Lector
— convert a document
API key (kept in this browser only)
Drop a document here
or click to choose — PDF, scan or photo (several photos become one document), Word, Excel, RTF, HTML
What do you want out of it?
Editable Word document
Rebuilt page by page on the source's paper and typeface
PDF
Word, Excel, RTF or HTML converted; a scan comes back searchable
Redacted PDF
Sensitive data blacked out and cut from the text layer
Fillable PDF
Blanks, signature lines and tick boxes become fields anyone can fill in
Plain text
Everything the document says, as a .txt file
Structured data
Amounts, dates and fields as JSON, with its arithmetic checked
Mark words the OCR probably misread as tracked changes
Rebuild dense landscape pages as tables
— schedules and financial tables become real Word tables; leave off for drawings and survey plats, which look the same to a machine
More options
Reading (structured data)
auto — classify, then run everything
financial statements
invoice
receipt
signatures — is it signed?
checkboxes
fields (label: value)
fillable fields — what's blank?
sensitive data
Region
server default
Recognition language
identify it from the first pages
default (English + Chinese)
Latin (fr, es, de, it, pt…)
Devanagari (hi, mr, ne)
Arabic (ar, fa, ur)
Cyrillic (ru, uk, sr)
Japanese
Korean
Tamil
Telugu
Convert