Image to Text
Extract text from images free. Photos, screenshots and scans become copyable text with OCR — processed on your device, never uploaded.
The 10-second test: switch off your Wi-Fi (or turn on airplane mode) and use this tool anyway. It keeps working — because there is no server doing the work.
The technical check: open your browser's developer tools, go to the Network tab, and run the tool. Your file is never sent anywhere.
Measured live on this page — files transmitted: 0 · file data sent: 0 bytes
This counter hooks the browser's own networking functions, so it would rise the instant any file data left this page. The only thing this site ever transmits is the contact form, if you choose to send one.
Select files
or drag & drop — pasting works too (Ctrl+V)
Working…
Your file is ready!
Processed on your device — 0 bytes uploaded
Thanks — feedback received!
How to extract text from an image
Add a photo, screenshot or scan, click Extract text, and the words appear ready to copy — or download them as a .txt file. You can also just paste a screenshot with Ctrl+V.
Everything runs in your browser: the OCR engine downloads once (about 15 MB) and then works offline. Your images are never uploaded, which matters when you are reading text off an ID, a payslip or a private document.
What it reads well
Printed text in ordinary fonts, photographed or scanned straight and in reasonable light. Screenshots are close to perfect because the text is already crisp and perfectly aligned. Book pages, printed letters, signs and labels all work well.
What it will not read
Handwriting, at all. Very stylised or decorative fonts. Text at an angle, which loses accuracy quickly. Faint photocopies and low-contrast text on coloured backgrounds. And text that is genuinely too small in the source image — no amount of processing recovers detail that was never captured.
Getting a better result from a phone photo
Fill the frame with the text rather than photographing the whole page from a distance. Shoot straight on. Use indirect light so the page is not half in shadow. If a photo reads badly, the fastest fix is almost always to take a better photo rather than to try again with the same one.
Why it runs on your device
People extract text from payslips, ID documents, medical letters and private correspondence. The recognition engine downloads once, then runs on your own processor and works offline — nothing is uploaded, which is the only sensible way to handle documents like those.
Frequently asked questions
Does it work on photos taken with my phone?
Yes. Lay the page flat, get good light and shoot straight down. The built-in clean-up boosts contrast automatically, which handles most phone photos well.
Can it read handwriting?
No — this reads printed text. Handwriting, especially cursive, is not reliably recognisable by any free OCR engine.
Is my image uploaded anywhere?
Never. The recognition happens inside your browser on your own device. You can switch off your Wi-Fi after the page loads and it still works.
Can it read handwriting?
No. Printed text in ordinary fonts only.
Why is the text coming out wrong?
Usually the photo. Fill the frame with the text, shoot straight on rather than at an angle, and use even indirect light. Retaking the photo beats retrying the same one.
Does it work on screenshots?
Very well — screenshot text is already crisp and perfectly aligned, which is the ideal case.
Is my image uploaded?
No. Recognition happens on your own device, which is why it still works with the network off.