Search a pile of scans like it's Google.
Drop the scans, type a query, get every hit - file, page, snippet. Free, no signup.
Drop the whole pile - OCR starts right away
Scans, faxes, photos - up to 10 files, 200MB each. Nothing is searchable? It will be.
No pile at hand?
Five fictional scans. Try searching Henderson - it's in three of them.
Search the whole pile in one query
Type a name and see everywhere it appears across the pile - file, page, and highlighted snippet - and each file also downloads back as a searchable PDF.
Paralegals and litigation support
"Find every mention of the Henderson account" across a production set - with page numbers you can cite.
Clerks and records officers
Decades of scanned minutes and permits, searched in one pass instead of opened one by one.
Journalists and investigators
A records-request dump of scanned memos becomes searchable the moment it lands.
Fictional samples, free to reuse: Typewriter memo (1994) (PDF) · Faxed order form (PDF) · Council meeting minutes (PDF) · Contract excerpt (PDF) · Handwritten note (PDF)
From the blog
The real unit of scanned paper is the pile, not the file
Searching and splitting scanned piles, with screenshots.
Read the postQuestions people with boxes of scans ask
Up to 10 files per session in the free tool, up to 200MB each. A free DocuPipe account raises those limits substantially.
Yes. Rotated and skewed pages are straightened automatically before recognition, and the OCR layer is built for fax-quality input - that is most of what this engine reads all day.
Printed text reads reliably; handwriting depends on the hand. Clear notes often work - the handwritten sample in the pile is there so you can see for yourself.
The OCR runs on DocuPipe servers over an encrypted connection; the searching happens entirely in your browser against the returned text, so queries are never sent anywhere. Files are processed on SOC 2 and ISO 27001 certified, HIPAA compliant infrastructure and never used to train models.
Yes - DocuPipe ingests entire archives, OCRs and classifies every document, and extracts the fields you care about.
Run it at scale
Make the whole archive permanently searchable.
DocuPipe ingests whole archives, OCRs and classifies everything, and extracts the fields into data your systems can query.
Free tier included. Takes about a minute to set up.
SOC 2 certified · ISO 27001 · HIPAA compliant · Encrypted in transit and at rest · Never used to train models