- Google has announced the integration of its multimodal video generation AI model, “Gemini Omni,” into its AI video editing service, “Google Vids.”
- The integration of “Gemini Omni” into “Google Vids” makes the generation and editing of high-quality videos easier than ever before.
- Available for “Google AI Pro” and “Google AI Ultra” members, as well as “Google Workspace” business account users.
On Thursday, July 16, 2026 (local time), Google announced that it is integrating its multimodal video generation AI model, “Gemini Omni,” into the AI video editing service “Google Vids.”
“Gemini Omni” is a video generation AI model that allows users to create videos that match their vision by combining short natural language text prompts with images such as photos or rough sketches. With the arrival of “Gemini Omni” in “Google Vids,” the process of generating and editing high-quality videos becomes easier than ever before.
A major feature of the “Gemini Omni” integration in “Google Vids” is the ability to edit videos step-by-step. Users can provide instructions using everyday language for tasks such as “changing the background,” “adjusting lighting,” or “adding effects.” Note that all video clips generated by “Gemini Omni” will include “SynthID,” an invisible digital watermark.
“Google Vids” with “Gemini Omni” is available for “Google AI Pro” and “Google AI Ultra” members, as well as for “Google Workspace” business accounts.
Source：Google（https://blog.google/products-and-platforms/products/workspace/gemini-omni-personal-avatars/）