HeadsUpAI

Google Gemini Launches Persistent AI Avatars to Generate Personalized Video Content

Google launched persistent AI avatars for Gemini Omni, enabling users to build digital versions of themselves. These avatars are stored within the Gemini app to streamline video production. The feature uses the Gemini Omni model to handle the multimodal synthesis required for realistic motion.
Availability
Google AI Plus, Pro, and Ultra subscribers
Verification
SynthID digital watermarking
Platforms
Web and mobile app
Persistence
Avatars are stored for reuse
Model
Gemini Omni

This update positions Google as a direct competitor to platforms like HeyGen, which introduced a high-fidelity programmatic video API. By integrating digital twins into a horizontal assistant, Google is lowering the barrier for creators to scale their on-camera presence. Every video includes an imperceptible SynthID watermark to ensure AI-generated content remains verifiable.

You can now use these avatars to generate marketing clips by providing text prompts to the Gemini app. Access is limited to paid subscribers on the Google AI Plus, Pro, and Ultra tiers, recently restructured for high-compute workflows, following the launch of Google Flow's autonomous agent. Both web and mobile apps are available immediately.

View the full update on blog.google
Google Gemini
Google Gemini
@GeminiApp
X

Create videos with your own voice and likeness using avatars with Gemini Omni. When you create an avatar, you have an AI digital version of yourself so you can easily generate videos that look and sound like you. No need to upload your image every time.

63retweets521likes
View on X

Still wondering? A few quick answers below.

Gemini Omni avatars are AI-generated digital versions of a user's own voice and likeness. Once created, these persistent digital twins allow you to generate personalized videos that look and sound like you without needing to upload new reference images or audio samples for every individual video session.

The ability to create and use AI avatars is currently rolling out to all paid subscribers of Google's premium AI tiers. This includes users with active Google AI Plus, Pro, and Ultra subscriptions. The feature is accessible through the Gemini web interface and the official mobile app on supported devices.

Every video created using the Gemini Omni avatar system includes SynthID, which is an imperceptible digital watermark embedded directly into the media. This technology allows platforms and users to verify that the content was generated by AI through the Gemini app, providing transparency for digital likenesses online.

No, you do not need to upload your image for every video. Once you have created your initial AI avatar, Gemini Omni stores your digital likeness and voice profile. This persistence allows you to generate multiple new videos easily by simply providing text instructions or prompts to the assistant.

Share this update