If your job involves going through meeting notes or training PDFs for hours every day, Google just gave you a workaround, one that not only saves your time but also makes wading through the document much less boring.
Google Vids can now convert your documents, including PDFs, Word files, and, of course, Google Docs, into a narrated video summary with curated visuals.
So what does this new Docs to Video feature actually do?
There’s a new option in Vids’ File menu called Docs to Video. It lets you pull in a document straight from your Drive or computer. Then, using AI, it scans the document, creates a script that summarizes the content (as key points), and adds voice narration to go with it.
Before the tool is ready to go, you can review the script, rewrite specific parts, or swap in a different narrator voice. Once everything is in place, Vids stitches everything together with AI-generated visuals and backgrounds. If this sounds familiar, it’s because Google’s NotebookLM can also do the same.
As someone who goes through a couple dozen press releases, text-heavy presentations, and emails daily, I can see people learning how to use it the day they get access. The obvious use case is skipping the reading altogether, whether it’s meeting notes or training material nobody has time for. Second, and more importantly, visuals and a voiceover make it much less monotonous.
When can you actually use it, and does it work yet?
As good as the feature sounds, there’s a catch. It’s only available to Google AI Plus, Pro, or Ultra users, as well as those enrolled in Business, Enterprise, and Education plans. Rollout depends on your account type.
While Google’s Rapid Release domains already have access today, those in the Scheduled Release domains will get access over the next two weeks, starting September 5, 2026.
While reading about the feature online, I came across something worth flagging: AndroidAuthority’s test run got only as far as generating a script. It then hit a repeated error trying to render the finished video. However, that’s normal for a brand-new multimodal AI feature trying to do a lot at once. So, don’t be surprised if it doesn’t work on the first attempt.