Skip to main content
GoogleVideo model

Veo 3.1

Google DeepMind's video model for short, photoreal shots with sound, up to 4K.

Build with Veo 3.1

Each clip is one prompt, run on Veo 3.1 in Runable.

Veo 3.1 on Runable

  • Up to 4K

    Render at 720p, 1080p or 4K, at 24 frames a second.

  • Start from a photo

    Animate your image as the first frame of the shot.

  • No Google Cloud account

    Runs on your Runable credits, next to other video models.

How to use Veo 3.1 on Runable

  1. Select Veo 3.1

    Start a task on Runable and pick Veo 3.1 in the model menu.

  2. Describe the shot

    Type the scene, or add images and clips for it to follow.

  3. Download the video

    Refine by chatting, then download the clip or cut it into an edit.

One prompt, finished work

Real results from single Runable tasks. Pick one to watch it.

Made on Runable with Veo 3.1
Close-up of an elderly man at a rain-streaked cafe window, steam rising from his cup. He looks up and speaks softly. Photoreal, natural skin texture.
top output resolution
4K
longest clip in one pass
8s
reference images per shot
3
turn to build
Your

Why choose Veo 3.1

  • True-to-life texture

    Google says it captures true-to-life textures, more real than Veo 3.

  • Sound included

    Conversations and sound effects generated with the picture.

  • Better image-to-video

    Animates your photo with stronger prompt following than Veo 3.

  • Consistent characters

    Up to 3 reference images keep a person, object or place the same.

  • Sharp 1080p and 4K

    Google’s upscaling gives clean footage for edits and big screens.

  • Vertical or wide

    Native 9:16 for Shorts and Reels, or 16:9.

Veo 3.1 specs

Maker
Google (Google DeepMind)
Released
October 15, 2025
Clip length
4, 6 or 8 seconds; 8 with reference images
Resolution
720p, 1080p or 4K
Frame rate
24 fps
Aspect ratios
16:9, 9:16
Inputs
Text, a first frame, or reference images
Audio
Optional, generated with the video
Specs are for Veo 3.1 on Runable, which runs Google’s generally available model on Vertex AI. Google’s own tools add scene extension, first-and-last-frame transitions and the faster Veo 3.1 Fast. Google lists English as the prompt language. On Runable you use your plan’s credits instead of a Google Cloud or Gemini subscription.

The only AI agent you need

Compare plansHelp

Need SSO, data localization, premium support, onboarding assistance? Contact Sales

Veo 3.1 FAQs

Veo 3.1 is Google’s video generation model, made by Google DeepMind. It launched on October 15, 2025, with richer audio, more narrative control and more realistic results than Veo 3.

Sources: Google: Introducing Veo 3.1 and advanced capabilities in Flow · Google for Developers: Introducing Veo 3.1 in the Gemini API · Google: Veo 3.1 Ingredients to Video, 1080p and 4K · Google Cloud: Veo 3.1 model specs

More AI models on Runable

Put Veo 3.1 to work

Describe the job. Runable runs it on Veo 3.1 and ships the result.