Google Vids adds Gemini Omni and personal avatars

Google Vids has two new features: Gemini Omni for text-and-image video generation and editing, and personal avatars that let a user star in a clip without turning on a camera. Omni takes a natural-language prompt plus optional image references — a photo or a rough sketch — and generates a clip. Editing works the same way: describe what you want changed and Vids will swap backgrounds, fix lighting, or add effects, step by step, without starting over. Personal avatars are built from a selfie and a short voice recording; the user then types a script and the avatar delivers it. Google says avatars are "linked to a user's Google Account and are restricted to the account holder's likeness." Both features are available to Google AI Pro and Ultra subscribers and Google Workspace business customers, with avatar access limited to users 18 or older in certain regions. Every generated clip carries an invisible SynthID watermark. The post follows the February rollout of Veo 3.1 to all Vids users.