Extract text from an image or PDF.
Simply choose your file. PourQui automatically detects whether it is an image or a PDF and extracts the text it contains.
Your files stay on your device and are not sent to our servers for processing.
Get text directly from an image or PDF
The tool automatically chooses the right method for your file. Images are read using optical character recognition (OCR). For PDFs, existing text is extracted directly; if a page is a scan, OCR takes over.
Choose your file
Choose a JPG, PNG, WebP or AVIF image, or select a PDF document.
The text is extracted
PourQui automatically determines the best way to read the contents of your file.
Copy or download
You can edit the result directly, then copy it or save it as a TXT file.
Private processing
Your image or PDF never leaves your device. The contents of your file are not sent to our servers to be read. This is particularly useful for letters, invoices, official documents or other files you prefer to keep private.
When should I extract text from an image or PDF?
Text extraction is useful when you want to quickly retrieve the contents of a document without retyping it. For example, you can use it with a photo of a letter, an invoice, a screenshot, an official document, a scanned page or a PDF whose text you want to copy.
Photo of a document
A clear photo of a letter, form or printed page can be turned into editable text using OCR.
Scanned PDF
If the PDF contains pages stored as images, character recognition can extract their text.
Text you can reuse
You can edit the result, copy it into another document or download it as a TXT file for easy reuse.
How can I get better OCR results?
A well-lit image that is large enough and taken as straight-on as possible makes character recognition easier. Where possible, avoid very small text, reflections, heavily blurred areas or pages photographed at an angle. The result remains editable so you can easily correct any remaining errors.
Frequently asked questions
What is the difference between a text-based PDF and a scanned PDF?
In a text-based PDF, characters are already stored as text and can be extracted directly. A scanned PDF mainly contains images of pages, so the tool uses character recognition instead.
Is OCR always perfect?
No. A clear, straight image of sufficient size gives better results. The tool preserves the original image as much as possible and only discards some small fragments that are clearly noise. It prioritises keeping sentences, addresses, dates and numbers to avoid losing useful information.
Can I edit the extracted text?
Yes. The results area remains editable so you can correct recognition errors before copying or downloading the text.
Are my documents sent to PourQui?
No. They stay on your device and are not sent to our servers for processing.