In a new round of updates for NotebookLM, Google announced yesterday (September 26) that the model is now capable of summarizing YouTube videos and creating shareable AI-generated discussions. It really seems like there is no end to what AI is capable of, especially for creatives.
That’s why I couldn’t wait to see what Google’s Notebook LM, powered by the company’s multimodal large language model Gemini 1.5 Pro, would do when I shared my young adult science fiction book with it.
Earlier this year, I wrote a book for my Fortnite-loving son after he told me he couldn’t find anything good in the library. Of course he was being overly dramatic, but since I already had a book idea, I got to work. My kids and their classmates enjoyed the book, and it turned out to be a best-seller on Amazon (for a week-ish, but I’ll take it considering I only wrote it for my son).
I wasn’t planning on doing anything else with the book until I discovered Google NotebookLM. Utilizing Google Gemini AI, the model is designed for AI-powered note-taking and has AI research tools and audio capabilities. Google’s NotebookLM recently expanded source options and enhanced citation features for more accurate research.
The announcement of these key updates means it’s a great fit for writers and anyone looking for deeper interactions with their data in a safe, efficient, and reliable manner.
One particular feature that stood out to me is NotebookLM’s podcast-style summaries. The audio overview capability of NotebookLM, enables users to create podcast-style summaries from their selected sources. Essentially, the model can take anything from an article or blog post to an entire book manuscript and produce an audio file that sounds exactly like two people naturally engaged in a discussion about the content.
This is an innovative addition to the model’s capabilities, as now, instead of reading through texts, users can listen to an audio version of a customized study guide or summary. With the latest update, the AI can even summarize YouTube videos.
This makes it a perfect feature for multitasking; that way, one could digest information on the go, just like listening to a podcast or an audiobook. This function is a godsend for anyone who has an extremely busy schedule.
For example, if my son did not want to read my book, he could listen to the AI-generated podcast of it on the way to soccer practice. But, please don't tell him that.
The AI-generated podcast of my book is so convincing, you’d instantly want to subscribe if it were real. The way the two voices engage with each other and elaborate about the content with scoffs, tiny ums, and laughter is so natural and human-like it’ll make you question reality.
Still, Google is quick to point out that NotebookLM is experimental. Like most AI models, it's not beyond making errors or inaccuracies from time to time. However, the updates this month have radically improved its usefulness, and NotebookLM is better positioned than ever before to cater to user demands for an effortless, AI-driven information management system.
One important note is that NotebookLM users have to be at least 18 years old, have a Google account, and live in one of the 180 regions where the Gemini API is available. Access to NotebookLM is free; users are not charged, and according to Google, your data is not used to continue training the AI, which is a key privacy consideration in today's AI landscape.
More from Tom's Guide
