Google DeepMind has launched Veo 3.1, an upgraded generative video model designed for enhanced creative control and improved audio features within its Flow filmmaking tool. Available via the Gemini API and Vertex AI, Veo 3.1 addresses developer needs, building on the 275 million videos generated since Veo’s initial release. This update enhances adherence to prompts and audiovisual quality, providing richer native audio, including synchronized sound effects and dialogue.
The Flow tool now includes precision editing capabilities, such as the ability to insert new elements or remove undesired objects, enhancing post-production workflows. Key features like Ingredients for Video, Frames to Video, and Extend enable businesses to generate consistent marketing clips and automate storyboarding. Priced similarly to its predecessor, Veo 3.1 positions itself as a robust solution for high-volume production, emphasizing Google’s move toward production-ready content creation tailored for B2B applications.
Source link
