What you need to know
- Google’s NotebookLM now condenses massive documents and notes into 60-second, TikTok-style vertical videos.
- The feature is fueled by Gemini 3.1 Flash-Lite Image, Google’s fastest and most cost-efficient image generation model, boasting four-second render times.
- Google is also previewing a robust full-video generation model that supports natural language editing, multimodal inputs, and native audio syncing.
Nobody really enjoys reading through a massive stack of notes or a 50-page research document when they’re cramped for time. Google knows this, and so it’s rolling out a huge upgrade to NotebookLM that takes your uploaded documents and turns them into bite-sized, 60-second AI-generated videos.
For the uninitiated, NotebookLM started out as a simple AI research assistant, but it’s now a powerful learning tool. The latest feature, Short Video Overviews, expands on the Cinematic Video Overviews we saw earlier. But the real star of the show is the engine that powers it: Google’s new Nano Banana 2 Lite.
Officially dubbed Gemini 3.1 Flash-Lite Image, Nano Banana 2 Lite is Google’s fastest and most cost-efficient image generation model to date. You get a whopping four-second image generation time and a big jump in visual quality over the original Gemini 2.5 Flash Image (the first Nano Banana). This engine combines world knowledge with rock-solid consistency of character. It lets you quickly sketch accurate scenes, develop storyboarding tools and render legible typography for localized ads without compromising object fidelity.
Using Short Video Overviews in NotebookLM activates this model, which condenses your sources into a vertical video packed with narrative explanations and educational animations. It’s purpose-built for people revising notes, presentations, or lengthy PDFs who just want the key takeaways. Before generating, you simply select “Short” from the output formats (alongside Explainer and Cinematic), pick your specific sources, and set the video’s focus using a custom prompt or a suggested topic.
Alongside this, Google also pushed Gemini Omni Flash into public preview. This model is aimed at full video generation, with conversational editing (relighting scenes and swapping characters with natural language) and multimodal inputs. It has native audio pairing for each video output and syncs on-screen text with kinetic movements.
Short Video Overviews aren’t available to everyone just yet. The feature begins rolling out over the coming weeks to English-speaking users aged 18 and older. When it goes live, you’ll be able to access it on the web, Android and iOS, whether you’re signed into a regular consumer account or Google Workspace.
Android Central’s Take
If you’re a student cramming for finals or someone who hates reading dense reports, turning a 50-page PDF into a digestible, TikTok-style recap is a massive win. But are we really so allergic to actual reading that we need an AI to hallucinate a 60-second clip from our notes? Google wants to sell the service as the ultimate productivity hack, but it feels disturbingly like a crutch for our fast-shrinking attention spans.