A recognized utterance that corresponds to a segment of recorded speech and that contains one or more transcription hypotheses.


An utterance is a collection of spoken words. The speech recognizer provides one or more possible transcriptions (known as transcription hypotheses) for an utterance, and assigns a rating to each hypothesis that indicates how likely it is to be correct. A recognition request passes an SFSpeechRecognitionResult object in its result handler.


Accessing Transcriptions

var transcriptions: [SFTranscription]

An array of hypotheses for possible transcriptions, sorted in descending order of confidence (that is, the most likely transcription is first).

var bestTranscription: SFTranscription

The transcription of recognized speech that has the highest confidence level.

Monitoring Speech Recognition Results

var isFinal: Bool

A Boolean value that indicates whether speech recognition is complete and whether the hypotheses are final (will not change).


Inherits From

See Also

Working with Recognition Results and Transcriptions

class SFTranscription

A hypothesized textual representation of recognized speech.

class SFTranscriptionSegment

A part of the entire hypothesized transcription.

protocol SFSpeechRecognitionTaskDelegate

A protocol that supports complex or multi-utterance speech recognition requests.

protocol SFSpeechRecognizerDelegate

A protocol that helps you track the availability of a speech recognizer.