Veo 3.1
Notable release: A meaningful new model: a new size or version, or a strong free-to-download model from a known lab.
Key facts
- Released
- Oct 15, 2025
- What it does
- Sees images: Understands pictures, screenshots and charts you share with it.Makes video: Creates video clips from a description or a picture.Makes sound: Creates speech, music or other audio.
View moreView less
- How
- For developers, through an API
- Announced as
- “Introducing Veo 3.1 and advanced capabilities in Flow”
From trckr's archive of releases before it started watching. Date and details from Epoch AI's database of AI models (CC BY 4.0).
How it scores
From independent testers, never the lab's own claims.
- Videos, by people's votes#14 of 46
- Gemini Omni 1.2 Flash1,540
- 2Gemini Omni 1.1 Flash1,513
- 13Sora 2 Pro1,367
- 14Veo 3.11,363
- 15Veo 3.1 Fast1,361
Source: LMArena · LMArena text-to-video
Compare Veo 3.1 with
It came out 76 days after Veo 3 Fast, the lab's previous model.
The details
Get alerts like this the moment they happen.
From Google and every other major lab.
Free, no account needed. Push, Telegram, Discord, email or RSS.