GoogleVideo
Veo 3.1
Veo 3.1: Google's Veo 3.1: realistic video with synchronized audio, from text or an image, and extendable clips.
- Popular
- Premium
At a glance
Veo 3.1 by the numbers
- 8 s Max length per generation
- 1080P Max quality
- Audio Sound generated with the picture
- 2 Aspect ratios
- 3 Ways to create
- Google Publisher
Use cases
What you can create with Veo 3.1
Interviews and dialogue
Street interviews, podcasts, two-character scenes: lines are clear and in sync.
Premium ads
A high-end spot with voice, music and effects already mixed.
Longer sequences
Chain 7-second extensions to play out a story.
Vertical formats
Native 9:16 for Reels, TikTok and Shorts.
Official demonstration
Video published by Google DeepMind.
Watch demonstrationOverview
What is Veo 3.1?
Veo 3.1 is Google DeepMind’s flagship video model, available since October 2025. Successor to Veo 3, the first mainstream model to generate native sound, it produces cinema-quality video with lip-synced dialogue, sound effects and music, in several languages.
In Havincy, Veo 3.1 generates 4, 6 or 8 second clips in 720p or 1080p, in 16:9 or 9:16, from a text or an image. It can also extend a clip by 7 seconds to build longer sequences. It is the reference when dialogue must be clear and perfectly in sync.
- Text or image to video
- Native audio
- Extend existing clips
- 4 to 8 s clips
Veo 3.1: specifications
- Publisher
- Generation modes
- text → video, image → video, and video → video
- Available durations
- 4, 6, 8 s
- Resolutions
- 720p, 1080p
- Aspect ratios
- 16:9, 9:16
- Audio
- Sound generated with the video
- Available since
- October 08, 2025
- License
- Commercial use allowed
- Cost
- View pricing
The credit price depends on your settings and is shown before every generation.
Specs taken from the publisher’s public model page. See the documentation on fal.ai
Prompt examples
Prompts to try with Veo 3.1
A neon-lit street in the rain, a cyclist rides past the camera
A close-up of ocean waves crashing on black rocks, cinematic
A cat jumps onto a sofa and stretches in warm morning light
Use cases
Compatible skills
How it works
How to create with this model
- Describe the desired result in a Havincy conversation.
- Add a reference when the style, product, or character needs to be preserved.
- Generate, then ask for a variation or improvement without starting over.
FAQ
Frequently asked questions about Veo 3.1
Is Veo 3.1 free?
No. Google offers it through paid plans; in Havincy, you use it with your credits, with no Google or Gemini subscription.
What’s the maximum duration?
Each generation is up to 8 seconds long. In Havincy, you can extend a clip 7 seconds at a time to go further.
Which languages can Veo 3.1 speak?
Veo 3.1 generates dialogue in several languages. Write the lines in quotes, in your language, in the prompt.
How much does Veo 3.1 cost in Havincy?
The credit price depends on the settings you pick (length, quality, sound, number of images) and is shown before every generation. See the Pricing page for details by plan.
More models to discover
A starting point for your next creation.
Seedance 2.5
Seedance 2.5: ByteDance's most advanced video model: text, image and multi-reference to video with native audio.
Kling 3.0 Pro
Kling 3.0 Pro: Kling's flagship: cinematic video from text or an image, with native audio and clips up to 15 s.
Seedance 2.0 Fast
Seedance 2.0 Fast: The fast Seedance 2.0: low-cost videos from text, images and references, with native audio.
Ready to create with Veo 3.1?
Describe your idea in Havincy, then refine the result in the conversation.