PDF OCR, extraction and AI tools
Make scans searchable with OCR and pull text, tables, images and links out of PDFs. AI tools are on the way.
Available now (9)
Coming soon (5)
About ocr & ai tools
OCR PDF adds a searchable text layer to scanned pages using an engine that runs in your browser. The language data downloads once from a public CDN, and your document is never uploaded. Extraction tools pull out images, tables, links, annotations and attachments.
AI tools such as a PDF summarizer and chat with PDF are coming soon. They’ll be opt-in, clearly labeled and grounded in your document with page references.
OCR & AI FAQ
Why does my scanned PDF produce no text?
Scans are pictures of pages with no text layer. Run OCR PDF to recognize the characters first.
Is my document uploaded for OCR?
No. Recognition runs in your browser. Only the language data is downloaded from a public CDN.
Will AI tools train on my documents?
No. When AI tools launch they’ll require opt-in, and documents won’t be used for model training.


