Google has released Veo 3.1, the latest version of its AI-powered video generation model, offering enhanced creative and technical features that improve narrative control, audio integration, and video realism. Available through Google’s Flow app, Gemini API, and soon Vertex AI, Veo 3.1 supports multiple input types including text, images, and clips, alongside new editing tools like frame interpolation and scene extension. The update allows users to generate longer videos with synchronized audio natively, streamlining workflows especially for enterprises creating marketing, training, and digital content. Pricing remains consistent with previous models, with no free tier and charges based on successful video generation. The model outputs video in 720p or 1080p at 24fps with flexible duration up to over two minutes using the extend feature. Early user feedback is mixed, praising new functionalities but noting areas like voice customization and consistent character representation need improvement compared to competitors such as OpenAI’s Sora 2. Google emphasizes safety with embedded SynthID watermarks and moderation controls, catering to regulated industries. Veo 3.1 signals a strong move toward scalable, customizable AI video tools for creative professionals and enterprises alike.
Back
