What do I get back from OCR Image?

The result is TXT, offered as a download the moment the work finishes. Multiple results come back together rather than as fifty separate save dialogs.

Is there a file size limit?

A single file may be up to 100 MB, and a batch up to 50 files. Those are guardrails rather than a paid tier — the work happens on your machine, so an enormous document is limited by your own memory before it is limited by us.

Is it safe to use for a document with personal details in it?

That is the design goal: the document stays on your device, so a statement, a contract or an ID photo is never transmitted for processing. Nothing here needs an internet connection once the page has loaded, apart from engines that fetch their own model data.

Will it work on a phone?

Yes. The layout adapts to a small screen and the processing runs in the mobile browser, so a photo or a downloaded document can be handled on the device it arrived on.

OCR Image

Extract text from photos of documents.

Drop scanned PDFs or photos here

or click to browse — .jpg, .jpeg, .png, .webp, .gif, .bmp, .svg, .tiff, .tif, .heic, .avif · up to 20 files

OCR languages

EnglishHindi

OCR runs fully in your browser with Tesseract WASM — a typical page takes 5–15 seconds. The language model is fetched once from the Tesseract CDN and cached afterwards. Handwriting and rotated pages reduce accuracy; for best results supply straightened scans at 200–300 DPI.

Add a file first.

Loading tool…

About OCR Image

OCR Image is here for reading and pulling content out of files: extract text from photos of documents. It takes JPG, JPEG, PNG and 8 more and produces TXT. Files up to 100 MB each, 50 at a time, and the work happens on your own machine rather than on a server.

Useful when the job is reading and pulling content out of files and you would rather not install software, join a queue or hand the file to a stranger.

How to use OCR Image in 3 steps

Drop the picture on the page — JPG, JPEG, PNG and 8 more works here, up to 100 MB.
Set the OCR languages (English is ticked by default) — English is ticked by default.
Press Run OCR and download the TXT result.

What you get with OCR Image

Accepts JPG, JPEG, PNG and 8 more in one go
Recognition with Tesseract, in the tab you are using
Runs in your browser — the file is never uploaded
Free to use, with no signup and no account
No watermark or logo added to your output
Works on desktop and mobile, no install

OCR Image: questions

What do I get back from OCR Image?: The result is TXT, offered as a download the moment the work finishes. Multiple results come back together rather than as fifty separate save dialogs.
Is there a file size limit?: A single file may be up to 100 MB, and a batch up to 50 files. Those are guardrails rather than a paid tier — the work happens on your machine, so an enormous document is limited by your own memory before it is limited by us.
Is it safe to use for a document with personal details in it?: That is the design goal: the document stays on your device, so a statement, a contract or an ID photo is never transmitted for processing. Nothing here needs an internet connection once the page has loaded, apart from engines that fetch their own model data.
Will it work on a phone?: Yes. The layout adapts to a small screen and the processing runs in the mobile browser, so a photo or a downloaded document can be handled on the device it arrived on.