Google's NotebookLM Turns Any Document Into a 60-Second Vertical Video
NotebookLM's new Short Video Overviews turn any document into a 60-second vertical explainer, powered by Google's fastest new image model.
Takeaways
- New format: NotebookLM launches Short Video Overviews -- 60-second, vertical (portrait) AI-generated videos from any uploaded source.
- Powered by Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image), Google's fastest image model with 4-second generation and improved visual quality.
- Availability: Rolling out now to Google AI Ultra and Pro subscribers on mobile and web; free users coming soon.
- English only for now; users must set output language to English to see the Short option in the Studio panel.
- No post-generation editing: you accept the output or regenerate -- no script or timeline control.
- Fits into a growing video lineup alongside Brief, Explainer, and Cinematic formats, each targeting different use cases and lengths.
NotebookLM just added a new output format that feels tailor-made for the way people actually consume content today: Short Video Overviews. Upload any source material, and the tool will generate a 60-second, portrait-orientation video that distills the key ideas into something you could watch during a commute or a scroll break. It is rolling out now to Google AI Ultra and Pro subscribers on mobile and web, with free users coming soon.
The anatomy of a Short Video Overview
NotebookLM is using Nano Banana 2 Lite for Short Video Overviews, producing a 60-second portrait video with "narrative explanations and educational animations." Think of it as the TikTok-length sibling of the longer Cinematic Video Overview format that launched earlier this year.
Nano Banana 2 Lite, officially known as Gemini 3.1 Flash-Lite Image, is Google's "fastest and most cost-efficient image generation and editing model," with the company touting 4-second image generation. Compared to the original Nano Banana (Gemini 2.5 Flash Image), this new model offers "fast image generation with a significant leap in visual quality and capability."
The Short format sits alongside the existing Video Overview lineup. Here is how all three formats compare:
| Format | Length | Orientation | Best for |
|---|---|---|---|
| Brief | ~1-2 min | Landscape | Quick concept grabs |
| Explainer | ~2-5 min | Landscape | Structured deep dives |
| Cinematic | ~1-3 min | Landscape | Animated, story-driven summaries |
| Short (new) | 60 sec | Portrait (vertical) | Mobile-first, shareable explainers |
How the pipeline actually works
NotebookLM's video generation is not powered by a single model. It combines three distinct AI systems, each handling a different part of the production pipeline. Gemini handles the comprehension layer: when you add sources to a notebook, Gemini reads and analyzes them to build a shared understanding of the content.
Gemini effectively acts as a creative director for the process, making hundreds of structural and stylistic decisions about how the video should unfold. The model determines the narrative flow, selects visual styles and formats, and even refines the output to keep scenes consistent throughout the video. Instead of simply summarizing documents, the AI is actively designing how the story should be told visually.
For Short Video Overviews specifically, Nano Banana 2 Lite takes over the image generation layer. Nano Banana generates helpful, contextual, and beautiful illustrations based on the sources you upload, producing Video Overviews that don't just tell you about your documents but help you understand and remember them.
What it is actually good at
The format shines in a few specific scenarios:
- Research papers and dense PDFs -- if you've gathered 10 research papers on a topic, NotebookLM can turn those into a coherent video that captures the main findings, useful for quickly briefing a team or creating a shareable artifact from work you've already done.
- Internal documentation -- companies using NotebookLM for internal documentation can convert long-form reports, strategy documents, or research briefs into video summaries.
- Education and training -- teachers and trainers can upload lesson materials and get an instant video explainer, a fast way to create supplemental content or previews.
- Multi-format notebooks -- you can create multiple outputs from the same notebook: video, audio, mind map, and written summary.
The real limitations to know about
The format has clear constraints worth understanding before you commit time to it.
- No post-generation editing. There is no direct customization after generation. You can't adjust the script, change the visual style, select a different narrator voice, or edit the timeline. You either accept the generated output or regenerate it.
- English only for now. The Short Video Overview format currently only supports English. The NotebookLM team confirmed in the announcement thread that changing your output language to English is required to see the Short option appear.
- Source quality matters. Accuracy is bounded by source quality. Gemini's understanding is only as good as the sources you provide. If your sources are unclear, contradictory, or poorly structured, the video script will reflect that.
- Generation can be slow. Video Overviews, including voices and visuals, are AI-generated and may contain inaccuracies or audio glitches. NotebookLM may take a while to generate the Video Overview, sometimes more than 30 minutes.
How to use it right now
The workflow is straightforward:
- Open an existing notebook or create a new one and upload your sources (PDFs, Google Docs, YouTube URLs, web pages, etc.).
- In the Studio panel, select "Video Overview" to initiate generation. Before generating, you can customize your video; otherwise, NotebookLM will create a video overview using default settings.
- Select the Short format option (the new vertical format). If you don't see it, make sure your output language is set to English.
- Add a steering prompt to give instructions that help NotebookLM focus on what's most important to you. For example, you can tell it to focus on certain sources or topics.
Who gets access and what it costs
Short Video Overviews are rolling out now to Google AI Ultra and Pro subscribers on mobile and web. Free users are explicitly promised access "soon" per the official announcement. Cinematic Video Overviews (the longer format) remain exclusive to the $249.99/month Google AI Ultra plan. Google AI Pro, which includes NotebookLM Pro access, is available as part of Google One AI Premium at $19.99/month.
The bigger picture
The Short Video Overview is not just a new export button. It signals a deliberate shift in how NotebookLM thinks about output formats. AI tools have spent the last two years getting dramatically better at summarizing text and answering questions about documents. But the next phase of the technology is increasingly focused on multimodal output -- meaning AI that can turn information into images, presentations, and now video.
The vertical, 60-second constraint is a meaningful design choice. It forces the model to prioritize ruthlessly, and it produces something that is actually shareable on the platforms where people already spend their time. The Audio Overview turned your research into a podcast. The Short Video Overview turns it into something closer to a YouTube Short or an Instagram Reel -- grounded entirely in your own source material. For anyone who regularly needs to communicate complex information to a non-expert audience, that is a genuinely useful new primitive.