Start from words only. You describe the video and the AI makes it from scratch.

Describe the video in your own words, as if telling a friend: who is in it, what they do, where it happens and what you hear. More detail gets you closer to what you imagine.

Aspect Ratio

The shape of the result. 16:9 is wide, like YouTube or a TV. 9:16 is tall, like TikTok or phone stories. 1:1 is square, like an Instagram post.

Duration

How many seconds long the video will be. Longer videos cost more credits.

Veo 3.1 1
Veo 3.1 2
Veo 3.1 3
Veo 3.1 4
Veo 3.1 5
Veo 3.1 6
Veo 3.1 7
Veo 3.1 8
Veo 3.1 9

Google · Text & image to video

Veo 3.1 AI Video Generator

Veo 3.1 is Google DeepMind's video model for 1080p clips with sound: dialogue, effects and ambience generated with the picture. Write the shot like a director, or start from a first and last frame, and Veo 3.1 renders it.

Real results

Discover What Veo 3.1 Can Create

Cinematic 1080p shots with sound, each made from one prompt with Veo 3.1. Unedited outputs from this page, with the prompt for each. The input photos are AI-generated people, not real ones.

Kitchen scene · Veo 3.1

Close-up, slow dolly in: a chef flips vegetables in a flaming wok in a busy restaurant kitchen at night, steam and orange light. Sound: sizzling, clattering pans, distant orders being called.

Key Features of Veo 3.1

Veo 3.1 is Google DeepMind's video model, released in October 2025 as an update to Veo 3, the model that made video with matching sound mainstream. Veo 3.1 improved realism, prompt adherence and audio, and it is the most capable video model on ImageFX.

01 / 05

Sound That Matches the Picture

Dialogue, sound effects and ambience are generated together with the video, so a door slam lands on the frame where the door closes. Footsteps, room tone and music fit what is on screen. Describe the sound in your prompt and Veo 3.1 adds it to the clip.

Try Veo 3.1 Now
Prompt · Close-up, slow dolly in: a chef flips vegetables in a flaming wok in a busy restaurant kitchen at night, steam and orange light. Sound: sizzling, clattering pans, distant orders being called.

02 / 05

Characters That Speak Your Lines

Put dialogue in quotes and say who speaks it, and Veo 3.1 has the character say it with lip movement that follows. That makes short ads and skits possible from a single prompt, without filming or recording anyone.

Make a Talking Video with Veo 3.1
Prompt · Medium shot of a tired office worker at a desk; he sips coffee and his eyes widen. He says, "Okay. Now I can do Mondays." Bright office light, upbeat ending.

03 / 05

Cinematic Camera Language

Veo 3.1 reads prompts like a director's notes. It understands shot types and moves such as close-up, dolly in, crane shot, handheld and rack focus. Name the shot, the action over time and the sound, and keep each prompt to one continuous shot.

Direct a Shot with Veo 3.1
Prompt · Wide aerial shot slowly tracking over a misty pine forest at sunrise, birds rising from the trees. Sound: wind, birdsong, soft ambient music.

04 / 05

Realistic Physics and Light

Water, cloth, hair and reflections behave plausibly, one of the main reasons Veo leads many video comparisons. Veo 3.1 renders at 1080p on ImageFX, in widescreen or vertical.

Try Veo 3.1 Now
Prompt · Handheld shot following a woman with a red umbrella across a rainy crosswalk at night, neon reflections. Sound: rain on the umbrella, car horns, footsteps in puddles.

05 / 05

Start From a First and Last Frame

Besides text-to-video, Veo 3.1 can open on an image you upload, or travel from a first frame to a last frame you choose. Use it to bring a product shot or a still to life, or to fix exactly where a shot ends.

Animate a Photo with Veo 3.1
Prompt · The camera glides from the closed shop door to the lit window display as the sign flips to Open. Morning light. Sound: a door bell, street ambience.

How to Use Veo 3.1 on ImageFX

  1. Pick Text or Image to Video

    Open the Veo 3.1 generator at the top of this page. Write from scratch on Text to Video, or switch to Image to Video and upload a first frame, or a first and last frame.

  2. Write It Like a Shot Description

    Give the subject and action, the setting, the camera move and the light, then the sound and any dialogue in quotes. Choose widescreen or vertical and the length; a negative prompt is there for anything you want left out.

  3. Generate and Download

    Click Generate, watch the clip beside the form and download the 1080p MP4 with its sound. Every video is saved to your account.

A Veo 3.1 run costs 40–80 credits depending on length; the Generate button shows the price first, and a failed run costs nothing. See plans and credit packs

FAQs About Veo 3.1

What is Veo 3.1?

Veo 3.1 is Google DeepMind's video model, released in October 2025 as an update to Veo 3. It generates video together with matching sound, including dialogue, and improved realism and prompt adherence over Veo 3.

Does Veo 3.1 generate audio?

Yes. Every Veo 3.1 clip on ImageFX comes with generated sound: ambience, effects and any dialogue you write. Sound is always on, so mute it in your editor if you only need the picture.

Can Veo 3.1 make characters speak?

Yes. Write the line in quotes and say who speaks it, and the character says it with matching lip movement.

What resolution is Veo 3.1 on ImageFX?

1080p, in widescreen 16:9 or vertical 9:16. Veo 3.1 doesn't make square video.

How long can a Veo 3.1 video be?

Up to 8 seconds per clip. For longer scenes, generate several shots and edit them together. The generator shows each length's price before you run, and credits are refunded if a run fails.

Can Veo 3.1 use reference images?

Google's API lets Veo 3.1 follow reference images, but that isn't on ImageFX. Here you can start from text, a first frame, or a first and last frame.

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

Veo 3.1 Fast is the lower-cost, quicker variant of the same model generation, with slightly less fidelity. Draft on Veo 3.1 Fast and use Veo 3.1 for the take you will publish.

Try Veo 3.1 on ImageFX

Write a shot with camera moves, dialogue and sound, and get a 1080p clip from Google DeepMind's top video model.

Create with Veo 3.1