Google Vids just became a far more capable video maker with Gemini Omni

Google Vids has received a major AI overhaul with Gemini Omni, enabling video creation and editing through natural language prompts. The update also introduces personal AI avatars generated from a selfie and voice recording, with safety measures including age restrictions and invisible SynthID watermarks. Users can now control AI narration with bracketed commands for emotions and pacing.

Affiliate links on Android Authority may earn us a commission. Learn more. https://www.androidauthority.com/external-links/ Google Vids just became a far more capable video maker with Gemini Omni Jul 16, 2026 — 10:49 PM ET - Google Vids gets a major AI overhaul with Gemini Omni, making video creation and editing as simple as describing what you want in plain language. - You can create a personal AI avatar by uploading a single selfie and a short voice recording. - To prevent misuse, personal avatars are restricted to the account holder’s likeness. Editing a video typically involves a long process of fixing lighting, changing backgrounds, or endless retakes to get the perfect shot. Now, Google is rewriting the playbook with massive Google Vids https://www.androidauthority.com/google-vids-latest-upgrades-3654492/ updates that do the AI work for you. The biggest new addition to Vids is Gemini Omni, Google’s multimodal video generation model first shown off at I/O 2026 https://www.androidauthority.com/google-gemini-omni-video-model-youtube-shorts-3668469/ . With Vids, you can now create or edit videos from natural language prompts, whether you’re starting from scratch with text and images or editing an existing clip, per Google’s blog post https://blog.google/products-and-platforms/products/workspace/gemini-omni-personal-avatars/ . You can skip the timeline and just tell Gemini to change a background, improve lighting, or add visual effects with conversational prompts. Google is also adding personal avatars to Vids, letting you appear in videos without stepping in front of a camera. The feature was previously made available to all US Google account holders https://www.androidauthority.com/google-vids-ai-avatars-free-for-everyone-us-3678613/ . After uploading a selfie and recording a short voice sample, Vids creates a digital version of you that can deliver any script you type. You can only use the feature with your Google account and image, and as a safety measure, Google is limiting it to users over 18 in supported regions. Additionally, every clip made in AI has an invisible watermark, called a SynthID, that can be used to verify its source. Google is also giving users much more granular control over the AI narration. Now you can add bracketed commands like “ excitedly ” or other prompts directly in your script to change an avatar’s emotions, pacing, or even start-up sound effects, the company said https://workspaceupdates.googleblog.com/2026/06/easily-steer-ai-voiceover-and-avatar-speaking-with-emotions-pacing-and-sound-effects.html . When you type an opening bracket, Google Vids suggests available steering tags, and if you don’t want to add them manually, the new “Apply audio tags” option can automatically insert appropriate cues throughout your script. The voice-steering tools are now available in both Rapid Release and Scheduled Release domains, with support for Google Workspace Business and Enterprise editions, Education Plus, nonprofit organizations, individual users, and personal Google accounts, including Google AI Pro and Ultra subscribers. Administrators don’t need to enable anything, as the feature is available automatically. Thank you for being part of our community. Read our Comment Policy https://www.androidauthority.com/android-authority-comment-policy/ before posting.