Image to Text – Extract Text From an Image Online
About Image to Text
Add a screenshot, photo or scanned page and get the text as something you can copy or save. The OCR engine runs entirely in your browser — the image is never uploaded.
Optical character recognition (OCR) reads the letters in a picture and turns them back into editable text. This tool uses Tesseract, a mature open-source OCR engine compiled to WebAssembly, so the whole process happens on your device: the engine and its English language data (about 6 MB) download once, and after that no image and no text ever leaves your browser.
It works best on clear, straight, reasonably high-resolution text — a screenshot, a document scan, a photo of a sign or a page. Handwriting, heavy stylised fonts, very low-resolution images and skewed photos will be less accurate. You can add several images at once and get the combined text.
The result is plain text you can copy to the clipboard or download as a .txt file. There is no account and no watermark. English only for now.
What you can use it for
- Copy the text out of a screenshot instead of retyping it.
- Get the text from a photo of a document, sign or whiteboard.
- Turn a scanned page into editable text.
- Extract a quote or address from an image someone sent you.
- Pull the text from several receipt or note photos at once.
How it works, step by step
- 1
Add your images
Drag in or choose up to 20 screenshots, photos or scans — JPG, PNG, WebP or HEIC.
- 2
Extract text
Click Extract. The OCR engine downloads once (~6 MB), then reads each image on your device.
- 3
Check the result
The text appears in a box with a rough confidence score. OCR is not perfect — proofread it.
- 4
Copy or save
Copy the text to the clipboard or download it as a .txt file.
Frequently asked questions
Is my image uploaded to a server?
No. The OCR engine runs in your browser as WebAssembly. The image and the extracted text never leave your device.
Why is the first extraction slow?
The OCR engine and English language data (about 6 MB) download the first time you use the tool. After that they are cached and it starts quickly.
How accurate is it?
For clear, straight, printed text it is usually very good. Accuracy drops with handwriting, decorative fonts, low resolution, glare or a tilted photo. Always proofread the result.
Which languages does it support?
English only for now. More languages may be added later.
Does it work with iPhone HEIC photos?
Yes — HEIC and HEIF images are decoded in your browser before OCR.
Which browsers work?
Any modern browser with WebAssembly SIMD: Chrome and Edge, Firefox 89+, and Safari 16.4+ (iOS 16.4+).