Image to Text (OCR)
Extract text from any image or screenshot, free and in your browser. OCR with no upload, no sign-up — your image never leaves your device.
Drop an image here, or click to choose
processed on your device · nothing is uploaded
your image never leaves your browser
How to convert an image to text
Drop an image onto the box above, or click to choose a file. On the first run your browser downloads the OCR model (this happens once), then it reads the text and shows it in a box you can copy or download as a .txt file. Nothing is uploaded — it all happens in your browser.
Tips for better OCR results
Use the sharpest, highest-contrast version of the image you have. Straighten skewed scans, crop out clutter, and make sure the text isn't tiny. Dark text on a light background reads most reliably. If the result has gaps, try a larger or clearer image.
Questions
Is it private? Where does my image go?
Yes — it runs entirely in your browser. The OCR engine (tesseract.js) and your image are processed on your device, so nothing is ever uploaded to a server. The image never leaves your computer or phone.
Why is the first run slower?
The first use downloads the OCR language model (a few megabytes) to your browser. Your browser caches it, so after that the recognition is fast and works even offline.
What kinds of images work best?
Clear, high-contrast images of printed or typed text work best — screenshots, scans, photos of documents, signs, and receipts. Very small, blurry, skewed, or handwritten text is harder and may not come out cleanly.
Is there a file-size limit or watermark?
No. There is no account, no watermark, and no size paywall. Because everything happens locally there is nothing for us to meter — but very large images take longer to process in the browser.