OCR PDF online
Turn scanned pages into searchable, selectable text you can copy and export.
MarqPDF reads the text off a scan and adds a real, invisible text layer under the page image, so the PDF looks the same but you can search it and copy from it.
Make a scanned PDF searchable
MarqPDF adds an accurate, invisible text layer over your scan so it is searchable and the text is selectable. See make a PDF searchable.
Photos and phone scans too
Upload a photo of a document and MarqPDF straightens the text into a searchable PDF, ready to email or file.
Extract text or export to Word
Pull the recognised text out, or convert to Word. See scanned PDF to Word and extract text from a PDF.
Frequently asked questions
What does OCR do?
OCR (optical character recognition) reads text out of an image or scan and turns it into real, selectable, searchable text.
Can I get the text into Word?
Yes. Convert the scan to a .docx with scanned PDF to Word and edit it there.
Which languages are supported?
OCR handles common Latin-script languages, with more on the way.
Do it from code or an AI agent
The same tool is in the MarqPDF API as POST /v1/ocr, and in MarqPDF's MCP server as ocr_pdf for Claude, Cursor and other AI agents.
curl https://marqpdf.com/v1/ocr \
-H "Authorization: Bearer $MARQPDF_API_KEY" \
-H "Content-Type: application/json" \
-d '{"file": "file_…"}'API reference · Use it from an AI agent (MCP) · JavaScript and Python SDKs · Chain it with other steps