NotebookLM shipped 6 major updates in 6 months. Cinematic Video Overviews, Slide Revisions with PPTX export, Data Tables, Deep Research, 1M-token chat, and custom personas. This page tracks every release with what changed, why it matters, and how to use it — updated monthly. Your go-to source outside Google's own blog.
Mar 2026: Cinematic Video Overviews, Slide Revisions, 10 infographic styles, EPUB support, PPTX export, improved flashcards/quizzes, artifact creation in chat. Jan 2026: Custom Chat Personas, saved conversation history, 1M-token context for all plans. Dec 2025: Gemini 3 engine upgrade, Data Tables. Nov 2025: Deep Research, Word & Sheets as sources. Oct 2025: 1M-token context window, custom goals, Notebook-to-Gemini connection.
Click any row to jump to full details
| Date | Update | Key Features | Guide |
|---|---|---|---|
| Mar 20, 2026 | Studio Expansion | Cinematic Video Overviews, Slide Revisions, 10 infographic styles, EPUB, PPTX export, improved flashcards/quizzes, artifact creation in chat | Details ↓ |
| Feb 18, 2026 | Slide Editing + Export | Prompt-based slide editing (Pencil UI), PPTX download, Gemini 3.1 Pro | Details ↓ |
| Jan 22, 2026 | Smarter Chat | Custom Chat Personas, saved conversation history, 1M-token context for all plans, 6× multi-turn capacity | Details ↓ |
| Dec 19, 2025 | Gemini 3 + Data Tables | Gemini 3 engine, Data Tables, improved reasoning, Notebook → Gemini connection | Details ↓ |
| Nov 14, 2025 | Deep Research + Sources | Deep Research agent, Word (.docx) + Sheets as sources, Discover Sources (web + Drive search) | Details ↓ |
| Oct 22, 2025 | 1M Context + Goals | 1M-token context window, custom goals per notebook, mobile app camera, flashcards/quizzes on mobile | Details ↓ |
Newest first. Each entry includes what changed, why it matters, and links to our guides.
Immersive, deep-dive videos with fluid animations and rich visuals, powered by Gemini 3, Nano Banana Pro, and Veo 3. Goes beyond narrated slides to create documentary-quality visual narratives. Ultra plan required.
Revise presentation content, ask for changes, or fix issues on both desktop and mobile. Submit stylistic or factual feedback per slide; slides regenerate as a new deck in Studio. Now works on mobile.
Manually choose from: Sketch Note, Kawaii, Professional, Scientific, Anime, Clay, Editorial, Instructional, Bento Grid, and Bricks. Auto-select still available by default.
Upload EPUB files (standard eBook format) directly as sources. Interact with long-form digital books without conversion.
Download generated slide decks as PowerPoint files (in addition to PDF). Slides are image layers inside the PPTX container — presentable as-is, but complex layout edits need external tools.
Progress saved across sessions. Mark cards as "Got it" or "Missed it." Shuffle decks. New results screen to rerun missed cards. Delete individual cards or questions. Works on web and mobile.
Transform chat conversations into Audio Overviews, Video Overviews, reports, and more — directly from the chat panel. No need to switch to Studio.
Target a specific slide with instructions like "fix slide 3" or "make slide 5 more concise." Queue multiple edits before regenerating. Only edited slides update — the rest stay intact.
Initial launch of PowerPoint export for slide decks. Expanded and refined in March update.
Engine upgrade from Gemini 3 to 3.1 Pro. Improved slide customization and visual quality.
Ability to add custom banner images for notebook customization. Observed in testing; not yet fully rolled out.
Set a specific goal, voice, or role for each notebook. Tell NotebookLM to act as a teacher, game master, executive coach, or any persona. The AI adapts its responses to match.
Conversations are now automatically saved and kept private. Close a session, resume later without losing context. Delete history at any time. In shared notebooks, your chat is visible only to you.
Full 1 million token context window of Gemini enabled across all plans (free included). Multi-turn conversation capacity increased 6×. 50% improvement in user satisfaction with large source collections.
NotebookLM now automatically explores sources from multiple angles, going beyond your initial prompt to synthesize findings into a single, more nuanced response.
The "brain" behind NotebookLM changed. Significantly improved reasoning, multimodal understanding, and less hallucination. Better at connecting disparate dots across complex texts.
Scan uploaded documents and synthesize variables into structured tables. Convert qualitative text into quantitative grids. Export to Google Sheets with one click. Ideal for competitive analysis, curriculum mapping, and literature reviews.
Add NotebookLM notebooks as a source directly inside the Gemini app. Gemini answers questions grounded in your notebook's content — building a "second brain" that Google's most powerful AI can access.
An autonomous research agent. Give it a topic — it creates a research plan, searches hundreds of quality web sources, and compiles a citation-backed report you can import as a notebook source. Free: 10 sessions/month.
Upload Microsoft Word documents and Google Sheets directly. No more converting to PDF first. Sheets bring structured numerical data alongside unstructured text.
Fast Research: search the web for relevant sources to add. Deep Research: automated synthesis. Drive search: find existing documents without leaving NotebookLM.
Flashcards and quizzes added to mobile app. Audio Overviews with offline playback. Camera for quick image-to-source upload.
Massively expanded processing capacity. Analyze entire book-length document collections in a single conversation. Foundation for all subsequent upgrades.
Early version of what became Custom Chat Personas in January. Set notebook-level goals that orient all AI responses toward your specific project needs.
New structure: Free ($0), Plus (~$14/mo), Pro ($19.99/mo), Ultra ($249.99/mo). Student discount: $9.99/mo. Enterprise: $9/license/mo.
Cross-source synthesis, multimodal extraction, slide optimization, Studio customization, troubleshooting diagnostics, and advanced multi-AI workflows — for researchers, business professionals, and educators.
Category Bundle — one-time access
Get Category Bundle — $19.99 All-Access — $88.99 one-timeSix major updates from Oct 2025 to Mar 2026: 1M-token context (Oct), Deep Research + Word/Sheets (Nov), Gemini 3 + Data Tables (Dec), Custom Personas + saved history (Jan), Slide Revisions + PPTX (Feb), and Cinematic Video + 10 infographic styles + EPUB (Mar). See the full timeline above.
Yes. Since February 2026, you can revise individual slides without regenerating the entire deck. Submit stylistic or factual feedback per slide. Also available on mobile since March 2026. See our Pencil UI & Revisions guide.
Launched March 2026, these are immersive deep-dive videos with fluid animations and rich visuals, powered by Gemini 3, Nano Banana Pro, and Veo 3. They go beyond narrated slides to create documentary-quality visual narratives. Requires the Ultra plan ($249.99/mo). Standard Video Overviews remain available on all plans.
Yes, since November 2025. Deep Research acts as an autonomous agent: give it a topic, it searches hundreds of web sources, compiles a citation-backed report, and lets you import findings as notebook sources. Free tier: 10 sessions/month.
Within 48 hours of each major Google release. We cross-reference the official Google Workspace Updates blog, 9to5Google, and hands-on testing. Minor updates are batched monthly. Bookmark this page and check back after any Google announcement.
Free ($0, 100 notebooks, 50 sources, 50 chats/day), Plus (~$14/mo), Pro ($19.99/mo, 300 sources), Ultra ($249.99/mo, Cinematic Video, watermark-free). Student: $9.99/mo. Enterprise: $9/license/mo. Full breakdown on our Pricing & Limits page.
No. Google's privacy policy states that personal data and uploaded content are not used to train AI models. Your notebooks remain private.