Google announced Tuesday that it was deploying a video overview to Notebooklm, an AI-based note-taking and research assistant. A video overview, first introduced in May, can help users turn dense multimedia, such as Raw Notes, PDFs, and images, into digestible visual presentations.
Previously, we adopted an audio approach to help users understand the material in an audio overview. This is a feature that gives users the ability to generate podcasts using AI virtual hosts based on documents shared with notebook bulk, such as course measurements and legal briefs.
With this new feature, NoteBookLM takes a more visual approach to help users understand a variety of topics and ideas.
Google says users can think of video overviews as a visual alternative to audio overviews. This feature draws images, diagrams, quotes and numbers from uploaded documents and creates new visuals when describing the content. Google says this feature is suitable for explaining data, demonstrating processes and making it easier to understand abstract concepts.
Image credit: Google
Users can customize the video overview, just like the audio overview. They specify topics to focus on, present learning goals, describe target audiences, and more.
“I don't know anything about this topic. Please help me understand the illustrations of the paper,” or “I'm already an X expert and I'm working on Y.
According to Google, the video summary is deployed to all users in English, with support for more languages coming soon.
Google has also announced that it is rolling out updates to its studio panels for Notebooklm. Users can now create and store multiple studio outputs of the same type in a single notebook. Additionally, users now have four tiles displayed at the top of the studio panel to create an audio overview, video overview, mind map and report in a single click.
Additionally, users can now create multitasking within the studio panel. For example, you can explore mind maps and listen to an audio overview while reviewing study guides.