This is how NotebookLM turns your work and ideas into cinematic works

NotebookLM – Google’s AI-powered research assistant Now turn your notes and documents into vibrant videos with smooth cinematic animations.

NotebookLM is a sophisticated AI engine, built on the same platform models as Google Gemini but with a less “talky” and more user-friendly interface. Like Gemini, it is regularly upgraded and new features are added. Recently, NotebookLM’s latest update added a “cinematic” video summary feature.

With features “Cinematic Video Overviews” new, NotebookLM is now possible “create unique, vibrant videos designed specifically for you”. Google says this new functionality relies on a trio of advanced AI models, including Gemini 3, Nano Banana Pro and Video 3, to create .“smooth animations and rich, detailed visuals”.

What can NotebookLM’s Cinematic Video Overviews do?

NotebookLM now allows users to upload documents, research papers, and notes to create summaries or ask questions about their sources. The new Cinematic Video Overview feature pushes that idea further by turning information into a visual story.

According to Google, the system can analyze uploaded document sources, build a structured explanation around the document, and create animations to illustrate key ideas.

For example, a set of research notes or lecture materials can be converted into a visual summary designed to make the topic easier to follow and understand. In fact, the result is closer to a short explainer video than a traditional text summary.

How did Google AI build this video?

This feature relies on a combination of Google’s AI models working together behind the scenes.

NotebookLM’s cinematic video overview uses:

• Gemini 3 to understand the source material and story structure
• Nano Banana Pro for creating images and visual elements
• Veo 3 to create the ultimate animated video

Video example made from NotebookLM’s Cinematic Video Overviews

AI tools have spent the past two years significantly improving their ability to summarize text and answer questions about documents. But the next phase of technology is increasingly focused on multimodal output — meaning AI can turn information into images, presentations, and now video.

Gemini essentially takes everything you give it (cluttered notes, research documents, etc.) and effectively acts as a creative director for the process, making hundreds of structural and stylistic decisions about how the video should be presented.

The model determines the narrative flow, chooses the visual style and format, and even fine-tunes the output to keep scenes consistent throughout the video.

Now, instead of simply summarizing material, AI is proactively designing how the story should be told visually.

The Cinematic Video Overviews feature is rolling out in English to users 18 and older with a Google AI Ultra subscription. This feature is available on NotebookLM for web and mobile.