Image to text (OCR)
Extract text from photos, screenshots and scanned documents with OCR, in your browser, without uploading the images.
Processed on your device: your file never leaves your computer
Up to 50 files, 50 MB max each.
What Image to text (OCR) does
Turn the text in an image into editable text: a photo of a document, a screenshot, a receipt or a scanned page. Choose the language of the text (Spanish, English, Portuguese, French or Chinese) for more accurate recognition. Everything happens on your device: the OCR engine and the language are downloaded once from our site and your images are not uploaded to any server. You get one .txt file per image, which you can also copy directly.
Limits
- Up to 50 files at a time, up to 50 MB each.
- With Pro: up to 500 files per batch.
- A job that takes longer than 3 minutes is stopped so it doesn't freeze your device.
- Processed in your browser: your files are never uploaded to a server.
Frequently asked questions
How accurate is it?
With sharp, straight printed text it usually gets almost everything right. Blurry, tilted or dark photos and handwriting give worse results; when confidence is low we warn you to check the text.
Are my images uploaded to a server?
No. Recognition runs in your browser. Only the OCR engine and the chosen language model (about 2 to 4 MB) are downloaded the first time, from our own site.
Which formats and languages are supported?
JPG, PNG, WEBP, BMP, GIF, TIFF, HEIC and AVIF, up to 50 MB per image. Languages: Spanish, English, Portuguese, French and Simplified Chinese. Choose the language the text is written in.
Does it work with scanned PDFs?
If your PDF is a scan, use “OCR scanned PDF”: it recognizes every page and gives you a searchable PDF or a .txt file.