All tools
OCR PDF
Extract text from scanned PDFs locally in your browser.
Your files stay on your device. Processing happens locally in your browser — nothing is uploaded.
How it works
- Select a scanned PDF — drag it into the drop zone or click to browse.
- Optionally limit the page range; fewer pages finish faster.
- Click Extract text and let the recognition run on your device.
- Review the preview, then copy the text or download it as a file.
Why local processing?
OCR PDF processes your file inside your browser, on your own device. Your document is not uploaded to our servers. The browser may download code needed to run the tool, but those requests do not contain your file.
Check it yourself: open your browser’s network tab while a file is being processed — your document never appears in any request.
Frequently asked questions
- Are my scanned pages sent to a server for OCR?
- No. Recognition runs in your browser with Tesseract.js. The first run downloads the OCR engine and its English language model from this site — you may see those requests in the network tab — but your PDF and its pages are never transmitted anywhere.
- Is there a limit on file size or page count?
- Each file can be up to 200 MB. Processing happens in your browser and also depends on available memory. Large or complex files may be slow or exceed your device’s resources even below this limit.
- Can I run OCR on GDPR-sensitive documents here?
- The scans are processed entirely on your device. Nothing is transferred to or stored on a server, so there is no server-side processing of personal data to worry about.
- How accurate is the recognition?
- It depends on the scan. Clean, high-resolution scans of printed text work well; low-resolution scans, skewed pages, unusual fonts, and handwriting reduce accuracy. Treat the output as a draft and proofread anything important.
- Which languages are supported?
- English only in this first version. The language model runs locally on your device, and additional languages are not available yet.
- My PDF already has selectable text — do I need OCR?
- No. If you can already select the text, OCR would only re-read a picture of it, which is less accurate than the text layer that is already there. The tool detects this and warns you; use PDF to Word or plain copy-and-paste instead.
Related tools
- Scanned PDF to Word — Recognize text from scanned or image-only PDFs into an editable Word document.
- Searchable OCR PDF — Add a searchable text layer over a scanned PDF — search and copy.
- PDF to Word — Convert a text-based PDF into an editable Word document — no OCR.