Tools

Gemini Notebook (Formerly NotebookLM): 2026 Guide

Google renamed NotebookLM to Gemini Notebook in July 2026, rewrote how its usage limits work in September, and in October wired it into the Gemini app and a free textbook library. Here's the verified timeline, ranked by what actually changes how you study and research.

Key Takeaways
    • NotebookLM is now called Gemini Notebook, and it's spreading across Google. Google renamed it on July 16, 2026, and notebooks now work inside AI Mode in Search and the Gemini app, which since October 23 can also create, edit, and answer from them; Google Docs can ground a draft in one. It's no longer a document Q&A tool; it's a source-grounded research agent that Google said in July is used by more than 30 million people.
  • Deep Research and free textbooks fixed the blank-notebook problem. Since November 2025, NotebookLM can build a cited source list from the open web on its own, and since October 29, 2026, you can add hundreds of free textbooks from OpenStax, the Open Textbook Library, and S Chand Publishing straight from the Add sources menu.
  • You can now talk to a notebook, and record into one. Real-time voice conversation in nearly 100 languages arrived on September 15, 2026, for Ultra first; Google's help page now lists the mobile app and an age of 18 or older as requirements, without naming plans. The mobile recorder is live on Android and iOS and turns up to an hour of lecture into a transcript source.
  • The limits system changed completely on September 2, 2026. For personal Google accounts, fixed daily caps gave way to a compute budget that refreshes every five hours against a weekly ceiling, so what you can do depends on how expensive your requests are.
  • Students can get a year free, and there's still no consumer API. Eligible US college students get 12 months of Google AI Pro (Google AI Plus in 140+ other markets) if they redeem by December 31, 2026. The only notebook API still requires an Enterprise license, and inside Gemini Notebook each notebook is still its own silo.
  • Gemini Notebook is only as good as the sources you feed it. That's why pairing it with a capture layer like Glasp matters more in 2026, not less.

What Is Gemini Notebook? The Rename, Explained

Gemini Notebook is NotebookLM. Google renamed the product on July 16, 2026, and nothing else about your account changed: same notebooks, same sources, same saved chats, and old notebooklm.google.com links now redirect to notebook.google.com. It's Google's free, source-grounded research and study tool: answers are built from sources you add, whether you upload them yourself or let its research agent find them on the web.

The rename wasn't cosmetic housekeeping. It came with a wider rollout of native code execution, and in the months since, Google has folded notebooks into Google Search, Google Docs, and the Gemini app, replaced the entire usage-limit system, added voice, and opened a free textbook shelf. The product still has a genuinely generous free tier, and most people still type "NotebookLM" into the search bar, so this guide uses both names.

When NotebookLM launched its Audio Overviews in late 2024, the pitch was simple: upload your documents, and an AI grounded in those documents answers questions and makes a podcast. That tool no longer exists in any meaningful sense. The product today researches the web on its own, generates animated videos, edits slide decks on command, writes and runs code on a secure cloud computer, holds a spoken conversation about your sources, and suggests new sources mid-conversation. In its July rename announcement, Google said more than 30 million people and over 600,000 organizations use it.

That pace creates a real problem for learners. Half the NotebookLM advice published in 2025 is now wrong, and the update stream is so fast that it's hard to tell which changes matter for an actual study workflow and which are demo material. A new infographic style is nice. An agent that builds your bibliography for you changes how you start every project.

This article is the sorting exercise. Every date and number below comes from Google's announcements and help pages, or from contemporary reporting where Google's own post isn't available, and all of it was re-checked on November 5, 2026. If you're deciding whether NotebookLM should be your main research tool, or whether to pay for it, this is the current state of play. If you've already decided to leave and want options, that's a different article: see our NotebookLM alternatives comparison.


The Verified Update Timeline

Here's what Google announced or began rolling out between August 2025 and the end of October 2026. A date marks the announcement or the start of a rollout, not the day every account got the feature. Skim the third column if you only care about impact. The newest changes sit at the bottom: guided co-creation for slides and videos, notebook actions inside the Gemini app, and a free textbook catalog, all from October 2026.

DateWhat ChangedWhy It Matters for Learners
Aug 25, 2025Video Overviews expanded to 80 languages; non-English Audio Overviews got the full-length treatmentStudy in your own language without the short, watered-down version
Oct 29, 20251M-token context window across all plans; custom chat goals per notebook; saved chat history began rolling outBook-length collections fit in one conversation, and chats stop vanishing
Nov 13, 2025Deep Research agent; Google Sheets, Word (.docx), Drive PDFs, and images as sourcesNotebookLM finds sources for you instead of waiting for uploads
Nov 2025Slide decks and infographics (Nano Banana Pro)Visual study materials straight from your sources
Dec 18, 2025Data Tables output with Sheets export, Pro and Ultra firstQualitative sources become comparison tables
Mar 4, 2026Cinematic Video Overviews (Gemini 3 + Nano Banana Pro + Veo 3), Ultra plans onlyAnimated explainer videos from your notes, at a steep price
Mar 2026EPUB support; new infographic styles; flashcard and quiz progress tracking; prompt-based slide editing and PPTX export; Cinematic Video Overviews reach ProBooks as sources, practice that remembers your misses, and targeted slide revisions saved as a new deck
May 2026Google I/O (May 19): Literature Insights, an experimental research tool built with NotebookLM; automatic Drive sync for imported files from May 26Sources stay current as the underlying files change
Jun 8, 2026Gemini 3.5 and Antigravity-powered agentic chat, including code execution and building a source repository from chat, for Ultra and Workspace AI Expanded Access firstStart from a question, not a pile of documents
Jun 2026Google AI Plus price cut to $4.99/monthThe cheapest paid tier got genuinely cheap
Jun 30, 2026Short Video Overviews (roughly 60-second clips), Ultra and Pro firstBite-size recaps for phone review between classes
Jul 16, 2026Renamed to Gemini Notebook; the secure cloud computer for code execution expanded, with all Pro users on the web promised next; cross-app sync with the Gemini app; Search AI Mode integration announcedSame tool, new name; Ultra notebooks can run code on your sources, with Pro promised
Aug 19, 2026Notebooks began rolling out inside AI Mode in Google Search, in English across 180+ countries outside the EEA; a free year of Google AI Pro announced for US college studentsYour notebook answers questions from the search bar
Aug 27, 2026Expert Intelligence: eligible ebooks you own on Google Play Books can be added as sourcesQuiz yourself on a book you bought, with answers grounded in it
Sep 2, 2026Fixed daily caps replaced by compute-based usage limits that refresh every 5 hours against a weekly ceilingThe single biggest change to how the free tier feels day to day
Sep 15, 2026Real-time voice chat with your notebook (~100 languages), Ultra first; mobile audio recorder; Interactive Learning Overviews; short answer, multiple select, and fill-in-the-blank quizzes announced; Short Video Overviews expanded to 80+ languages and made shareableLectures can enter a notebook directly, and quizzes are meant to test recall, not just recognition
Sep 2026Notebooks in the Gemini app (from Sep 14) and its adaptive study notebooks (from Sep 17) began reaching Google Workspace school and work accounts, students of all ages includedSchool accounts get notebooks inside the Gemini app
Sep 23, 2026Google Docs can ground a draft in a notebook: type @ in the Gemini panel (Pro, Ultra, and eligible business and education plans)Write with inline citations to your own sources
Oct 16, 2026Google confirmed the new short answer, multi-select, and fill-in-the-blank quiz formats are live, plus feedback on where to focus after a quiz or flashcard roundQuizzes now test recall, not just recognition
Oct 19, 2026Guided co-creation for slide decks and Video Overviews: suggested topics, a reviewable outline or producer notes, and feedback before renderingSteer a deck or video before it renders instead of regenerating it
Oct 23, 2026Gemini Notebook became a Connected App in Gemini: create, edit, and delete notebooks, manage sources, and get answers from a notebook in a Gemini chat; off by default in the EEAYour notebooks work from the main Gemini chat
Oct 29, 2026Hundreds of free textbooks from OpenStax, the Open Textbook Library, and S Chand Publishing, added via Add sources, then TextbooksA free, citable textbook becomes a source in two clicks

Five threads run through this list: ingestion got agentic, outputs multiplied, the chat itself got smarter and learned to talk, in July the whole thing was folded into Google's Gemini brand and then spread into Search, Docs, and the Gemini app, and in September the economics of using it were rewritten. The next sections take each thread in turn.


Research Ingestion: Deep Research and Sources That Find Themselves

The single most important change in this entire timeline is the November 13, 2025 Deep Research launch. Before it, NotebookLM had a cold-start problem: the tool was only useful after you'd done the work of collecting sources. Deep Research inverts that. You type a question, it drafts a research plan, browses the web for several minutes, and returns a cited report plus a list of sources you can import into the notebook with one click. A lighter "Fast Research" mode does a quicker scan when you don't need depth.

The June 8, 2026 update pushed this further. You can now start a plain chat about a project, and NotebookLM will suggest sources as the conversation develops, using its research skills and Google Search to build the knowledge base around you. Google's framing is that you no longer need to bring your own sources at all. It launched for Ultra subscribers and Workspace customers with AI Expanded Access. Google's help page now describes finding and importing sources from the chat without naming a plan, but Google hasn't announced a wider rollout, so check whether your account has it.

The same period quietly fixed the format gaps. NotebookLM now accepts Google Sheets, Word documents, PDFs straight from Drive, images, audio files, and as of March 2026, EPUB files. In late May 2026, Google added automatic Drive sync for imported files, so a notebook built on living documents picks up their edits when you open it. It syncs the files you added, not a whole folder: a course notebook tracks edits to the lecture notes you imported, but new files in the shared folder still need adding.

Two newer additions change where sources come from. Since August 27, 2026, Google's Expert Intelligence program lets you add eligible ebooks you've bought on Google Play Books (more than 100,000 titles from publishers including Penguin Random House, Macmillan, and O'Reilly Media) and ask questions grounded in the book; on a shared notebook, each collaborator needs their own copy. And on October 29, Google added hundreds of free textbooks from OpenStax, the Open Textbook Library, and S Chand Publishing: choose Add sources, then Textbooks, and every answer cites the book with links back to the original. If your course already uses one of those texts, the notebook can now quiz you on the assigned book itself.

What does this mean in practice? The honest answer is that Deep Research is excellent for breadth and mediocre for judgment. In a few minutes it can hand you a stack of plausible sources on, say, spaced repetition, which beats an hour of manual searching. It will not tell you which three of those are worth reading closely, and it inherits all the usual weaknesses of automated source-finding: SEO bait ranks, paywalled gems don't. Treat its output as a draft bibliography, not a finished one. The textbook shelf is the opposite trade: narrow, but vetted. For how Deep Research-style agents compare across ChatGPT, Gemini, and Perplexity, see our deep research tools comparison.


Output Formats: Audio, Video, and the Studio Explosion

In mid-2025, NotebookLM's Studio panel produced an audio overview and a few text artifacts. Today the menu reads: Audio Overview, Video Overview, Short Video Overview, Cinematic Video Overview, Mind Map, Reports (including Interactive Learning Overviews), Flashcards, Quiz, Infographic, Slide Deck, and Data Table.

Audio Overviews matured rather than changed. The headline move was August 25, 2025, when non-English audio finally got the full-length, genuinely conversational treatment instead of the shorter summaries non-English users were getting before. If you tried a Japanese or Hindi Audio Overview in early 2025 and found it thin, give it a second look.

Video Overviews now come in three formats. The standard version, which is a narrated slideshow, is available on every tier including free. Short Video Overviews, added at the end of June 2026, are roughly 60-second clips that pair a narrative summary with educational animation, built for phone-sized review. They launched on Ultra and Pro; since the September 15, 2026 update they run in more than 80 languages and can be shared with classmates. The Cinematic Video Overviews, launched March 4, 2026, are a different animal: Gemini 3 acts as a creative director while Nano Banana Pro and Veo 3 generate animated, film-style visuals from your sources. They're impressive, they're English-only and 18+, and they went out Ultra-only before reaching Pro later the same month. For most learners, the cinematic version is a curiosity, not a study tool. A narrated slideshow conveys the same information.

The study artifacts are the underrated story. Flashcards and quizzes gained progress tracking in March 2026: Gemini Notebook remembers where you left off, and at the end of a round you can review or retake what you missed. Google doesn't describe it as a spaced-repetition scheduler, so deciding when to come back is still your job, and spaced repetition for readers explains how to time it. Fall 2026 went after the quizzes' biggest weakness. Google announced short answer, multiple select, and fill-in-the-blank questions on September 15, and on October 16 said it had added them alongside multiple choice, along with a way to ask the notebook for feedback on where to focus next. The new formats matter more than they sound. Multiple choice tests recognition. Short answer and fill in the blank force retrieval, and retrieval is the mechanism that builds durable memory. The same announcement covered Interactive Learning Overviews, which live under Reports on the web (Studio, then Reports, then Interactive) and walk you through your material step by step, with suggested infographics, quizzes, and flashcards from the same sources embedded along the way instead of left as separate artifacts you have to assemble yourself.

Data Tables, added in December 2025, turn a pile of qualitative sources into a structured comparison table you can export to Sheets, which is genuinely useful for literature reviews and product comparisons alike. By March 2026, slide decks were editable by prompt and exported to PowerPoint, which moved them from toy to usable for actual class presentations. Since October 19, you can also co-create a deck or a video: Gemini Notebook suggests topics from your sources, lays out an outline for slides or producer notes for a video, and takes feedback, like adding a summary up front or swapping two scenes, before it renders. You can still skip the review and generate straight away. Google's October 19 post said this would reach all users within a week, though its help pages still list slide and video co-creation as Ultra-only.

A ranking for learners, most to least valuable: quizzes and flashcards with tracking (especially the new recall formats), Interactive Learning Overviews, Data Tables, Audio Overviews for commute review, standard Video Overviews, infographics, and Cinematic videos last. The pattern is boring but consistent: the formats that make you retrieve information beat the formats you passively watch. That's the same finding behind active recall, and it holds no matter who generates the cards.


Smarter Chat: Saved History, Personas, and Voice

Google has swapped the model under the hood more than once. The most visible upgrade came on June 8, 2026, when Gemini 3.5 and Antigravity-powered agentic chat arrived for Ultra subscribers and Workspace customers with AI Expanded Access. Google doesn't say which model version each of the other plans runs, so be wary of any guide that names one model for everyone. What's worth testing on your own notebook is cross-source reasoning: a question like "where do these five papers disagree about working memory" should come back citing the actual points of tension, not a summary of each paper in sequence.

Two quieter changes matter as much for a study workflow:

Saved conversation history, which began rolling out on October 29, 2025, ended one of NotebookLM's most annoying behaviors: chats that vanished when you closed the tab. Conversations now persist, resume, and can be deleted. Google enabled the full 1M-token context window across all plans in the same update, so a semester-long dialogue with your course materials is now actually possible on the free tier.

Custom personas and goals, which reached every user on October 29, 2025, let you tell each notebook how to behave. A persona like "act as a tutor preparing me for a closed-book exam, always quiz me before explaining" turns the same notebook from a summary machine into something closer to a teaching assistant. Most users never touch this setting. It's the highest-leverage five minutes of setup the product offers.

You can now talk to it. On September 15, 2026, Google announced real-time voice conversation with a notebook in the Android and iOS apps, in nearly 100 languages, and began rolling it out to Ultra that week. You ask out loud, it answers only from your sources, and you can interrupt mid-answer to redirect it, which is closer to how you'd actually question a tutor. Google's help page now lists the mobile app and an age of 18 or older as requirements and no longer mentions Ultra. For anyone who revises while walking or commuting, it's a hands-free way to question your sources.

The June 2026 update, Ultra first, also added what Google calls Antigravity-powered skills: you can give detailed instructions for output formats and the agent executes multi-step work, including writing code and producing downloadable reports. That's aimed more at professional research than studying, but it signals where the product is going: less notebook, more agent.


The Rename, Notebooks Across Google, and the API Question

On July 16, 2026, Google renamed NotebookLM to Gemini Notebook. The logo picked up the blue and purple Gemini gradient, and Google's framing was that the product stays "a standalone product focused on being your premier research tool" while doing "more across the Google ecosystem." Nothing you saved disappeared, and none of your notebooks broke. Bookmarks to notebooklm.google.com now redirect to notebook.google.com. For most learners the new name changes nothing day to day, but it signals Google folding the tool into the Gemini family rather than letting it drift as a side project.

The substantive news in the same announcement was a wider rollout of the secure cloud computer Google had introduced on June 8 for Ultra, which lets a notebook on an eligible plan write and execute code natively, grounded in your sources. Ask it to chart the trend across a Data Table, run a quick statistical test on a dataset you uploaded, or clean up a messy CSV, and it does the work instead of hand-waving an answer. The July post confirmed it for Google AI Ultra users and Workspace business customers with AI Ultra Access or AI Expanded Access, and promised all Pro users on the web over the following weeks; Google hasn't said whether that rollout is finished, or whether Plus and free will get it. For anyone doing quantitative coursework or light data analysis, this is the most useful thing to arrive since Deep Research.

Two ecosystem moves came with the rename, and both have landed. Notebooks sync across the Gemini app and the standalone Gemini Notebook site, so a notebook you build on the web shows up in the app for quick chat on your phone. And on August 19, 2026, notebooks began rolling out inside Google Search's AI Mode, in English, across every country Gemini Notebook supports except the European Economic Area. You can create, edit, and chat with a notebook straight from the search bar, and sources, renames, custom instructions, and deletions sync both ways.

Chats don't sync, and that catches people out: an AI Mode conversation stays in Search, and a Gemini Notebook conversation stays in Gemini Notebook. And notebooks shared with you by someone else don't appear in AI Mode at all, though you keep normal access to them in Gemini Notebook. Google Play Books sources can't be used there either.

Notebooks have kept spreading since. In mid-September, notebooks in the Gemini app, and its adaptive study notebooks, began reaching Google Workspace school and work accounts, students of all ages included, wherever an admin has turned on both apps. On September 23, Google Docs learned to ground a draft in a notebook: type @ in the Gemini panel, pick the notebook, and the draft cites your sources inline, on Pro, Ultra, and eligible business and education plans. And on October 23, Gemini Notebook became a Connected App in Gemini, so an ordinary Gemini chat can create, edit, or delete notebooks, add or remove sources, and answer questions using a notebook's contents. It's on by default everywhere except the European Economic Area, where it starts switched off.

Does NotebookLM have an API? This is one of the most common questions, and the answer is split. Google's documentation offers no public, self-serve consumer API: you can't grab an API key from a settings page and script your personal notebooks. What does exist is an enterprise API, now branded Gemini Notebook Enterprise, sold standalone or as part of Gemini Enterprise (the platform Google folded Agentspace into). Its docs currently carry a Preview, Pre-GA banner despite an earlier release note calling notebook management generally available. It exposes REST endpoints to create, retrieve, share, batch-delete, and list recently viewed notebooks, manage and upload sources, and generate an audio overview, with US, EU, and global endpoints and enterprise controls like VPC Service Controls and, on the US and EU endpoints, customer-managed encryption keys. The gap developers keep hitting is stark: the product's own overview sells it as somewhere you "query, chat, or generate summaries," and query and chat are exactly what its documented methods don't offer. The new Gemini Connected App isn't an API either: it lets Gemini act on your notebooks inside a chat, not your own scripts. For a student or solo researcher, the practical takeaway is simple: the documented API is an enterprise feature, and unofficial community clients that drive the web app exist but can break whenever Google ships a change, which lately is often.


What Still Frustrates

A verified changelog should also verify what didn't change. Four structural problems survived the entire update wave.

Notebooks are still silos. Inside Gemini Notebook, your knowledge lives in per-notebook buckets, and chat works within one notebook at a time. The Gemini app's new Connected App can list your notebooks and answer from a notebook's contents in a chat, which helps, but Google hasn't documented a way to ask one question across everything you've ever saved, and there's no graph of connections across notebooks. If you study four subjects, you maintain four walled gardens, and insights from one don't surface in another.

There's still no capture layer for reading. Google has closed part of this gap: the mobile app can receive a website, PDF, or YouTube video shared to it from your phone, and the audio recorder announced on September 15, 2026 is now in the Android and iOS apps, where it records up to an hour and keeps the transcript, not the audio. Both are real improvements for anyone who learns by listening. The reading half is untouched. There's no highlighting on live web pages, no annotation while you watch a video, no way to mark the paragraph that mattered rather than filing the whole document. Web pages still enter as whole sources, and while you can paste a passage in as a note, the gap between "this one paragraph changed my mind" and "it's in my notebook" stays manual.

The limits got harder to predict, not just tighter. Fifty sources per notebook on the free tier sounds generous until a real literature review hits it. The bigger change is September 2's move to a compute budget: instead of knowing you have 50 chats today, you now have an allowance that drains faster when you ask for something expensive. Gemini Notebook warns you as you approach the wall, but you can no longer plan a study session around a number you know in advance.

The best features land on expensive tiers first. Cinematic videos launched Ultra-only and reached Pro weeks later; Google has never announced them for Free or Plus. Code execution, voice chat, and source suggestions from chat all started on Ultra too. Some of it trickles down (Google's voice chat instructions no longer mention Ultra), but Google rarely says when a lower tier catches up. The free tier today is more capable than the free tier of 2025, yet the distance between free and Ultra widened, and the rollout pattern consistently rewards the $99.99-and-up crowd first.

None of these are dealbreakers. They just define what a notebook is good for: deep work on a bounded set of sources you assembled on purpose. So where does that set come from?


Pairing NotebookLM with a Capture Layer

Every NotebookLM workflow has the same dependency: the quality of the notebook is the quality of its sources. Deep Research helps you cold-start a topic you know nothing about. But the most valuable sources for your learning are usually the ones you already found yourself, scattered across months of reading, watching, and browsing. Gemini Notebook can receive a whole page you share to it, but it has no way to capture the one paragraph that stopped you, or to build that habit across months of reading. That's not a missing feature so much as a different job, and it's the job a highlighter does.

The pairing works like this. As you read during the day, Glasp's web highlighter captures the passages that made you stop, on any web page, with your notes attached. For video, YouTube Summary gives you the transcript alongside the player so you can highlight the moments that matter with timestamps instead of vaguely remembering "somewhere in that two-hour lecture." Over weeks, this builds a record of what actually caught your attention, which is exactly the raw material a notebook needs.

When a project takes shape, you export those highlights as markdown or text and drop them into a notebook as a source. Now NotebookLM's chat, quizzes, and audio overviews run over the things you personally found worth keeping, not just whatever Deep Research scraped. The two tools are honestly complementary: Glasp is the wide-open capture net across your daily reading, NotebookLM is the deep synthesis engine for a bounded project. One is free and social, the other is Google-scale and private. Using both costs nothing.

We've written up the full pipeline, including how this fits with Deep Research-style agents, in our AI research workflow guide, and the video-specific version in turning YouTube videos into study notes.


Free vs Paid: Limits, Pricing, and Which Tier You Need

On September 2, 2026, Google started throwing out the way Gemini Notebook counts, beginning with personal accounts on the web and mobile. The old system gave you fixed daily allowances: 50 chats a day, 3 audio overviews a day, 10 Deep Research runs a month. For personal accounts, those are gone. In their place is a compute budget that, in Google's wording, factors in "the complexity of your prompt, the models and features you use, the length of your chat and specific features."

Three practical consequences:

  • It refreshes every five hours, not every midnight, and it runs against a weekly ceiling. Hitting the wall at 2pm no longer costs you the rest of the day, though reaching the weekly ceiling still stops you until it resets.
  • Cheap things are now genuinely cheap. A short factual question about one source barely moves the meter. A multi-source Cinematic Video Overview moves it a lot. Under the old caps, every chat counted the same against your daily allowance, however small.
  • You can queue work instead of losing it. On the web, when you're out of budget, Gemini Notebook will offer to generate a Video Overview or Slide Deck later and notify you when it's ready, which Google warns "may take a couple hours." It also suggests a cheaper output format when your first choice won't fit.

Settings, then Usage, shows what you've used against your weekly limit; the chat warns you as you near the wall ("You're almost at your AI usage limit. Limit resets at 3:00 PM"); and Studio fills in a bar showing the expected cost before you generate. That helps. What doesn't help is that Google has never published what one unit of compute buys, so you can't plan against a number you know in advance. The budget applies in the mobile apps as well as on the web; only the generate-later queue is web-only.

What survived the change are the structural caps, the multipliers between tiers, and the features that stay tier-gated. Google's English plans page has caught up: it now lists only notebook and source caps and points to a separate usage-limits page, though some translated versions still show the old daily caps, so don't trust a localized table. One thing that has not changed at all: you can't buy the consumer tool on its own, since every paid tier is bundled with a Google AI subscription (only the enterprise edition is sold separately).

LimitFree (Standard)Plus ($4.99/mo)Pro ($19.99/mo)Ultra (from $99.99/mo)
Notebooks100200500500
Sources per notebook50100300500 to 600
AI usage allowanceBaseline2x baseline4x baseline20x to 80x baseline (5x to 20x Pro)
Allowance resetsEvery 5 hours, against a weekly ceilingSameSameSame
Native code executionNot announcedNot announcedPromised in JulyYes
Cinematic Video OverviewsNot announcedNot announcedYesYes

Pricing context, because it moved twice recently: Google restructured Ultra at I/O 2026 in May, adding a $99.99 entry tier and cutting the top tier from $249.99 to $199.99. Then in June 2026, Google cut the Plus plan to $4.99 a month, with 400 GB of storage. These are US prices; local prices differ.

Students get a year free, and it's the best deal in the product. First announced on August 19, 2026 and repeated on September 15, the offer gives eligible US college students 12 months of Google AI Pro, normally $19.99 a month. Students in more than 140 other markets get Google AI Plus instead, normally $4.99 a month, with 400 GB of storage (a handful of markets, including Hong Kong, Macau, and Tunisia, are excluded, so check the offer page). You have until December 31, 2026 to redeem it, with a personal Google account, proof of enrollment, and an age of 18 or older. Read the fine print before celebrating: it requires a valid payment method up front and rolls into the paid rate automatically unless you cancel, so put a reminder in your calendar for month eleven.

Who should pay what:

Stay free if you're a casual user or working at course scale, and check the student offer first. A hundred notebooks at 50 sources each covers a typical course load with room to spare, and under the new compute budget the ordinary work of studying, asking questions of your own readings, is the cheapest thing you can do. Expensive generation is what drains the meter, so be deliberate about video.

Plus at $4.99 is the new sweet spot. Doubled source caps and twice the compute allowance for the price of a coffee. If you hit the five-hour wall more than once a month, this is the rational upgrade, and the June price cut made it an easy call.

Pro is for thesis-scale work: 100+ sources per notebook, study materials generated daily. Four times the baseline allowance is plenty for one person doing mostly text work.

Ultra is for teams and video production, not learners. Unless Cinematic Video Overviews are part of your job or you need thousands of queries a day, the $99.99+ tiers buy you very little studying.


Frequently Asked Questions

Did NotebookLM change its name to Gemini Notebook?

Yes. On July 16, 2026, Google renamed NotebookLM to Gemini Notebook, and old notebooklm.google.com links now redirect to notebook.google.com. It's the same product with the same notebooks, sources, and features, plus a new logo and a wider rollout of native code execution announced the same day. Google kept it as a standalone research tool rather than merging it into the main Gemini app, though the two now sync, and since October 23 the Gemini app can create, edit, and answer from your notebooks. Most people still type "NotebookLM" into search, so both names point to the same tool.

What are Gemini Notebook's usage limits?

Since September 2, 2026 there is no single number to quote. Gemini Notebook runs on a compute budget that depends on what you ask for: a short question about one source costs very little, a Cinematic Video Overview across ten sources costs a lot. The budget refreshes every five hours until you hit a weekly ceiling, and Settings, then Usage, shows what you've used against your weekly limit. The caps that are still fixed numbers are structural: 100 notebooks and 50 sources per notebook on the free tier, rising to 500 notebooks and 500 to 600 sources on Ultra.

Is Gemini Notebook free in 2026?

Yes. NotebookLM, now called Gemini Notebook, still has a free Standard tier with 100 notebooks and 50 sources per notebook, and it has the full 1M-token context window. What changed on September 2, 2026 is how the AI limits work: instead of fixed daily counts, the free tier gets a baseline compute allowance that refreshes every five hours against a weekly ceiling. Paid tiers multiply that allowance (Plus 2x baseline, Pro 4x, Ultra 5x to 20x Pro again) rather than add fundamentally different core features. Google offers the textbook catalog at no charge and announced Interactive Learning Overviews for all users. The exceptions are features that launched on paid plans and haven't been announced for free users, such as native code execution and Cinematic Video Overviews.

Is Gemini Notebook free for students?

Better than free. Google's student offer, first announced on August 19, 2026, gives eligible US college students 12 months of Google AI Pro at no cost, normally $19.99 a month, and students in more than 140 other markets 12 months of Google AI Plus, normally $4.99 a month. Redemption closes December 31, 2026. You need to be 18 or older, verify your enrollment, and use a personal Google account. It requires a valid payment method at signup and renews at the full price automatically unless you cancel first.

When did Gemini Notebook come out?

Gemini Notebook came out on July 16, 2026, as a rename of NotebookLM, not a new product. Google previewed it as Project Tailwind at I/O in May 2023, began testing it as NotebookLM with a small group of US users in July 2023, opened it to US adults in December 2023, and expanded it to more than 200 countries in June 2024. So if you're looking for a "Gemini Notebook release date," July 16, 2026 is the date of the rename; the product itself dates to 2023.

What's new in NotebookLM?

As of November 5, 2026, the latest changes are from October: hundreds of free textbooks you can add from the Add sources menu (October 29), notebook actions inside the Gemini app (October 23), guided co-creation for slide decks and Video Overviews (October 19), and short answer, multi-select, and fill-in-the-blank quizzes (confirmed October 16). September brought compute-based usage limits that refresh every five hours, real-time voice conversation with a notebook, a mobile audio recorder for lectures, Interactive Learning Overviews, notebooks for school accounts in the Gemini app, and notebook grounding in Google Docs. Before that: notebooks inside AI Mode in Google Search and Play Books ebooks as sources (August), the July 2026 rename, Deep Research, support for Sheets, Word, EPUB, images, and Drive-synced files, saved chat history, Data Tables, and editable slide decks with PowerPoint export. The full dated timeline is in the table near the top of this article.

Can I use Gemini Notebook inside Google Search?

Yes. Notebooks began rolling out to AI Mode in Google Search on August 19, 2026, in English, across every country Gemini Notebook supports except the European Economic Area. You can create, edit, and chat with a notebook from the search bar, and sources, renames, and custom instructions sync with the standalone app. Two catches: chats don't sync between the two, and notebooks that someone else shared with you won't show up in AI Mode. Google Play Books sources can't be used there either.

Is Gemini Notebook the same as notebooks in the Gemini app?

They're connected, not identical. Gemini Notebook, formerly NotebookLM, is the standalone research tool at notebook.google.com, with up to 50 sources per notebook on the free tier and the full Studio of outputs. The Gemini app has notebooks too, and Google describes them as combining the two products. Its own example: add class notes to a notebook, use Gemini Notebook to make a Cinematic Video Overview, then open the notebook in the Gemini app the next day and ask it for a study guide. Separately, the Gemini app's study notebooks build lessons around a diagnostic quiz, which our Gemini vs ChatGPT for studying comparison covers.

NotebookLM vs ChatGPT for studying: which is better?

They solve different problems. NotebookLM grounds every answer in sources you (or its Deep Research agent) put into the notebook, which keeps it honest and citable, and its quiz, flashcard, and audio outputs are built for studying. ChatGPT is a generalist: better at open-ended explanation, coding, and conversation, but you have to manage grounding yourself. For coursework built on a defined set of readings, NotebookLM's source-grounded design wins. For "explain this concept five different ways until one clicks," ChatGPT remains stronger. Many students sensibly use both. Our NotebookLM vs ChatGPT for studying comparison breaks it down task by task.

What are Cinematic Video Overviews?

Launched March 4, 2026, they're animated explainer videos generated from your sources, with Gemini 3 directing the narrative and Nano Banana Pro and Veo 3 producing the visuals. They look dramatically better than the standard slideshow-style Video Overviews. They reached Google AI Pro in March 2026, and Google's help page lists them as English-only and for users 18 and over. For learning value per dollar, the standard Video Overviews on the free tier deliver most of the same information.

Does NotebookLM work with web pages and YouTube videos?

You can add URLs and YouTube links as sources, and Deep Research can pull web sources in for you. What NotebookLM still can't do is capture while you read or watch: there's no live highlighting on pages, no transcript annotation during a video, and phone sharing sends only whole pages. If your learning starts on the open web, a capture tool like Glasp fills that gap, and you can export your highlights into NotebookLM as a source when a project firms up.

Can NotebookLM read Kindle books?

Not directly. NotebookLM accepts PDFs, Google Docs, Slides, Sheets, Word and PowerPoint files, plain text, Markdown, CSV, audio, images, websites, YouTube transcripts, and, since March 2026, EPUB files, but it can't open Amazon's proprietary Kindle format. Google's own answer for ebooks is Play Books: since August 27, 2026, eligible ebooks you've bought there can be added as sources. For books you read on Kindle, bring your reading in as text. If you highlight as you read on Kindle, Glasp's Kindle import pulls those highlights out of Amazon and lets you export them as markdown, which you then add to a notebook as a source. That way the notebook runs on the passages you actually marked, not the entire book. It's the same capture-then-synthesize pattern that makes NotebookLM stronger with any source.


Conclusion

Gemini Notebook in late 2026 is a genuinely different product from the one most people tried as NotebookLM in 2024 and 2025. The changes that matter for learners are the unglamorous ones: Deep Research and the free textbook shelf killing the cold-start problem, saved chat history, quizzes that remember your progress and now demand recall, a 1M-token context on the free tier, a free year for students, and a compute budget that stops punishing you for asking small questions. The cinematic videos will get the headlines; the retrieval practice features will get you through the exam.

What hasn't changed is the architecture of the thing. Gemini Notebook synthesizes what you give it, notebook by notebook, and the work of noticing, capturing, and collecting good material across your daily reading still happens upstream of every notebook you'll ever build. September's audio recorder proved Google understands the problem, but it solved it for lectures, not for the forty browser tabs you closed this week. Get that layer right and every Gemini Notebook feature gets better, because it's running on sources you actually chose.

That's the workflow worth building this year: capture as you read with Glasp's web highlighter, highlight lectures and talks with YouTube Summary, then export the best of it into a notebook when a project takes shape. Gemini Notebook keeps changing month to month, right down to its name and how it counts. A well-built source library is the part of your system that compounds no matter what Google ships next, or what it calls the notebook.

Start building your knowledge library

Highlight what matters as you read across the web. Save insights from articles, books, and YouTube videos in one place.

Get Started Free

Or highlight this page as you read it