<!--
{
  "availability" : [
    "iOS: 18.0.0 -",
    "iPadOS: 18.0.0 -",
    "macOS: 15.0.0 -",
    "tvOS: 18.0.0 -",
    "visionOS: 2.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "Vision",
  "identifier" : "/documentation/Vision/RecognizeTextRequest",
  "metadataVersion" : "0.1.0",
  "role" : "Structure",
  "symbol" : {
    "kind" : "Structure",
    "modules" : [
      "Vision"
    ],
    "preciseIdentifier" : "s:6Vision20RecognizeTextRequestV"
  },
  "title" : "RecognizeTextRequest"
}
-->

# RecognizeTextRequest

An image-analysis request that recognizes text in an image.

```
struct RecognizeTextRequest
```

## Overview

This request generates a collection of [`RecognizedTextObservation`](/documentation/Vision/RecognizedTextObservation) objects that describe the text the request detects. By default, a text-recognition request first locates all possible glyphs or characters in the input image, and then analyzes each string. To specify or limit the languages to find in the request, set [`recognitionLanguages`](/documentation/Vision/RecognizeTextRequest/recognitionLanguages) to an array that contains the names of the languages of text you want to recognize.

## Topics

### Creating a request

[`init(_:)`](/documentation/Vision/RecognizeTextRequest/init(_:))

Creates a text-recognition request.

### Performing a request

[`perform(on:orientation:)`](/documentation/Vision/ImageProcessingRequest/perform(on:orientation:)-80bya)

Performs the request on an image URL and produces observations.

[`perform(on:orientation:)`](/documentation/Vision/ImageProcessingRequest/perform(on:orientation:)-3f3f1)

Performs the request on image data and produces observations.

[`perform(on:orientation:)`](/documentation/Vision/ImageProcessingRequest/perform(on:orientation:)-qxxx)

Performs the request on a Core Graphics image and produces observations.

[`perform(on:orientation:)`](/documentation/Vision/ImageProcessingRequest/perform(on:orientation:)-xspx)

Performs the request on a pixel buffer and produces observations.

[`perform(on:orientation:)`](/documentation/Vision/ImageProcessingRequest/perform(on:orientation:)-3hddl)

Performs the request on a Core Media buffer and produces observations.

[`perform(on:orientation:)`](/documentation/Vision/ImageProcessingRequest/perform(on:orientation:)-85ex1)

Performs the request on a Core Image image and produces observations.

### Understanding the result

[`RecognizedTextObservation`](/documentation/Vision/RecognizedTextObservation)

An object that contains information about both the location and content of text and glyphs that the framework recognizes in an image.

### Configuring a request

[`automaticallyDetectsLanguage`](/documentation/Vision/RecognizeTextRequest/automaticallyDetectsLanguage)

A Boolean value that indicates whether to attempt detecting the language to use the appropriate model for recognition and language correction.

[`usesLanguageCorrection`](/documentation/Vision/RecognizeTextRequest/usesLanguageCorrection)

A Boolean value that indicates whether the request applies language correction during the recognition process.

[`supportedRecognitionLanguages`](/documentation/Vision/RecognizeTextRequest/supportedRecognitionLanguages)

The identifiers of the languages that the request supports.

[`customWords`](/documentation/Vision/RecognizeTextRequest/customWords)

An array of strings to supplement the recognized languages at the word-recognition stage.

[`minimumTextHeightFraction`](/documentation/Vision/RecognizeTextRequest/minimumTextHeightFraction)

The minimum height, relative to the image height, of the text to recognize.

[`recognitionLanguages`](/documentation/Vision/RecognizeTextRequest/recognitionLanguages)

An array of languages to detect, in priority order.

[`recognitionLevel`](/documentation/Vision/RecognizeTextRequest/recognitionLevel-swift.property)

A value that determines whether the request prioritizes accuracy or speed in text recognition.

[`RecognizeTextRequest.RecognitionLevel`](/documentation/Vision/RecognizeTextRequest/RecognitionLevel-swift.enum)

Constants that identify the performance and accuracy of the text recognition.

### Getting the revision

[`revision`](/documentation/Vision/RecognizeTextRequest/revision-swift.property)

The algorithm or implementation the request uses.

[`supportedRevisions`](/documentation/Vision/RecognizeTextRequest/supportedRevisions)

The collection of revisions the request supports.

[`RecognizeTextRequest.Revision`](/documentation/Vision/RecognizeTextRequest/Revision-swift.enum)

A type that describes the algorithm or implementation that the request performs.


---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)