Got My Tools

OCR PDF (Scanned to Text)

Extract text from scanned PDFs and photographed documents using on-device OCR — no sign-up, no upload, no file size limit.

Drop a scanned PDF or image here, or click to browse

Your files never leave your device. Everything runs locally in your browser — nothing is uploaded to a server, so there's no file size limit, no subscription, and no one but you ever sees what's in your file.

How it works

Upload a scanned PDF or a photo of a document. Each page is rendered as an image and run through an on-device OCR engine that recognizes characters directly from the pixels — the same underlying technique used by paid OCR services, just running locally in your browser instead of on their servers.

A note on the first run

The OCR engine (a few megabytes of code and language data) loads the first time you use this tool in a session. Your browser caches it, so it won't need to reload on repeat use in the same session.

Frequently asked questions

How is this different from PDF to Word?+

PDF to Word reads text that's already embedded in the PDF — it's fast but does nothing for a scanned page, which is really just a photo with no underlying text. This tool instead recognizes text directly from the image using OCR (optical character recognition), which works on scans and photos but is slower and can make occasional misreads, especially on low-quality scans or unusual fonts.

Why is this slower than the other tools?+

OCR is genuinely CPU-intensive — the first run also downloads the OCR engine and language data (a one-time cost per session, cached by your browser). Processing happens on your own device rather than a server, so speed depends on your device; a multi-page document can take a while.

How accurate is the extracted text?+

It depends heavily on scan quality — clean, high-contrast, well-lit scans of printed (not handwritten) text generally come out very accurate. Skewed, blurry, low-resolution, or handwritten documents will have more errors. Always proofread the result.

Can I OCR a plain image instead of a PDF?+

Yes — this tool accepts JPG and PNG images directly, not just PDFs.

Does this create a searchable PDF, or just text?+

Just the extracted text, downloadable as a .txt file (or copy it straight from the preview). It doesn't rebuild a new PDF with an invisible, searchable text layer behind your scanned images — that's a more involved feature we may add later.

Keep a backup of your original file. This tool processes everything locally in your browser, and we've tested it carefully — but no conversion tool handles every PDF perfectly. Always keep your original file and double-check important results before relying on them.