Google releases new AI video model Veo 3.1 in Flow and API: what it means for enterprises

Google releases new AI video model Veo 3.1 in Flow and API: what it means for enterprises

Google has introduced Veo 3.1, its latest AI video generation model, following considerable speculation online. This model includes various enhancements designed to improve narrative control, audio integration, and realism in video production. The updates offer increased functionality for both hobbyists and content creators using Google’s Flow application, while also targeting enterprises and developers in need of customizable video tools.

The new version features improved quality and physics, maintaining the same pricing structure as its predecessor. Notably, Veo 3.1 expands audio capabilities, allowing users to generate native audio integrated with various features like “Frames to Video” and “Ingredients to Video.” This advancement enables users to produce video with synchronized sound directly within the application, potentially streamlining content creation processes in enterprise settings.

In terms of inputs and editing, Veo 3.1 supports text prompts, images, and video clips, along with additional features such as reference images to guide output style, scene extension, and interpolation between frames. These tools are designed to provide granular control, aiding enterprises in maintaining brand consistency and meeting creative briefs.

Veo 3.1 is available through several Google platforms, including Flow, the Gemini API, and Vertex AI, allowing users to choose between graphical or programmatic environments. Currently in preview, the model operates on a paid tier similar to that of Veo 3, with standardized pricing for video generation.

Initial responses from users highlight a mix of optimism and critique, particularly in relation to its competitors. While some acknowledged improvements in audio quality and editing capabilities, concerns were raised regarding limitations in voice customization and video lengths.

Despite mixed feedback, Google reports substantial adoption, with over 275 million videos generated using various Veo models since the launch of Flow. Features like watermarks and safety filters are integrated to address privacy and copyright considerations, reflecting the company’s commitment to responsible AI use. As Google continues to refine Veo 3.1 and expand its access, its ability to address user concerns will be crucial in maintaining a competitive edge in the AI video generation market.

Source: https://venturebeat.com/ai/google-releases-new-ai-video-model-veo-3-1-in-flow-and-api-what-it-means-for

Leave a Comment

Your email address will not be published. Required fields are marked *

Scroll to Top