---
title: "Detect and identify text in an image using AI"
method: POST
path: "/api/ai/images/v2/image-text-detection"
tags: ["AI Services"]
---

# Detect and identify text in an image using AI

`POST /api/ai/images/v2/image-text-detection`

## Request

- Base URL: `https://api.worqhat.com`
- URL: `https://api.worqhat.com/api/ai/images/v2/image-text-detection`
- Auth: HTTP bearer
- TypeScript: <https://skmtc.dev/worqhat/apis/worqhat-ai-api-endpoints-2/docs/api/ai/images/v2/image-text-detection/post.ts> (a function with typed inputs; its response is checked against the schema)

This endpoint is used to modify an existing image using AI. It accepts a Form Data containing the image modification parameters and returns the modified image.

## Request body `multi-part/form-data`

- object
  - `image` string, binary: The image to be sent as input.
  - `output_type` 'json' | 'text': The type of output to be generated. You can choose between `json` and `text`. `json` will return the text detection results as a JSON object with the scan words marked and positional information. `text` will return the text detection results as a plain text string.

## Response `200`

OK

- object
  - `code` integer: The HTTP status code.
  - `status` string: Status indicating the success of the response. In case you have an error for `multipart/form-data` requests, try removing the `Content-Type` header.
  - `data` string: The response data.
  - `processing_time` integer: The time taken to process the request, in milliseconds.
  - `processing_id` string: A universally unique identifier for the request. This can be used to track the request in the logs.
  - `processing_count` integer: The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes.

## Other responses

- `400`: Bad Request. This mostly happens because of invalid image sizes. Neither `height` nor `width` of the image should be less than 128px. Only one of the sides of the image should be greater than or equal to 512px. (Eg: 512x512, 512x768, 768x512) Maximum dimensions supported is 512x896.
- `401`: Unauthorized
- `404`: Not Found
- `406`: Not Acceptable
- `500`: Internal Server Error

## Changes

- **2023-10-20** `871850b7231f`: 2 breaking, 3 warning, 19 info
  - request body became required
  - removed the media type `multipart/form-data` from the request body
  - removed the optional property `content` from the response with the `200` status
  - removed the optional property `id` from the response with the `200` status
  - …20 more
- **2023-09-01** `7e5a49493623`: 1 info
  - added the new optional request property `output_type`
- **2023-08-15** `b5ffe2a9748f`: 6 breaking, 18 info
  - the response's body type changed from no type to `object` for status `400`
  - the response's body type changed from no type to `object` for status `401`
  - the response's body type changed from no type to `object` for status `404`
  - the response's body type changed from no type to `object` for status `406`
  - …20 more
- **2023-08-04** `be85a8f8fc8c`: 6 breaking, 16 warning
  - the response's body type changed from `object` to no type for status `400`
  - the response's body type changed from `object` to no type for status `401`
  - the response's body type changed from `object` to no type for status `404`
  - the response's body type changed from `object` to no type for status `406`
  - …18 more
- **2023-08-04** `d6dbf089e00d`: 1 info
  - the endpoint scheme security `bearerAuth` was removed from the API

[Operation history](https://skmtc.dev/worqhat/apis/worqhat-ai-api-endpoints-2/changes/api/ai/images/v2/image-text-detection/post.md)

---

[API](https://skmtc.dev/worqhat/apis/worqhat-ai-api-endpoints-2.md) - [All operations](https://skmtc.dev/worqhat/apis/worqhat-ai-api-endpoints-2/llms.txt) - [OpenAPI document](https://skmtc.dev/worqhat/apis/worqhat-ai-api-endpoints-2/revisions/fc369f69a3e6?raw)
