<!--
{
  "availability" : [
    "iOS: 10.0.0 -",
    "iPadOS: 10.0.0 -",
    "macCatalyst: 10.0.0 -",
    "macOS: 10.15.0 -",
    "visionOS: 1.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "Speech",
  "identifier" : "/documentation/Speech/SFTranscription",
  "metadataVersion" : "0.1.0",
  "role" : "Class",
  "symbol" : {
    "kind" : "Class",
    "modules" : [
      "Speech"
    ],
    "preciseIdentifier" : "c:objc(cs)SFTranscription"
  },
  "title" : "SFTranscription"
}
-->

# SFTranscription

A textual representation of the specified speech in its entirety, as recognized by the speech recognizer.

```
class SFTranscription
```

## Overview

Use `SFTranscription` to obtain all the recognized utterances from your audio content. An *utterance* is a vocalized word or group of words that represent a single meaning to the speech recognizer ([`SFSpeechRecognizer`](/documentation/Speech/SFSpeechRecognizer)).

Use the [`formattedString`](/documentation/Speech/SFTranscription/formattedString) property to retrieve the entire transcription of utterances, or use the [`segments`](/documentation/Speech/SFTranscription/segments) property to retrieve an individual utterance ([`SFTranscriptionSegment`](/documentation/Speech/SFTranscriptionSegment)).

You don’t create an `SFTranscription` directly. Instead, you retrieve it from an [`SFSpeechRecognitionResult`](/documentation/Speech/SFSpeechRecognitionResult) instance. The speech recognizer sends a speech recognition result to your app in one of two ways, depending on how your app started a speech recognition task.

You can start a speech recognition task by using the speech recognizer’s [`recognitionTask(with:resultHandler:)`](/documentation/Speech/SFSpeechRecognizer/recognitionTask(with:resultHandler:)) method. When the task is complete, the speech recognizer sends an [`SFSpeechRecognitionResult`](/documentation/Speech/SFSpeechRecognitionResult) instance to your `resultHandler` closure. Alternatively, you can use the speech recognizer’s [`recognitionTask(with:delegate:)`](/documentation/Speech/SFSpeechRecognizer/recognitionTask(with:delegate:)) method to start a speech recognition task. When the task is complete, the speech recognizer uses your [`SFSpeechRecognitionTaskDelegate`](/documentation/Speech/SFSpeechRecognitionTaskDelegate) to send an [`SFSpeechRecognitionResult`](/documentation/Speech/SFSpeechRecognitionResult) by using the delegate’s [`speechRecognitionTask(_:didFinishRecognition:)`](/documentation/Speech/SFSpeechRecognitionTaskDelegate/speechRecognitionTask(_:didFinishRecognition:)) method.

An `SFTranscription` represents only a potential version of the speech. It might not be an accurate representation of the utterances.

## Topics

### Transcribing utterances

[`formattedString`](/documentation/Speech/SFTranscription/formattedString)

The entire transcription of utterances, formatted into a single, user-displayable string.

### Getting individual utterances

[`segments`](/documentation/Speech/SFTranscription/segments)

An array of transcription segments that represent the parts of the transcription, as identified by the speech recognizer.

### Deprecated

[`averagePauseDuration`](/documentation/Speech/SFTranscription/averagePauseDuration)

The average pause duration between words, measured in seconds.

[`speakingRate`](/documentation/Speech/SFTranscription/speakingRate)

The number of words spoken per minute.


---

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)