Google Brings Personal Avatars With Your Face and Voice to Gemini

Google has introduced Personal Avatars in the Gemini app, a feature that lets users generate AI images and videos featuring their own face and voice. Avatars can also be shared with friends, family members and colleagues, who can then use them to make their own content.

The feature relies on the Nano Banana model for images and Gemini Omni for video. Users can appear in the results themselves and combine their avatar with those of other people who have shared theirs with them.

How to create and share an avatar

Setup starts on a computer, where the user begins the avatar creation process and scans a QR code to continue on a phone or tablet. The face and voice are then recorded. Google advises keeping the face clearly visible throughout and choosing a quiet, well-lit spot.

Sharing works through invitations sent to email addresses via Gmail. Recipients cannot use an avatar right away; they must accept the invitation first. The owner manages access in Gemini settings, either by setting an expiry date for sharing or by revoking permission entirely. After revocation, the other person can no longer create new content with the avatar, but images and videos already made remain available.

Availability and limits

Personal Avatars are open to users aged 18 and over with a personal Google account. For now the feature supports English only and is not available in the United Kingdom, the European Economic Area or Switzerland. Creating videos with avatars requires a Google AI subscription plan.

An avatar can be deleted from Google account settings, which also removes the associated face image and voice recordings. Anyone who wants to use the feature again must record a new avatar. Deleting an avatar does not remove images or videos that were already created or published with it.

The controls over who can use an avatar, and for how long, are central to the design, as the feature puts a person's likeness and voice into content that others can generate.