Your files stay on your device

# Image to text (OCR)

Pick a JPG, PNG, or WebP image and read its English text locally with a bundled glyph-matching OCR engine, then copy or download the result with word and character counts.

Drop a picture of some text here

A screenshot, a scan, a photo of a sign. The reading runs on this device and the file is not uploaded anywhere.

Pick an image to read its text.

The reader is a bundled pattern matcher, not a neural engine: it binarizes the image, finds text lines, and matches each glyph against a built-in 5x7 bitmap font of Latin letters, digits, and common punctuation. Clean, straight, single-font text on a plain background reads well. Handwriting, skew, multiple fonts, colored or textured backgrounds, and character touching degrade to ? placeholders, and the confidence number tells you when to distrust a line. Nothing is uploaded; every pixel stays in this tab.
Options

## More text tools

- [Word & character count](/text/word-count)
- [Character table](/text/character-table)
- [Convert images](/images/convert)
[All text tools](/text)

Was this tool useful?
YesNo

---

Canonical HTML: https://nutter.tools/text/image-to-text
Markdown version: https://nutter.tools/text/image-to-text.md
Plain-text version: https://nutter.tools/text/image-to-text.txt
Agent index: https://nutter.tools/llms.txt