Can Gemini Notebook (NotebookLM) Read Scanned PDFs? Yes, in 2026

Gemini Notebook, the new name for NotebookLM, now reads scanned PDFs and images. What changed, what still goes wrong with scans, and how to check yours.

Short answer: yes. NotebookLM, which Google renamed Gemini Notebook on 16 July 2026, now reads scanned PDFs and image files. Google's help centre lists images as a supported source type, and when we re-tested in October 2026 a scanned PDF imported with text we could question and cite. Scans aren't the brick wall they were in 2025, but poor scans, old imports and a few edge cases still trip it up.

What Gemini Notebook reads in 2026

Google's "Add or discover new sources" help page lists the source types: PDFs, Word, text, Markdown, CSV and PowerPoint files, Google Docs, Slides and Sheets, web URLs, YouTube videos, audio files, ePub files, and images in formats including JPEG, PNG, TIFF, HEIC and WebP. Each source can hold up to 500,000 words or 200 MB, and a free notebook holds up to 50 sources.

That image support is what changed the scanned-PDF story. A scan is a picture of a page; Gemini Notebook now reads the text in that picture instead of looking only for a text layer.

What still goes wrong with scans

  • Poor image quality. Google's own page says "certain types of images may not work as well". Faint photocopies, phone photos at an angle and low-resolution faxes give any model less to read, and the answer quietly inherits the gaps.
  • Handwriting. Neat block capitals usually come through; cursive and hurried notes are unreliable. See can AI read handwriting in PDFs?.
  • Old imports. A scanned PDF you added before image support improved may still be stored as it was processed then. Remove it and add it again.
  • Lost Drive access. A source imported from Google Drive becomes inactive if you lose access to the file or it's deleted. It still counts toward your source limit but isn't referenced in answers.
  • Web pages. A source added by URL imports only the page's text: images, embedded videos and nested pages are skipped, and paywalled pages aren't supported.
  • Locked files. Password-protected PDFs still fail. Unlock a copy first.

How to check a scanned source in five minutes

  1. Ask a pinpoint question. Pick a fact that appears only on one scanned page, such as a date, figure or name, and ask for it.
  2. Compare with the page. Open the PDF and check the answer against the image. If it's wrong or missing, the page didn't read cleanly.
  3. Fix the weak pages. Rescan at 300 dpi, straighten skewed pages, or run the file through OCR to add a real text layer. Our guide to making a PDF searchable covers the free and paid routes.
  4. Re-add the source. Upload the improved copy and delete the old one so it doesn't use a slot.

Reading a scanned PDF without uploading it

If your scans live in Google Drive, SharePoint, a wiki or an email, an in-browser reader skips the upload step. Sidenote is a reading assistant for Chrome, Edge and Firefox that reads the PDF you have open, runs OCR on scanned pages on paid plans, and answers with a scroll-to-source citation: click it and the document scrolls to the exact sentence and highlights it. Claims it can't match to a real passage are dropped server-side, so a bad read shows up as "not found" rather than a confident guess.

Gemini Notebook vs an in-browser reader for scanned files

Gemini NotebookIn-browser reader (Sidenote)
Scanned and image-only PDFsRead, with quality caveatsOCR'd on paid plans, then cited
WorkflowUpload sources into a notebookRead the file where it already is
Verify a claimCitation to the sourceClick to the exact highlighted sentence
Audio and Video OverviewsYesNo
Best forSynthesising a set of uploaded sourcesReading and citing whatever you have open

Gemini Notebook is genuinely good at what it's for: pulling a set of sources into one notebook and working across them, with Audio Overviews, mind maps and reports on top. For scans you just need an answer from, with a citation you can check against the exact line, reading in place is quicker. See the full Sidenote vs Gemini Notebook comparison and our roundup of Gemini Notebook alternatives.

Frequently asked questions
Yes. NotebookLM, renamed Gemini Notebook in July 2026, now reads scanned and image-only PDFs, and Google lists images as a supported source type. Clean scans of printed text work well. Faint, skewed or handwritten pages can still read poorly, so check a few lines against the original before relying on it.
In effect, yes: it reads the text inside images and scanned pages rather than needing a text layer. Google doesn't call it OCR, and its help page warns that certain types of images may not work as well, so a poor scan can still come through with gaps.
Yes. Google renamed NotebookLM to Gemini Notebook on 16 July 2026. It's the same product at notebook.google.com, and old NotebookLM links redirect automatically.
Usually one of four things: the PDF is password-protected, the scan is too faint or skewed to read, the file came from Google Drive and you've lost access to it, or the source was added long ago and imported before image support improved. Remove the source and add it again, and test with a clear page first.
Often, yes, since it now handles images as sources. Results vary with the image, so for a chart or diagram you care about, ask about it directly and compare the answer with the figure. Images on web pages added by URL are not imported: only the page text is.
Install Sidenote (free)Sidenote vs Gemini Notebook
All guides
Ready when you are

Stop digging. Start asking.

Add Sidenote to your browser, open any page in your wiki, and ask it the question you’ve been Slacking the team about.

Free plan · No card required