Google upgrades AI video generator with smarter editing, audio tools

Google has recently released Veo 3.1, an update to its state-of-the-art AI filmmaking tool Flow, making videos even more realistic and harder to identify as AI-generated at first sight.

The company announced on Wednesday that this new feature brings significant enhancements in both editing and acoustic properties.

The expanded editing features in Flow are tied to the Veo 3.1 update, and Google has confirmed that the model now produces better results when generating video from images submitted as a prompt.

How can users generate videos by using the distinctive new features?

Flow users will be able to develop videos with audio using several tools with distinctive new features.

Users can make a video with audio based on three reference images - a feature that the company calls “Ingredients to Video”.

Another feature, “Frames to Video” creates a video that smoothly transitions between a starting image and an ending image, complete with concurrent audio.

The “Scene Extension” feature specifically lets you take the final second of a clip and extend it with an additional generated video, up to a minute in length, complete with generated audio.

It has been observed that Veo 3.1 costs the same as Veo 3, and is available as a part of “paid preview” through the Gemini API to developers and is enabled in the Gemini app.

Flow users will be soon able to remove anything from a video; the system will revamp the background to make it look as though the object was never there.

This new move coupled with the introduction of richer and synchronized audio features, delivers a significant leap in functionality.