Google has announced a major upgrade for its AI video generation tool, introducing Veo 3.1 into Flow to bring more refined editing, richer audio support, and finer narrative control.
Flow was launched earlier this year as a creative filmmaking tool powered by Veo, and since then users have produced more than 275 million videos using it according to Google.
With Veo 3.1, Google is responding to feedback from creators who want stronger control over storytelling, more precise edits, and enhanced audio across all features. With the new version, audio is now integrated into existing features that previously focused on visuals. That means tools like Ingredients to Video, Frames to Video, and Extend now support generated audio tracks that match the visuals.
In “Ingredients to Video,” users begin with multiple reference images to define characters, objects, and aesthetic style. With Veo 3.1, the system now weaves in audio that aligns with the visual composition.
In “Frames to Video,” creators specify a starting and ending image and the tool fills in intermediate frames to animate a smooth transition—now with matching audio behavior. The “Extend” feature, which lets users elongate sequences seamlessly by extending from the final frame of a clip, also gains audio continuity so extended scenes retain immersion.
Beyond adding audio support, Veo 3.1 introduces finer scene editing within Flow. The update offers an Insert tool to introduce new elements, such as extra characters, objects, or visual motifs, while maintaining lighting, shadows, and environment consistency. The system is also preparing a removal tool, allowing creators to eliminate unwanted objects or characters and reconstruct the backdrop realistically.
Google indicates that Veo 3.1 demonstrates better prompt adherence and superior audiovisual quality when translating images into video. The goal is to increase realism and texture in videos generated from static inputs.
The new capabilities are not limited to Flow alone. Developers can access Veo 3.1 through the Gemini API, while enterprise users will find it available in Vertex AI. The Gemini app and broader Google AI infrastructure also support these enhancements. Some tools such as “Add object” and “Remove object” are noted as not yet enabled in the APIs.
Want to see more of our stories on Google?
P.S. Want to keep this site truly independent? Support us by buying us a beer, treating us to a coffee, or shopping through Amazon here. Links in this post are affiliate links, so we earn a tiny commission at no charge to you. Thanks for supporting independent Canadian media!
Only a pro customers can access and use Veo.