Convert scanned PDF documents into searchable files with selectable text. Recognize content in Spanish, English or both languages.
A free account is required to use OCR processing.
Convert scanned PDF pages into searchable documents with selectable text.
Sign in or create a free account to use SG Hub secure OCR processing.
Registration is free. Your PDF remains private and is processed temporarily.
or drag and drop it here
PDF · Maximum 25 MB
Upload a PDF containing scanned pages or text that cannot currently be selected.
Select Spanish, English or both languages according to the content of the document.
Choose the OCR mode and enable automatic orientation, straightening or cleanup when necessary.
When processing is complete, download the document with its new text layer.
OCR does not automatically convert the document into Word or reconstruct its layout as an editable file. The result remains a PDF.
This is the recommended mode. It preserves existing text and processes only pages that appear to require OCR.
It attempts to replace a previous OCR layer when the text is damaged, misaligned or contains significant errors.
It rasterizes every page and creates a new text layer. It can help when existing recognition does not work.
Text extraction works when the PDF already contains digital characters. OCR is used when the page is an image and the text does not yet exist as selectable information.
When you can already select and copy the text normally, the document may not require OCR.
The document is temporarily sent to SG Hub infrastructure because OCR recognition requires a specialized processing engine. The file is used to perform the requested operation and generate the result.
Download the PDF when it becomes available and keep your own copy. SG Hub does not operate as permanent storage or as a backup service.
Read the Privacy Policy →OCR can confuse letters, numbers, symbols and proper names. Do not use the result without reviewing it when the document contains important legal, financial, medical, academic or administrative information.
OCR PDF is a tool that recognizes text contained in images or scanned pages and adds a searchable and selectable text layer to the document.
Upload the document, choose the OCR language and mode, and process it. The result remains a PDF and receives a text layer that can be searched and selected when recognition is successful.
In the recommended mode, pages that already contain text are preserved and OCR is applied only where necessary. The overall appearance should remain similar, although small differences may occur.
You can currently process documents in Spanish, English or documents that combine both languages.
This mode preserves pages that already contain text and applies recognition only to pages that appear to be images or scans.
It attempts to replace an existing OCR layer when the recognized text contains errors, is misaligned or cannot be selected correctly.
It rasterizes every page and creates a new text layer. It can be useful when existing OCR is damaged, although it may change the visual quality of the document.
Yes. You can enable automatic orientation correction and straighten pages that are slightly tilted.
The tool accepts PDF files up to 25 MB. Large documents or files containing many images may require several minutes.
No. Accuracy depends on resolution, language, typography, contrast, page angle and scan quality. Review the result when the document contains important information.
Not completely. OCR adds a searchable and selectable text layer, but the document remains a PDF and is not automatically converted into an editable Word file.
Yes. The PDF is temporarily sent to SG Hub infrastructure to apply OCR and generate the searchable file.