Extract text from an image (OCR)
A photo of a page, a screenshot of a message, a picture of a receipt or a whiteboard — this tool reads the text in it so you can copy, edit or search it. Pick the language for best accuracy, add one or many images, and get the text on screen with a copy button plus a .txt download. Recognition runs on your device with an open-source OCR engine: nothing is uploaded.
How to use the Image to text (OCR) tool
Select or drag your images.
Choose the language of the text.
Click “Extract text”, then copy it or download the .txt.
Your files stay on your device
This tool runs entirely in your browser using JavaScript and WebAssembly. There is no upload step and no server processing — open your network panel and check: zero document data is transmitted. It even keeps working offline once the page has loaded.
Frequently asked questions
How accurate is the OCR?
Very good on clear, well-lit photos and screenshots of printed text. Blurry photos, handwriting and very small text lower accuracy — crop tightly, keep the page flat and choose the right language.
Does it work with photos taken on a phone?
Yes. Small images are upscaled automatically before recognition, which helps with phone photos. For best results avoid shadows across the text.
Is my photo sent to a server?
No. The OCR engine downloads once and runs inside your browser — the image itself is never transmitted. That is why it is safe for IDs, contracts or private messages.
Is it safe to use this tool with confidential documents?
Yes — and verifiably so. PDFAgent has no upload step: your file is processed by JavaScript running in your own browser and never leaves your device. You can open your browser’s network panel (or even go offline after loading the page) and confirm that no document data is transmitted.