OCR PDF
120+ language optical character recognition with layout-aware output.
Make scanned PDFs searchable.
OCR PDF runs optical character recognition across scans and image-only PDFs, producing a file that looks identical but is now fully searchable and selectable. Sable recognises 120+ languages, understands columns and tables, and preserves the original page image so nothing visual changes — only the invisible text layer.
- Batch processing
- API access
- Encrypted transport
- No file retention
What people use OCR PDF for.
Make a decade of scanned invoices searchable in your DMS.
Select text from a scanned book chapter to quote it.
Prep scans for Chat with PDF, Summarize, or Extract Data.
Turn scanned exhibits into searchable evidence.
Three steps, no learning curve.
Built for people who care about their documents.
Including Arabic, Chinese, Japanese, Korean, Hindi, Cyrillic, and Hebrew.
Columns and tables come back with reading order preserved.
The page image is unchanged — the searchable text sits underneath.
Neat handwriting is recognised on best-effort mode.
Your documents belong to you.
Sable is designed around a single principle: your files are yours. We never train on them, never sell them, and never keep them longer than we need to.