Google’s AI video generator gets better editing and more audio

Google is making videos created with AI filmmaking tool Flow even more realistic and harder to identify as AI-generated at first glance. The company announced Wednesday that users can add and edit shadows and lighting to their AI videos. Flow’s expanded editing features tie into the Veo 3.1 update, also announced Wednesday, which Google says does a better job of creating a video based on images submitted as a prompt.

Flow users will also be able to generate videos with audio using several of the tool’s new features. Users can create a video with audio based on three reference frames that the company calls “Video Ingredients.” Another feature, called “Frames to Video,” creates a video that connects a starting frame with an ending frame, accompanied by audio. The “Scene Extend” feature allows you to take the last second of a clip and add an additional generated video up to one minute long, also with generated audio.

Veo 3.1 costs the same as Veo 3, is available as part of a “paid preview” via the Gemini API for developers, and is enabled in the Gemini app.

According to Google, Flow users will soon be able to remove “anything” from a video: the tool will restructure the background and scene to make it “look like the object was never there.”