Image to Text (OCR) Image
Extract text from a photo, screenshot or scan using optical character recognition.
Image to Text (OCR) is a free online tool that extract text from a photo, screenshot or scan using optical character recognition. It runs entirely in your web browser using Canvas 2D, so files are processed on your own device and never uploaded to a server. There is no sign-up, no file size limit imposed by the site, no watermark and no paid tier.
- Price
- Free — no account, no quota, no watermark
- Category
- Image
- Where it runs
- In your browser, on your device
- Files uploaded
- None
- Technology
- Canvas 2D
- Settings
- None — it just works
- Works offline
- Yes, after the first visit
About Image to Text (OCR)
Optical character recognition turns pictures of words back into words. This runs Tesseract — the long-standing open-source OCR engine, originally from HP and maintained by Google for years — compiled to WebAssembly and served from this site, so your image is never uploaded and no third party is involved. Accuracy depends almost entirely on the input: crisp, straight, high-contrast text reads near-perfectly, while a blurry photo of a curved receipt in bad light will not.
How to use it
- Everything image to text (ocr) needs is on this page.
- Your input is processed locally and discarded when you close the tab.
Under the hood
| Runs on | Canvas 2D — does the pixel work |
Questions
Which browsers does this work in?
It relies on Canvas 2D, supported in current versions of Chrome, Edge, Firefox and Safari. Features needing camera, microphone or screen access will ask permission first, and that prompt comes from your browser rather than from this page.
What does Image to Text (OCR) use to do the work?
Canvas 2D does the pixel work — all of it running inside this page rather than on a server.