Images

Read the text from an image (OCR)

Extracts text from a photo or screenshot using Tesseract, hosted by us (no third-party AI provider). Works best on clean printed text; handwriting or blurry photos give worse results. Only eng and spa are supported today.

Costs 1 credit per call.

post/image-ocr

Request

  • Base URL: https://api.cofferdock.com
  • URL: https://api.cofferdock.com/image-ocr
  • Auth: API key in header x-api-key

Request body

filestring byte required

The image to read the text from, base64-encoded (e.g. PNG or JPEG).

language'eng' | 'spa'

Language of the text in the image: "eng" (English, default) or "spa" (Spanish). Pick the one that matches the text.

Response

Result.

successboolean
textstring
confidenceinteger

Changes

No recorded changes to this operation across all 1 revision of this API.