Veo 3.1
Google's Veo 3.1 turns text or images into video with native synchronized audio, up to 4K.
Made with Veo 3.1
Sample outputs. Open in Studio to generate your own.
Where Veo 3.1 shines
Text to Video
Write a prompt and Veo 3.1 generates a complete clip with synchronized dialogue, sound effects, and ambient audio.
Animate a Still
Upload one image and the model brings it to life as motion video in 16:9 or 9:16.
Frame Transitions
Provide two images as the first and last frame to direct a controlled transition between two shots.
Strengths
- Handles both text-to-video and image-to-video from one model
- Generates native synchronized audio with dialogue, sound effects, and ambient sound alongside the video
- Outputs up to 4K resolution
- Three tiers (Lite, Fast, Quality) to balance speed and cost against fidelity
- Image-to-video supports one image to animate or two images for first-and-last-frame control
- Works in both landscape 16:9 and portrait 9:16
Trade-offs
- Only two aspect ratios are offered, 16:9 and 9:16, with no square or other ratios
- Image-to-video requires uploading reference image(s), and no more than two are accepted
- Output duration is not user-selectable in this configuration
- Audio is described by Google as an experimental feature and may be unavailable on some videos
At a glance
About Veo 3.1
Veo 3.1 is Google DeepMind's video generation model, available on HexGen for both text-to-video and image-to-video work. Describe a scene in words or hand it a reference image, and it produces a finished clip complete with native synchronized audio, including dialogue, sound effects, and ambient sound generated alongside the picture.
The model outputs up to 4K resolution and supports both landscape 16:9 and portrait 9:16 framing, so the same idea can be shaped for a widescreen edit or a vertical feed. Image-to-video accepts a single image to animate, or two images used as the first and last frame for a controlled transition from one shot to another.
Three tiers, Lite, Fast, and Quality, let you trade speed and cost against fidelity, so quick drafts and polished final renders both have a home. Pricing is a flat per-video rate set by the tier you pick crossed with the output resolution, which keeps the cost of a clip predictable before you hit generate.
Starting points
Copy, tweak, and run. Good prompts get you most of the way there.
A barista steam-frothing milk in a sunlit cafe, close-up on the cup, with the hiss of the steam wand and quiet morning chatter in the background. 16:9, 4K.
Animate this photo of a still harbor at dusk: gentle water ripples, a slow drifting boat, and the soft call of distant gulls. 9:16.
Transition from an empty stage to the same stage filled with light and a single dancer mid-spin, using the two reference images as first and last frame.
Pay only for what you render. 1 USD = 1,000 HGcoins. HGcoins never expire and failed runs refund automatically.
Veo 3.1 vs other models
Veo 3.1 sits at the high end of HexGen's video lineup, with native audio and 4K output. Here is how it lines up against two other video models in the catalog.
| Model | Quality | Speed | Cost | Choose it when |
|---|---|---|---|---|
Veo 3.1 This Google | Best | Fast | Higher cost | Pick Veo 3.1 when you want the highest fidelity with native synchronized audio and up to 4K, and you can choose a tier to manage cost. |
Kuaishou | Best | Fast | Higher cost | A strong Kuaishou alternative for high-end video generation. |
ByteDance | Great | Fastest | Mid cost | A ByteDance option when speed and lower cost matter more than maximum fidelity. |
Related models
Frequently asked questions
It generates video from a text prompt or from reference images, producing clips up to 4K with native synchronized audio that includes dialogue, sound effects, and ambient sound.