OCR PDF — Recognize Scanned Documents & Images
Text recognition in 100+ languages with tesseract.js — 100% free and runs in your browser
Drop PDF or image to OCR
or click to browse · PDF, PNG, JPG, WebP · max 150 MB
The scan image stays untouched; an invisible text layer is added so text becomes selectable and searchable.
Add a PDF to continue.
Feeding PDFs to an AI support agent?
helpGPT answers your customers' questions from your own docs, with citations and honest refusals.
Make scans searchable without touching the image
Pick the recognition language and run — the page image stays exactly as scanned while an invisible text layer is added on top, so text becomes selectable and searchable. The engine downloads on first run.
Safe for scans and archives
Recognition adds a searchable text layer over your scanned image locally, so court filings, old letters and patient files stay on your device.
How to oCR PDF — Recognize Scanned Documents & Images
- 1Upload your scanned PDFUpload your image-based or scanned PDF.
- 2Select languageChoose the primary language of the document for best OCR accuracy.
- 3Run OCRClick "Make Searchable". Each page is processed locally — time depends on number of pages.
- 4DownloadDownload the PDF with an embedded text layer. Text is now selectable, copyable, and searchable.
Frequently asked questions
Which languages are supported?
English plus many European and Asian languages, depending on the recognition model loaded.
Does OCR change my scan?
No — the page image stays; an invisible text layer is added on top so text becomes selectable and searchable.