Google Vids, Google's video creation app, has gained a feature that reads a document and turns it into a summary video. Beyond Google Docs, it accepts PDF and Word files, and the AI drafts a script from the text, then adds narration and visuals to produce a single video. Google announced the feature in its Workspace updates on September 2, 2026 (US time). Organizations on the Rapid Release track can use it already, while those on Scheduled Release will see it appear gradually from September 5 over a period of up to 15 days. Individual subscribers to Google AI Plus, Pro and Ultra are also covered.
Turning long documents from something you read into something you watch
The goal of the feature is easy to grasp: take a long, text-heavy file and turn it into something that can be absorbed quickly. Google lists catching up on training material, reviewing meeting notes and going through lengthy documentation or reports as the intended use cases. The AI pulls out the key points of the uploaded file and packages them as a video with visuals and audio, so that getting the gist of a document takes less effort.
Supported inputs are Google Docs plus .doc, .docx and .pdf files. You can pick a file stored in Google Drive or upload one from your computer. Direct support for Word documents and PDFs should prove useful when dealing with material received from outside the organization or older documents that started life on paper.
The workflow begins in the File menu of Vids. Google's Help Center describes the entry under the name Convert Docs. Once you select a file and move on, the AI analyzes the document and generates a script. The script is split into one scene per section of the document, and you can edit the content at this stage.
On the script screen you can delete entire sections or rewrite the text inside a scene directly. This is also where you choose the AI voice that will narrate the video. When you finish editing and run the generation, Vids lays out AI-generated images and backgrounds to match the script and narration and assembles them into a video. The finished video can be edited, shared and exported just like any other Vids project.
In other words, rather than handing over a document and getting a video back with no intervention, the flow has a person review and adjust the AI draft before it is finalized. For material where you would hesitate to leave the level of detail or wording entirely to the AI, being able to check the script first is a practical reassurance.
No admin settings needed, and a wide range of eligible plans
There is no control in the admin console for this feature, and no on/off switch on the user side either. If the feature is included in your plan, it simply becomes available once the rollout reaches you.
Eligible plans include Google Workspace Business Starter, Standard and Plus; Enterprise Starter, Standard and Plus; Education Plus; the Nonprofits edition; and the education add-ons Google AI Pro for Education and Teaching and Learning. Individual users can access it with a Google AI Plus, Pro or Ultra subscription. A free Google account on its own is not eligible, so anyone wanting to try it should check their subscription status first.
The rollout comes in two stages. Domains set to Rapid Release had access at the time of the announcement, while Scheduled Release domains will see the feature appear gradually over up to 15 days starting September 5. As for language support, Google says it follows the list of supported languages for Gemini in Workspace. How natural the script and narration turn out for Japanese documents is something best confirmed by trying it on your own account.
AI features keep arriving in Vids this year
Google Vids is a video creation app offered as part of Google Workspace, designed so that AI assists with everything from drafting the script to placing assets and generating audio. Feature additions have continued through 2026, including integration with Slides and stronger Gemini-powered video generation and editing. The new document conversion extends that trend by widening the entry point for building a video from material you already have.
A document-to-video feature seems a natural fit for teams that want to produce explainer videos for internal training or sales material in bulk. At the same time, how well the images and backgrounds the AI picks match the content will vary with the nature of the document, and the more specialized the material, the more essential a review of the script becomes. A realistic approach is to start with short meeting notes or procedure guides, get a feel for how the summaries behave, and only then move on to production material.
Summary
Google Vids has added a feature that reads Google Docs, PDF and Word files and generates a summary video. The AI writes a section-by-section script and narration, and the user refines the script before generating the video. No admin settings are required, and the feature is available on the main Workspace Business, Enterprise and Education plans as well as the consumer Google AI Plus, Pro and Ultra subscriptions. It is already live for Rapid Release and will roll out to Scheduled Release domains gradually from September 5 over up to 15 days.
