OCR: Optical Character Recognition

Our API provides a feature to extract characters from images.

Extract text from images using OCR.

Performs optical character recognition (OCR) to extract text from images, enabling text-based analysis, data extraction, and automation workflows from visual data.

POSThttps://api.aimlapi.com/ocr

Body

application/json

document*any of

Document URL

string (uri)string

mimeTypeenum

Mime type of the provided document

application/pdfimage/gifimage/tiffimage/jpegimage/pngimage/bmpimage/webptext/html

Response

201

Body

application/json

urinullable string

contentany of

stringanynullable any

mimeTypenullable string

textnullable string

textStylesnullable array of nullable any

pagesnullable array of nullable any

entitiesnullable array of nullable any

entityRelationsnullable array of nullable any

textChangesnullable array of nullable any

shardInfonullable any

errornullable any

revisionsnullable array of nullable any

documentLayoutnullable any

chunkedDocumentnullable any

Request

JavaScriptCurlPython

const response = await fetch('https://api.aimlapi.com/ocr', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "document": "https://example.com"
    }),
});
const data = await response.json();

Response

201

{
  "uri": "text",
  "content": "text",
  "mimeType": "text",
  "text": "text",
  "textStyles": [],
  "pages": [],
  "entities": [],
  "entityRelations": [],
  "textChanges": [],
  "revisions": []
}