Popular OCR tools
Choose a task. Heavy OCR libraries and language models load only after you select a file.
Photo to text
Recognize printed text from a photo locally.
📄PDF OCR
Recognize text on selected pages of a scanned PDF.
🔍Searchable PDF
Create a PDF with page images and an invisible text layer.
🌍Polish OCR
Recognize Polish characters and printed text.
✨Deskew scan
Set the angle of skewed text lines.
▦Image table to Excel
Correct the grid and save an XLSX workbook.
⬇️OCR to DOCX
Create a local Word document with paragraphs and page breaks.
📊OCR quality report
Summarize confidence, time and pages needing correction.
All categories
Image to text
OCR for photos, screenshots and images.
🌍OCR languages
Polish, English and additional models.
📄PDF OCR
Scanned PDFs, page ranges and text.
🔍Searchable PDF
Add a local searchable text layer.
✨Scan enhancement
Rotate, deskew, improve contrast and clean scans.
▤Document layout
Regions, columns, lines and words.
✍️Text cleanup
Join lines and clean OCR output.
▦Tables and data
Experimental extraction of tables and fields.
⬇️Export
TXT, DOCX, PDF, JSON, CSV and hOCR.
📊OCR reports
Confidence, errors and reference comparison.
Private browser OCR
Skan uses a WebAssembly OCR engine in a Web Worker. The document does not need to be sent to a conversion server. PDF pages are rendered locally, and the result can be corrected before export.