
Veo 3.1, 3.1 Fast, 3, 3 Fast
Released
15 Oct 2025

Real demo

Veo 3.1 vs Wan 3 — same image, same prompt

Switch between the two and turn the sound on. Same start image and motion prompt, two models.

  • Veo 3.1. Veo 3.1 image to video, 6 s at 720p with dialogue and sound.
  • Wan 3. Wan 3 image to video, 5 s at 720p with sound.

Both are unedited outputs from Kenerate's video studio.

Try Veo 3.1

Real results

Real Veo 3.1 clips

Five Veo 3.1 image-to-video clips (6 s, 720p, with sound) — dialogue, music, kitchens, storms and ice.

Real Veo 3.1 clips (6 s, 720p, with sound). Turn the sound on — Veo generates dialogue and effects.

How to

How to use Veo 3.1 on Kenerate

Time needed
Steps
4 steps

  1. Step 1

    Open the video studio

    Pick Veo 3.1, 3.1 Fast, Veo 3 or Veo 3 Fast.

  2. Step 2

    Start from text or an image

    Add a last frame for control, or up to 3 reference images on Veo 3.1.

  3. Step 3

    Write the prompt

    Subject, action, camera, style — and put spoken lines in quotes.

  4. Step 4

    Pick 4, 6 or 8 s and a resolution

    720p to test; 1080p or 4K for the final.

1Describe the scene2Or start from an image3Pick a video model4Set ratio and length, then Create5Watch and download
Kenerate AI Video Studio in Text to Video mode with a lighthouse scene prompt typed in

Open Video Studio in Text to Video mode and write the shot — subject, action, camera move and light.

1 / 5 · Describe the scene

Watch the tour · 1:19

Text, image & reference to video, models, edit, extend & chat

Chapters

Engines

Veo versions in the studio

From the studio's own model list.

  • Veo 3.1 title card — two fictional adult characters in dialogue on a rainy noir street
    Newest Veo

    Google DeepMind

    Veo 3.1

    Input
    Text, image (+ last frame) or 3 refs
    Output
    4/6/8 s · up to 4K · sound

    Best for

    Dialogue and cinematic sound

    Open Veo 3.1
  • Veo 3.1 Fast title card — a fast draft film still of a vintage car on a coastal road

    Google DeepMind

    Veo 3.1 Fast

    Input
    Same as Veo 3.1
    Output
    4/6/8 s · up to 4K · sound

    Best for

    Faster drafts

    Open Veo 3.1 Fast
  • Veo 3 title card — a cinematic film still of a jazz club with visible sound waves rising from a saxophone

    Google DeepMind

    Veo 3

    Input
    Text or image
    Output
    4/6/8 s · 720p or 1080p · sound

    Best for

    The original sound model

    Open Veo 3
  • Veo 3 Fast title card — a quick cinematic clip still of a street musician with visible sound waves

    Google DeepMind

    Veo 3 Fast

    Input
    Text or image
    Output
    4/6/8 s · 720p or 1080p · sound

    Best for

    Quick Veo 3 clips

    Open Veo 3 Fast
  • Gemini Omni 1.1 Flash title card — a film frame being edited by description

    Google

    Gemini Omni 1.1 Flash

    Input
    Text, image, 4 refs or a clip to edit
    Output
    3–10 s · up to 4K

    Best for

    Editing a video by describing the change

    Open Gemini Omni 1.1 Flash

The clips above were made with Veo 3.1; the comparison uses Wan 3.

Tips

Prompting Veo like Google suggests

From Google's Veo prompt guide.

  • Subject, action, style, camera, ambiance, then audio.

  • Put dialogue in quotes: the character says: "…".

  • Name sound effects and ambient noise separately.

  • Use first and last frames for exact start and end poses.

  • Extend adds 7 seconds per step.

  • Veo 3.1 Fast for drafts, Veo 3.1 for finals.

Example uses

How creators use Google Veo 3.1

Illustrative examples of typical workflows, not customer reviews.

  • Editing monitor showing a rainy noir dialogue scene with an audio timeline below it

    Indie filmmaker

    An indie filmmaker could block out a dialogue scene by writing each spoken line in quotes, then test it with Veo 3.1 Fast before rendering the final take in 1080p or 4K.

  • Chef tossing pasta over flames in a busy trattoria kitchen

    Restaurant marketer

    A restaurant marketer could animate a photo of the kitchen line into a short clip with sizzling pans and an order call-out, ready for vertical social posts.

  • Small red boat sailing between blue glaciers in an Arctic fjord

    Nature documentary maker

    A documentary maker could use first and last frames to control a slow glacier shot and let the model add the crack and splash of falling ice.

FAQ

Google Veo 3.1 questions

What is Veo AI?

Veo is Google DeepMind's AI video generator. Veo was announced in May 2024, Veo 2 followed in December 2024, Veo 3 added native sound in May 2025, and Veo 3.1 (October 2025) added reference images, first-and-last-frame and extend. Kenerate runs Veo 3.1, Veo 3.1 Fast, Veo 3 and Veo 3 Fast.

Link to this answer

Is Veo AI the same as veo-ai sites and apps?

No. Several third-party websites and apps use the name "Veo AI" but are separate products. Google's model is called Veo and runs in Google's own apps (Gemini, Flow, YouTube) and APIs, and through platforms that license it, such as Kenerate.

Link to this answer

What is Google Veo 3.1?

Google DeepMind's video model: 4, 6 or 8-second clips at up to 4K with dialogue, sound effects and music, from text, an image, first and last frames or up to 3 reference images.

Link to this answer

Is Veo 3 free?

In Google's Gemini app, video needs a Google AI Plus, Pro or Ultra plan; YouTube Shorts offers a free Veo 3 Fast in some countries. On Kenerate, Veo runs on one-time credit packs that never expire.

Link to this answer

How do I use Veo 3?

Pick Veo 3.1 in the video studio, start from text or an image, write the prompt with any dialogue in quotes, choose 4, 6 or 8 seconds and a resolution, and generate.

Link to this answer

How long can Veo videos be?

4, 6 or 8 seconds per clip. Extend adds 7 seconds at a time.

Link to this answer

How much does Veo 3.1 cost?

On Kenerate, Veo 3.1 is 120 credits a second with sound and 60 without at 720p or 1080p (180 / 120 at 4K), so an 8-second 1080p clip with sound is 960 credits. Veo 3.1 Fast is 45 credits a second with sound, 360 for 8 seconds.

Link to this answer

What is the difference between Veo 3.1 and Veo 3.1 Fast?

Same inputs, lengths and resolutions; Fast renders quicker and costs 45 instead of 120 credits a second with sound. Use Fast for drafts and Veo 3.1 for the final clip.

Link to this answer

Does Veo 3 make sound?

Yes — Veo 3 and 3.1 generate dialogue, sound effects and ambient audio with the video.

Link to this answer

Is there a Veo 4?

No. Google's newest video model is Gemini Omni Flash (May 2026), which you can also run in Kenerate's studio.

Link to this answer

In depth

Google Veo 3.1, explained

On this page

What is Veo AI? Every Veo version

Veo is the name of Google DeepMind's text- and image-to-video models. People search for "Veo AI" to mean any of them; this is how they line up:

  • Veo (May 2024, Google I/O) — the first version, 1080p video from text.
  • Veo 2 (December 2024) — better physics and camera control, still silent.
  • Veo 3 and Veo 3 Fast (May 2025) — the first Veo with dialogue, sound effects and music generated with the picture. Both run on Kenerate.
  • Veo 3.1 and Veo 3.1 Fast (October 2025) — up to 3 reference images, first and last frame, extend, and later 9:16 and 4K. Both run on Kenerate.
  • After Veo — Google's newest video model is Gemini Omni Flash (May 2026), also in Kenerate's studio.

Explore

Every Kenerate video tool

Generators, tools, models and guides — all in one studio.

See more of Kenerate AI in your Google resultsAdd kenerateai.com as a preferred source — Google shows more from your preferred sources in Top Stories and AI answers.

Keep going

More from Kenerate

By Last updated and reviewed

Sources: Kenerate video studio · Google — Veo (Gemini API docs) · Google Developers — Introducing Veo 3.1 · Google — Gemini Omni · Gemini Apps Help — video generation · Google — Generative AI prohibited use policy

Try Veo 3.1 on Kenerate

One studio for images and video.

Try Veo 3.1

Tried it? Tell us how it went