Image OCR API for Developers
OCR
Image OCR API built for teams that need reliable document automation at scale. Convert and process files with simple REST requests, predictable output quality, and production-grade uptime. Use it for receipt extraction, form processing, and screenshot text workflows. Includes clear docs, SDK-ready endpoints, and quick testing in your browser.
What it does
OCR parse image input from URL, upload, or base64 string.
Set lang, psm, oem for better recognition quality.
Useful for invoices, receipts, forms, and screenshot text extraction.
Endpoint & Example
POST /v1/image/ocr/parse
image_url / file / base64_image
required
Provide image as public URL, multipart upload, or base64 payload.
lang
optional
OCR language code(s), e.g. eng or eng+hin.
psm, oem
optional
Tesseract segmentation and engine modes for recognition behavior tuning.
curl -X POST https://pdfmunk.com/api/v1/image/ocr/parse \
-H "CLIENT-API-KEY: your_api_key_here" \
-H "Content-Type: application/json" \
-d '{
"image_url": "https://example.com/invoice.jpg",
"lang": "eng",
"psm": 6,
"oem": 3
}'Sandbox
Please sign in or sign up to use the sandbox.