Google Vids Gets AI Avatars and Prompt-Based Video Creation Powered by Gemini

Google is expanding the capabilities of Google Vids with a major AI upgrade that makes creating videos much easier. The company has introduced two new features that allow users to generate videos using simple text prompts and even appear in them without recording themselves on camera.

The update brings AI-generated personal avatars along with support for Gemini Omni, Google’s latest multimodal AI model designed to simplify video production.

Create an AI Avatar From a Selfie

One of the headline additions is the ability to create a digital version of yourself. Instead of filming a video, users can upload a selfie and provide a short voice sample. Google then generates an AI avatar that closely resembles their appearance and speaking style.

Once created, the avatar is used to present data in videos, which makes it easier to produce content without needing cameras, microphones, or repeated takes.

Turn Ideas Into Videos With a Prompt

Google is also integrating Gemini Omni into Google Vids, allowing users to create videos simply by describing what they want.

A text prompt, combined with optional reference images, is all it needs to generate a personalized video. The system can assemble visuals, narration, and presentation elements into a finished draft, reducing the amount of manual editing required.

This makes Google Vids a more capable AI-powered video creation platform rather than just an assistant for assembling presentations.

Easier Editing With AI

The update also improves the editing experience.

Users can modify backgrounds, adjust lighting, and apply various visual enhancements after a video has been generated. Instead of recreating an entire project after spotting a mistake, edits can now be made incrementally, making the production process faster and more flexible.

More Than Just a Workplace Tool

Google Vids was originally introduced as a productivity tool for businesses, but these new features significantly broaden its capabilities.

Since the platform is integrated with Google Workspace, organizations can create training materials, onboarding videos, presentations, and internal communications featuring AI-generated presenters that match their brand’s messaging.

The addition of personal avatars also gives these videos a more conversational and engaging feel compared to traditional slide-based presentations.

Competing in the AI Video Space

Google isn’t the first company to offer AI-generated video avatars. Platforms like HeyGen and Synthesia have already established themselves in this category.

However, Google’s entry into the space could increase competition, particularly because Google Vids is already integrated into Workspace, making AI-powered video creation more accessible for existing Google users.

AI Transparency Measures

To help distinguish AI-generated content from real footage, videos created using these new features will include Google’s invisible SynthID watermark. This watermark is designed to identify AI-generated media without affecting the viewing experience.

Google also says personal avatars will be linked to the creator’s Google account. The feature will be available only in supported regions and is limited to users who are at least 18 years old.

Final Thoughts

With AI avatars, prompt-based video generation, and smarter editing tools, Google Vids is evolving beyond a business presentation tool into a more complete AI video creation platform. The latest additions make it possible to produce professional-looking videos with minimal equipment, while Google’s built-in safeguards aim to provide greater transparency around AI-generated content.