Saltar al contenido principal

OCR PDF & Images

Extract real, searchable text from scanned PDFs and images. Runs entirely in your browser.

Processed in your browser — files never uploaded

Drop a scanned PDF or image

or browse from your computer

Supports PDF, PNG, JPG, WebP, BMP · max 50 MB

Cómo OCR PDF & Image

Turn scanned PDFs and images into real, searchable text. Our browser-based OCR uses Tesseract — no uploads, no signups, and no per-page limits. Output as a .txt file or a fully searchable PDF that looks identical to the original but lets you select, copy, and search the text.

  1. 1

    Upload your file

    Drop a scanned PDF or image (PNG, JPG, WebP, BMP). Files up to 50 MB are supported.

  2. 2

    Pick a language

    Choose the language of the text in your document. The first run for each language downloads a small model (~10 MB).

  3. 3

    Run OCR

    Click Run OCR. Each page is rendered, then recognized in your browser using Tesseract.js.

  4. 4

    Copy, download, or save as searchable PDF

    Copy the text to your clipboard, download as .txt, or download a searchable PDF that preserves the original layout.

Consejos Pro

  • •Higher-resolution scans yield much better OCR accuracy. 300 DPI is the sweet spot for text documents.
  • •Pick the right language — using English on a French document will produce garbled text.
  • •For multi-language documents, run OCR once per language and combine the results.
  • •The searchable PDF preserves the original page image and adds an invisible text layer behind it. Search and copy-paste both work in any PDF viewer.
  • •If a page has very dense text, try increasing the scale (resolution) before re-running.
  • •OCR confidence is shown per file. Below 70% means accuracy is questionable — improve the source scan.

Preguntas Frecuentes