At its annual developer conference, Google I/O 2025, the tech giant introduced Veo 3, the latest version of its AI-powered video generation model. This update marks a significant advancement by adding audio generation, enabling users to create realistic videos complete with synchronized soundtracks and dialogue directly from text prompts.
Veo 3 builds on its predecessor with improved realism, better understanding of complex prompts, and features like camera control and object removal—giving creators more flexibility and control during video editing.
Alongside Veo 3, Google also launched Flow, a new AI filmmaking app. Flow allows users to generate short, eight-second video clips from text or image inputs, which can be stitched together using built-in scene-building tools to create full stories.
These launches are part of Google’s broader push to embed generative AI into its ecosystem. Other major announcements at I/O 2025 included Imagen 4, a next-gen image generation model, and Gemini 2.5 Pro, an enhanced large language model with improved reasoning for complex tasks.
Veo 3 and Flow are now available to U.S. users through Google’s AI Pro and AI Ultra subscription plans, offering different tiers of access and usage. These innovations highlight Google’s commitment to pushing the boundaries of what generative AI can do for content creators and developers.
Comments
Post a Comment