OCR PDF
Recognizes text in scanned pages across 126 languages.
OCR PDF recognises the text in scanned pages with Tesseract, in 126 languages with automatic detection, and writes it back as a searchable text layer under the scan. The recognition engine downloads once as program code; your scan stays on your device.
OCR PDF recognizes the text in scanned pages and adds an invisible, searchable text layer over the original images. The result is a PDF whose text you can select, copy, and search. OCR PDF is one of UnboundPDF's 53 free browser-based PDF and image tools: it runs on your own device with no upload, no account and no watermark, and reports what it measured on the output.
How to use OCR PDF — steps & common uses
What people use OCR PDF for
Anyone with a scanned PDF they cannot search or select — turning pictures of text into a searchable document, on their device.
- Make a scanned PDF searchable
- Select text in a scanned contract
- Search an old scanned book
- Copy text from a photographed page
- Prepare a scan for text export
Editing a scan, not just making it searchable? See how to edit text in a scanned PDF.
How to use OCR PDF
- Add your scanned PDF; the page images are processed on your device.
- Pick the document's language for the most accurate recognition.
- Click Run OCR to recognize the text page by page.
- Preview and download the searchable PDF, or grab the recognized text as a .txt file.
Good to know: The OCR engine is about 14 MB, downloaded once from unboundpdf.com on first use and then cached; the document image itself never leaves your device.
Questions about OCR PDF 8
Are my files uploaded to a server?
No. UnboundPDF processes PDFs locally in the browser — documents are not uploaded to a server. We have no backend that receives, stores, or scans your files.
Does my document get uploaded for OCR?
No. Recognition runs in your browser and your document image stays on your device. The recognition engine is about 14 MB, downloaded once from unboundpdf.com the first time you use OCR and then cached by your browser, so only the first run needs a connection.
What does the output look like?
It is a searchable PDF: your original page images with an invisible text layer on top, so the text can be selected and searched. You can also download the plain recognized text.
Why is some recognized text wrong?
Accuracy depends on scan quality. Clear, high-resolution scans in the selected language give the best results, while blurry or skewed pages produce more errors.
Does OCR lower the quality of my scan?
No. Your original page images are kept exactly as they are — OCR only adds an invisible, selectable text layer on top.
Which languages can it read?
126, grouped by script with a search box. Pick the document's language — or several, joined together — for the best accuracy, or let auto-detect suggest one from the scan.
Is my document sent to a cloud OCR service?
No. Recognition runs entirely on your device; the engine loads once from this site and then works in the tab.
How many languages does OCR support?
126, grouped by script with a search box, plus auto-detect to suggest the right one from the scan itself. Measured accuracy on our own test fixtures: Polish and Turkish 100%, Vietnamese 99.88%, Simplified Chinese 96.46% on a representative fixture (89.95% on a dense-text fixture) — your scan's own quality decides yours.
Read more
How your files are handled
The work runs on your own device, inside the browser tab — so there is no server to send your document to.
- Nothing is uploaded. We have no backend that receives or stores documents, so we cannot see your files during processing or after.
- Your device does the work. Large documents are handled in stages, pages are rendered as you reach them, and each job is checked against your device before it starts — so a long run takes longer on a phone than on a laptop, nothing is queued behind other people's jobs, and you can stop a run at any point without touching your original file.
- No account and no watermark. The output is a clean file you can use anywhere, with no sign-up and no hourly cap.
OCR note: The recognition engine loads from this site the first time you run it, so the first scan takes a moment. It is served from us, not a third party, and your PDF never leaves your device.
More optimize tools
Other free PDF utilities that work the same way — in your browser, no sign-up.