To polish your screen recording using Google Vids, you can use the built-in editing features directly in your browser (0:33–0:40). Here is how you can refine your video:

• Trim and Edit: Use the transcript trim feature to remove filler words and cut clips as easily as editing a document (0:43–0:49).
• Enhance Visuals: Add styled captions to ensure your message is clear and engaging (0:49–0:52).
• Utilize AI Tools: You can generate custom voiceovers, add video clips, and incorporate music to give your recording a more creative and professional flair (0:53–0:58).

• Install the tool: Go to the Chrome Web Store to add and pin the extension to your browser toolbar.
• Choose your mode: Click the extension icon or open , select Record, and pick between screen only, camera and screen together, camera only, or audio only.
• Select capture area: Choose to record a specific Chrome tab, an open application window, or your entire desktop screen.
• Manage audio and effects: Turn on noise cancellation, select your preferred microphone, and optionally apply background blurs or filters.
• Record and save: Hit Start recording (after the countdown), capture up to 30 minutes of footage, and click Finish to instantly save or edit your video. [1, 6, 7]

Would you like to know how to use Google Vids’ AI editing features like transcript trimming, or do you need help sharing your recording via Google Drive?

The tool highlighted in the video is Gemini Omni integrated within Google Vids.

Gemini Omni is an advanced AI model designed to enhance video creation and editing workflows. Key features include:

• Conversational Editing: It allows users to generate or edit high-quality video clips using simple text prompts.
• Multimodal Capabilities: The model can process various inputs, such as text, images, audio, and existing video, to create new content.
• Integration: It is built directly into Google Vids, enabling a more streamlined experience for professional video production and scaling content creation.

Key Editing Capabilities

• Restyling & Lighting: Change the lighting to resemble a specific time of day or restyle the footage (e.g., anime or a specific comic book look).
• Object Manipulation: Add, remove, or swap elements in a scene, like replacing background cars with buses.
• Motion Graphics & Subtitles: Instruct the app to add animated subtitles or dynamic motion graphics suitable for short-form platforms like Instagram Reels or TikTok.
• Reference Images: Upload a specific reference image (like a classical art style) and tell the AI to re-edit your video to match its aesthetics.
• Personal Avatars: Generate hyper-realistic AI avatars that look and sound like you using just a single selfie and a short voice recording. [1, 6]

How to Get Started

Could you tell me what kind of video you are working on (e.g., a corporate presentation or a social media reel) so I can help you craft the perfect prompts for Gemini Omni?

• Navigate to Likeness Settings: Open the Gemini app (or navigate to gemini.google.com) and go to the Personal avatar settings. [1, 2]

• Scan Your Face: Follow the on-screen instructions to take a short selfie video, turning your head slowly so the model can map your face from multiple angles. [1, 2]

• Record Your Voice: You will be prompted to read a random series of numbers aloud. This acts as a biometric handshake to ensure authenticity and prevent unauthorized deepfakes. [1, 2, 3, 4]

• Save Your Avatar: Once processed, your digital likeness will be securely linked to your Google Account. [1, 2]

• Tag Your Likeness: In the Gemini chat prompt bar, tap Add files, select Avatar, or simply type @[your Google username] (or @me) to summon your character. [1, 2]

• Describe the Prompt: Type out exactly what you want the video to show. For example, “@me presenting our new product launch in a modern studio” or “@me walking through a rainy city in a trench coat.”

• Generate: Hit submit and Gemini Omni will render a highly realistic, roughly 10-second video clip complete with native ambient audio and realistic lighting. [1, 2]

• Open a new project in Google Vids.

• From the video generation interface, select your avatar from the character picker.

• Type the script or the scenario you want to portray, and the AI will generate the sequence featuring your face and synthesized voice. [1, 2, 3, 4, 5]

• Admins: There is no admin control for this feature.
• End users: Visit the Help Center to learn more about creating voiceovers with AI and using AI avatars in Google Vids.

• Rapid Release and Scheduled Release domains: Full rollout (1–3 days for feature visibility) started on July 15, 2026

• Business: Business Starter, Standard, and Plus
• Enterprise: Enterprise Starter, Standard, and Plus
• Education: Education Plus
• Consumer: All users with personal Google accounts, including Google AI Pro and Ultra
• Other Editions: Enterprise Essentials, and Enterprise Essentials Plus; Nonprofits; Individual
• Education Add-ons: Teaching and Learning; Google AI Pro for Education
• Other Add-ons: AI Expanded Access*

• Google Docs Editors Help: Use AI avatars in Google Vids
• Google Docs Editors Help: Create voiceovers with AI in Google Vids

Option 1: Directing Manually with Bracket Tags

Option 2: Using the AI Auto-Tag Feature