Image OCR

Image OCR is an API that reads the text from a photo or screenshot (an invoice, a sign, a scanned page) and gives it back to you as plain text. The engine runs on our own server: the image is never sent to an outside AI provider.

How it works

You send the image and the text's language (eng or spa), and get back the text found, along with a confidence percentage.

Honest note: it works very well on printed text and a reasonably sharp image (invoices, scanned documents, screenshots). With handwriting or blurry/tilted photos, results get noticeably worse: for that, a specialized paid AI service will do better.

All you need

Your API key. Create it in your dashboard with "+ Create key".
In your automation platform, an "HTTP Request" step (n8n, Make, Zapier, Pipedream…).

How to use it in n8n

Method: POST · URL: https://api.cofferdock.com/image-ocr
Send Headers: x-api-key = your key
Send Body: binary file (in n8n: "n8n Binary File")

Options

Option	Default	What it does
`language`	`eng`	`eng` (English) or `spa` (Spanish).

API overview

Endpoint: POST https://api.cofferdock.com/image-ocr
Auth: x-api-key: YOUR_KEY.
Input: raw image bytes, or JSON { "file": "<base64>" }.
Engine: Tesseract, hosted by us (open source, no third-party AI provider).
Languages: eng and spa only for now.
Limits: 20 requests/min per IP (lower than the rest: OCR uses more CPU). 1 call = 1 credit.

Example

curl -X POST "https://api.cofferdock.com/image-ocr?language=eng" \
  -H "x-api-key: YOUR_KEY" -H "Content-Type: image/jpeg" \
  --data-binary @invoice.jpg

Response

{ "success": true, "text": "INVOICE #2026-001\nTotal: $145.00",
    "confidence": 94, "meta": { "language": "eng", "used": 12, "remaining": 488 } }

What you get back

text (the text found) and confidence (0 to 100, how sure the tool is about the result).