Google Vids Integrates Gemini Omni for AI-Powered Conversational Video Editing

Gemini Omni powers conversational video editing in Google Vids

Gemini Omni and Conversational Editing

View this post on Instagram about google vids integrates gemini, Gemini Omni and Conversational Editing

The core of the recent Google Vids update is the integration of Gemini Omni, a multimodal AI model designed to remove the complexity from the editing process. Unlike traditional editing software, which often requires manual timeline adjustments, Gemini Omni allows users to generate and refine high-quality clips simply by writing natural language prompts. This capability facilitates a conversational editing workflow where users can make step-by-step changes to their videos, such as swapping backgrounds, fixing lighting, or adding effects, without needing to restart the generation process from scratch.

The platform’s flexibility allows for a variety of inputs. According to Google, users can start with a simple text prompt in natural language, and add image references — like a photo or a rough sketch — for more detail. The Omni model then synthesizes these various inputs to generate a video that aligns with the user’s creative vision. This integration is conceptually similar to how Google’s Nano Banana model handles image generation, providing a video-specific equivalent that allows for iterative refinement through dialogue with the AI.

Google Vids introduces personal avatars for digital likeness

Personal Avatars and Digital Likeness

In addition to the editing upgrades, Google has introduced personal avatars, a feature that enables users to create a digital version of themselves. By uploading a selfie and a voice recording, a user can generate an avatar that looks and sounds like them. This tool allows creators to appear in videos without the need to set up a camera or step in front of one. Once the digital avatar is generated, a user simply writes a script, and the AI avatar produces the video content.

This feature is designed to streamline the production of professional content, such as business presentations or marketing campaigns, which can otherwise be incredibly time-consuming. By utilizing their own likeness, users can maintain a personal touch in their communications while leveraging the efficiency of AI-generated delivery.

SynthID embeds digital watermarks into AI-generated videos

Availability and Safety Measures

These new features are currently available to specific tiers of the Google ecosystem. Access is restricted to Google AI Pro and Google AI Ultra subscribers, as well as eligible Google Workspace business customers. The rollout reflects Google’s broader effort to integrate its most advanced AI tools directly into its existing productivity platforms.

As the platform increases its capacity for AI-generated media, Google has prioritized safety and transparency. Every video produced using these new tools is embedded with SynthID, a digital watermark designed to ensure that AI-generated content can be easily identified. This measure is part of Google’s commitment to providing clear indicators for synthetic media, allowing viewers to distinguish between human-recorded footage and AI-generated outputs.

Google Vids has been building toward this level of sophistication throughout the year. In February, the company made the video creation process simpler by rolling out Veo 3.1 to all users. The addition of Gemini Omni and personal avatars now complements existing Vids functionality, such as AI presenters, screen recording, and tools that convert Slides presentations into narrated videos. By enabling users to generate, edit, and star in their own content through natural language, Google is positioning Vids as a central hub for professional video workflows, aiming to turn what were once hour-long editing projects into streamlined, prompt-based tasks.

Sources: Ei Samay, দৈনিক ইনকিলাব.