Spanish PDF OCR, without uploading the file
Spanish text recognition with accents and ñ, running in your browser. Ideal for scanned Latin American documents.
Sent to servers: 0 BNothing left your device
About this tool
Generic OCR is usually tuned for English and mangles accents, the ñ and opening marks (¿ ¡). Here the Spanish model is loaded alongside English, so a Spanish document — or a mixed one, as technical reports often are — is recognized with its spelling intact.
That matters most for redaction: if OCR turns "Peña" into "Pena" or breaks an ID number in two, the detector can miss it. With the right model, ID numbers, tax IDs and names come through whole and can be hidden.
How it works
- 1
Drop the scanned Spanish PDF.
- 2
Press "Extract text with OCR".
- 3
Review the detected personal data and copy the Markdown.
Questions
- Which languages does it recognize?
- Spanish and English together, which covers most documents in the region. Other languages would need extra models.
- Does it keep accents and ñ?
- Yes, with the Spanish model loaded. In low-quality scans accents are the first thing lost: review the result.