Image to Text (OCR)
Pull the text out of a photo or screenshot — free, and everything happens in your browser.
Your image is never uploaded. The OCR engine itself downloads once from a CDN the first time you use a language, but your photo stays on your device the whole time.
Drop an image here, or choose files
JPG, PNG, WEBP or BMP — add more than one to extract text from all of them at once.
Frequently asked questions
Is my image uploaded anywhere?
No. The recognition runs entirely inside your browser using an open-source OCR engine (Tesseract) compiled to run on-device. The only network request is the one-time download of that engine and the language data itself, from a CDN — your image and the text extracted from it never leave your device.
How accurate is the text it gives me?
It works best on clear, well-lit, printed text — documents, screenshots, signs, book pages. Accuracy drops with handwriting, blurry photos, low contrast, or heavily stylized fonts. Straightening and cropping the photo first (our Scan to PDF tool can help) usually improves results.
Can I extract text in a language other than English?
Yes — pick the language from the dropdown before extracting. Choosing the right language matters: running English text through an Arabic model (or vice versa) will produce garbled results.
Can I process more than one image at once?
Yes. Add as many images as you like — they're processed one after another, and the text from every image is combined into a single result you can copy or download.
Is it free, with no limits?
Yes. No account, no watermark, and no limit on how many images you can process.