Google has launched Veo 3.1, the latest update to its AI video generation model, bringing significant improvements over the previous Veo 3 released in May 2025. Veo 3.1 features richer, native audio integration including synchronized dialogue, ambient sounds, and effects enhancing the realism and cinematic quality of AI-generated videos. It supports both horizontal (16:9) and vertical (9:16) aspect ratios to cater to social media content formats.
The model offers new creative capabilities, such as “Ingredients to Video,” allowing users to upload up to three reference images for consistent character and style representation. The “Insert” feature enables adding elements into existing videos with automatic lighting and shadow adjustments, while a “Remove” feature to delete objects will be launched soon. Videos can now extend up to one minute, up from the previous eight seconds, with smooth transitions between frames and enhanced texture realism.
Veo 3.1 is available through Google Flow, Gemini API, Gemini app, and Vertex AI, targeting professional creators and enterprise users. It maintains the same pricing as its predecessor, positioning itself as a high-quality cinematic tool compared to competitors like OpenAI’s Sora model, with stronger storytelling focus and longer video generation capabilities. Since the launch of Flow, more than 275 million videos have been created using Google’s Veo technology, highlighting its growing adoption in the AI video creation space.
Also Read: FSSAI restricts ‘ORS’ labeling to WHO-approved products only
