Google has launched a new Veo 3.1 video model with improved audio output, detailed editing controls and better image-to-video output. Veo 3.1 is said to build on the May release of Veo 3 and produce more realistic clips and better adapt to tooltips.
According to Google, the model allows users to add objects to the video and blend in with the style of the clip. Users will soon be able to remove an existing object from a video in Flow as well.
Veo 3 already has editing features such as adding reference images for character guidance, sharing the first and last frame to generate a clip using artificial intelligence, and the ability to augment existing video based on the last few frames. In Veo 3.1, Google is adding audio to all of these features to make your clips more vivid.
The company implements the model in its Flow video editor, Gemini app, and Vertex and Gemini APIs. Since Flow's May launch, users are said to have shot more than 275 million videos on the app.
