Google adds image‑to‑video capability to its Gemini app this week, powered by the advanced VEO 3 model. Now, Pro and Ultra subscribers can animate still photos into short video clips with sound and motion.
What’s New?
Previously, VEO 3 offered only text‑to‑video functionality. It generated up to 8‑second clips with realistic visuals and synced audio like dialogue, ambient noise, and music ([Wikipedia][3]).
Now, users can upload an image, describe desired action or audio, and let VEO 3 animate it. The result is a short video—complete with background noise, sound effects, and even dialogue..
Who Can Use It?
The feature is available to Gemini Pro and Ultra subscribers. Initially on the web, it will roll out to mobile versions soon. It’s live in 150+ countries and territories
How Good Is It?
VEO 3 is DeepMind’s third‑gen model. It handles real‑world physics, produces smooth lip‑syncing, and captures detailed scene context. Critics say its videos “are scary good” and hard to distinguish from human‑made clips.
Why It Matters
- Creative boost: Enables non‑experts and marketers to produce cinematic clips from photos.
- Market lead: Google joins other platforms like OpenAI’s Sora, Microsoft Copilot’s Agent Store, and Vertex AI’s video tools in offering AI video generation.
- Ethical concerns: With realism comes risk—deepfakes, misinformation, and unsettled copyright remain issues
Final Take
Google’s expansion of VEO 3 to image‑to‑video makes Gemini a mini film studio in your pocket. But the uncanny realism also elevates ethical stakes. Still, for content creators, it’s a major leap forward.
Related>>AWS Agent Marketplace Launch to Feature Anthropic Partner
