Google Released A new update to its Veo AI video generation model that can do a better job of sticking it to prompts and converting images to video. Veo 3.1 is available to try today through Google’s Gemini API and now also powers the company’s Flow video editor.
Veo 3.1 builds on the new capabilities that Google introduced with the launch of Veo 3 at Google I/O 2025. The new model offers better “prompt fidelity,” according to Google, and you should have an easier time creating videos based on image “elements” you upload with written prompts. Veo 3.1 makes it possible to convert images to video and create audio at the same time, a capability that was not available with Veo 3.
Google’s Veo 3.1 is better at generating
In Flow, Veo 3.1 supports at least one new feature that gives you finer control over the videos you create. What Google calls “frames from video,” Flow lets you upload a first and last frame and then creates video in between. Adobe Firefly, which is powered by Veo 3, offers a similar feature, but Flow will be able to turn it off and produce audio at the same time. Those added audio capabilities will also apply to the video editor’s ability to stretch clips and insert objects into existing footage.
Based on samples shared by Google, videos created with Veo 3.1 still have an odd quality that seems to vary widely depending on the prompt and subject. While it lacks some of the realism of OpenAI’s Sora 2, the company’s decision to make Veo more useful for people who work with videos rather than sources of social media spam is a welcome move.