Image to text
Read the words in a picture. The OCR model downloads once and runs in this browser.
Runs in browser
Use from your agent
Streamable HTTP at https://benchline.fabwaseem.com/mcp. No key. The tool name is read_image_text.
mcp.jsonjson
1{
2 "mcpServers": {
3 "benchline": {
4 "url": "https://benchline.fabwaseem.com/mcp"
5 }
6 }
7}
tools/calljson
1{
2 "jsonrpc": "2.0",
3 "id": 1,
4 "method": "tools/call",
5 "params": {
6 "name": "read_image_text",
7 "arguments": {
8 "file": {
9 "url": "https://example.com/file"
10 },
11 "language": "eng"
12 }
13 }
14}
Related tools
- Image format converterConvert HEIC, WebP, PNG, JPG, and AVIF in the browser. Nothing is uploaded.ImageMCPNew
- QR and barcode readerRead QR codes and barcodes from a photo, a paste, or the camera.ImageMCPNew
- Image to PDFTurn JPG, PNG, and WebP images into one PDF. Set the page size, orientation, margin, and order.PDFMCPNew
- Merge PDFCombine PDFs in the browser. Reorder them, keep a page range from each file, and download one document.PDFMCPNew
How it works
Free image to text. Tesseract reads the picture in this browser after a one-time download of the language data. Pick a language, then copy or download the text. A progress line shows the download and the recognition.
- 01
Drop the image
Add a screenshot, a scan, or a photo of text.
- 02
Choose the language
English is ready first. Other languages download when you pick them.
- 03
Copy the text
The page shows progress, then the text and a confidence score.