Google’s NotebookLM is one of the most powerful use cases for AI

This article is republished with permission from Wonder Tools, a newsletter that helps you discover the most useful sites and apps. Subscribe here.

Google’s free NotebookLM made improvements on October 17 to what has become one of the most powerful ways to use AI. You can now customize its most popular feature — AI-generated audio summaries — to focus on specific topics, target audiences, or documents.

Read on for an updated overview of one of the year’s most surprising AI tools, including suggested ways to use it and a few limitations.

What it is in a nutshell: NotebookLM is a free Web-based AI service that helps you draw insights and learn from notes, documents, links, and recordings. It doesn’t do research on the Web or make up information. Instead it’s focused exclusively on analyzing the sources you upload.

Updates to Google’s fast-growing experiment

What’s new: Since I first covered NotebookLM, it’s improved substantially.

• Use it in 200 countries. You no longer have to be in the U.S to join.
• Upload more files. You can now add all sorts of doc, links and multimedia.
• Use Gemini’s best model. You can now ask questions about images, charts, or diagrams that appear in any of the sources you upload.
• More specific, accurate citations. When NotebookLM identifies something in your notes or documents, you can click on a citation link to see a more precise selection from the material in your own notes.
• Join as a team. As of Oct 17, Google is inviting businesses, universities, and other organizations to join a new pilot program for team collaboration. It’s initially free, but will eventually be a paid service.

New: Create customized audio posts

Customize Audio Summaries. Here’s one I generated to test out the brand new custom prompt feature. First I uploaded a YouTube recording of a workshop I led about AI for educators. Then I provided a few sentences of guidance to shape the focus of the audio clip, targeting educators skeptically curious about AI.

How it works: NotebookLM can turn anything you upload into an AI-generated podcast episode. Each notebook you create can include one of these “audio overviews” featuring a conversation between two AI voices. Here’s an example I made by uploading a post I wrote about Perplexity.

• Human-like voices. The quality of the voices and the AI summarization is so good that when I played a recording recently for a group, people assumed the hosts were human. Even before this week’s customization improvements, NotebookLM was generating buzz for the quality of its audio generation, as reflected in this Twitter/X thread.
• Enthusiastic bots. NotebookLM’s algorithm instructs its AI audio hosts to be energetic. Even when given resumes and credit card receipts to summarize, the AI hosts still sound thrilled.
• English only. NotebookLM can understand materials in close to 100 languages, and queries in numerous languages. The audio overviews are English-only for now because of voice-model limitations.
• Mostly seven-to-15 minutes long. You can’t customize the audio length. If you provide brief material you may get a 3-minute audio result. Exhaustive texts may end up with 20-minute audio summaries.

How to get started

• Sign up at notebooklm.google.com. It’s free with no usage limitations. Start by exploring sample notebooks included in your account.
• Create a new notebook. You can then add: Google Docs or Slides. PDFs, text, or Markdown files. YouTube or other Web links, or audio files.
• Upload up to 50 sources into each notebook. Each can be up to 200mb and contain up to 500,000 words.
• Create up to 100 notebooks. (I have ones for research, teaching, and hobbies).

• Google Docs or Slides.
• PDFs, text, or Markdown files.
• YouTube or other Web links, or audio files.

Apply AI to a collection of notes or documents

NotebookLM’s AI can generate overviews of the material in each notebook. You can ask specific questions about your materials, or you can start with some default resources.

• FAQ = Get a summary of questions and answers related to your material.
• Table of Contents = See a roadmap of what’s in your notebook.
• Study Guide = Get quiz and essay questions and a glossary of key terms.
• Timeline = See an ordering of events and a list of people mentioned.
• Briefing Doc = View a summary of primary themes, notable ideas, and quotes.
• Chat. You can query your notebook just as you would chat with ChatGPT, Claude or any other AI bot. The benefit in NotebookLM is that it will provide a citation to the section of a document it relied on in answering your query.
• Noteboard. Inside each notebook, there’s a bulletin-board style space for saving AI responses. You can use it to reflect on new ideas, annotate passages, or save observations that emerge as you interact with the AI.

How NotebookLM’s creator suggests using it

I spoke recently with Steven Johnson, who helped develop NotebookLM. He’s a popular author of 14 non-fiction books, who has also been a tech founder and serves as Editorial Director of Google Labs. He shared with me a helpful approach to making the most of NotebookLM:

• Create a master notebook. Put in the documents most important to you. A notebook can accept about 25 million words, enough to store a lifetime’s worth of thinking and writing. You can then query that notebook to surface your past ideas, research or writings that relate to current projects.
• Create project-specific notebooks. Dump in your most recent 10 docs, slides or other materials and use the notebook as a reference resource.
• Create an audio overview to review the week. Put in transcripts of your recent meetings and read the summary briefing and/or listen to the overview on your commute to review key conversations.

Some new ways to use NotebookLM

• Create a collection of your favorite quotes or reading highlights. I exported my collection of thousands of Readwise highlights to Google Docs, then imported those into a new NotebookLM. Now I can use AI to explore a decade’s worth of passages I’ve highlighted in Kindle books, online articles, and podcasts.1 I can draw inspiration from these quotes and ideas in new ways that inform my writing and teaching. Listen to an audio summary of this collection I asked NotebookLM to personalize for me.
• Create an AI-enabled journal. Export your past musings to make it easy to search for patterns in your past thinking.
• Turn class or reporting notes into AI-powered idea seeds. Convert anything you’ve learned into an AI-enhanced notebook. It’s easy to then generate study guides, FAQs, or query the notebook about various themes you’ve been exploring.

• Now I can use AI to explore a decade’s worth of passages I’ve highlighted in Kindle books, online articles, and podcasts.1 I can draw inspiration from these quotes and ideas in new ways that inform my writing and teaching. Listen to an audio summary of this collection I asked NotebookLM to personalize for me.

Build on your own notes

• Clarify, critique, or expand on notes. You can highlight any notes on your noteboard and ask for them to be clarified, critiqued, combined, or summarized. Or you can ask for an outline based on a note, or for it to suggest related ideas.
• Dialogue with your notes. When you’re writing something or preparing a presentation, use NotebookLM to assist in exploring your materials. Initiate a dialogue with your own notes. This ability to surface and connect valuable ideas otherwise hidden deep within my notes or documents is what I find most valuable about NotebookLM.
• Query an individual document or a full collection. NotebookLM generates a summary for each source you add. It also adds subject tags based on the content. You can query one or more documents or the full notebook.

Caveats

• NotebookLM is labeled an “experimental” service, so Google could potentially pull the plug anytime.2 This week’s announcement of a new paid business service may be a good sign that the company envisions a sustainable future for this service.
• NotebookLM doesn’t yet work with Google Sheets or other data formats.
• No mobile app, though the mobile Web version works well for simple queries.
• Available only to people 18 and older.
• Google doesn’t train its models on your material. But if you’re skeptical about the company, avoid uploading private material.