Google releases Veo 3.1 on Flow with video editing

Google has announced the release of Veo 3.1, the latest version of its AI-powered video generation model, now available within its Flow filmmaking tool. This update introduces richer audio generation, greater narrative control, and improved realism in video outputs, addressing demand from creators for more granular artistic control and robust audio support.

Veo 3.1 brings enhancements to features like "Ingredients to Video," "Frames to Video," and "Extend," offering users the ability to craft scenes using multiple references, generate seamless video transitions, and extend shots beyond a minute—all now with integrated, high-quality audio. New editing capabilities allow users to insert new elements or remove unwanted objects from scenes, with Flow handling complex details like shadows and lighting for natural results.

The Veo 3.1 model is accessible through multiple channels: it powers Flow for content creators, is available to developers via the Gemini API, and can be used by enterprise customers through Vertex AI and the Gemini app. This broad availability ensures both individuals and organizations can leverage Veo’s advanced video generation capabilities.

Compared to previous versions, Veo 3.1 offers stronger adherence to user prompts and superior audiovisual quality, setting a new benchmark for AI-driven filmmaking tools. Early feedback from creators highlights the improved control and realism, positioning Flow and Veo 3.1 as leading tools for those seeking sophisticated video storytelling powered by artificial intelligence.

Google DeepMind, the division responsible for Veo, continues to focus on advancing generative AI for creative applications. With Flow and Veo 3.1, Google aims to empower a wide range of users, from independent filmmakers to enterprise clients, by providing cutting-edge tools for video creation and editing directly within its platforms.

Source