# Image to Text - Complete Guide

> Extract text from photos, scans and screenshots in your browser, in English, Hindi and other Indian languages.

Source: https://edesy.in/docs/tools/image-tools/image-to-text

[Image to Text](https://edesy.in/tools/image-to-text) reads the text in a photo, scan or screenshot (OCR) so you can copy and edit it. The OCR runs in your browser, so your images are not uploaded.

## How to Use

1. Drop JPG, PNG or WebP images onto the tool, or paste a screenshot with Ctrl+V. You can add several.
2. Pick the **Language in the image**. English is selected by default; the list also has Hindi, English + Hindi, Bengali, Marathi, Tamil, Telugu, Gujarati, Kannada, Malayalam and Punjabi.
3. Leave **Enhance image** and **Join split words** on unless they make the result worse.
4. Click **Extract text**. Each image gets its own result box with a confidence score.
5. Edit the text if needed, then click **Copy** or **Download .txt**.

## Things to know

- **File limits**: JPG, PNG and WebP only, up to 20 MB each.
- **First run**: the first time you use a language, its language data (a few MB) downloads. After that it is cached, so you need a connection the first time.
- **Accuracy**: sharp, well-lit, straight photos of printed text work best. Handwriting is not read reliably.
- **Confidence**: a low score means you should check the text carefully. A closer photo, the right language, or cropping to just the text usually helps.
- **Privacy**: images stay on your device.

## Tips

- **Enhance image** enlarges small images and converts them to greyscale before reading, which helps with small screenshot text.
- **Join split words** rejoins words broken with a hyphen at the end of a line.
- Mixed Hindi and English text reads better with **English + Hindi** than with either language alone.
- For scanned PDFs, use [OCR PDF](https://edesy.in/tools/ocr-pdf) instead.

**Related:** [OCR PDF](https://edesy.in/tools/ocr-pdf), [Crop Image](https://edesy.in/tools/crop-image), [Case Converter](https://edesy.in/tools/case-converter)