Image to Text (OCR)
Pull editable text out of photos, screenshots and scans.
The first run downloads the recognition engine and language data (a few MB); your image is not uploaded.
Runs 100% in your browser. Your files are not uploaded to any server.
How to use Image to Text (OCR)
- Drop an image or paste a screenshot with Ctrl+V.
- Pick the language of the text in the image.
- Click “Extract text”. The first time, the language data downloads once.
- Copy the text or download it as a .txt file.
Frequently asked questions
How accurate is it?
Clear, straight, high-contrast text usually comes out almost perfect. Handwriting, tiny fonts, blur and busy backgrounds lower the accuracy — the confidence score tells you how sure the engine is.
Can it read Chinese and English mixed together?
Yes. Choose “简体中文 + English” for documents that mix both.
Is Image to Text (OCR) free?
Yes. Image to Text (OCR) is free to use with no sign-up and no watermark.
Are my files uploaded to your server?
No. All processing happens locally in your browser using JavaScript and WebAssembly. Your files never leave your device, which also makes it fast and private.
Does it work on my phone?
Yes. It works in any modern browser on Windows, Mac, Linux, Android and iPhone. Very large files may be slow on older phones.