A discrete part of an entire transcription, as identified by the speech recognizer.


class SFTranscriptionSegment : NSObject


Use SFTranscriptionSegment to get details about a part of an overall SFTranscription. An SFTranscriptionSegment represents an utterance, which is a vocalized word or group of words that represent a single meaning to the speech recognizer (SFSpeechRecognizer).

You don’t create transcription object segments directly. Instead, you access them from a transcription’s segments property.

A transcription segment includes the following information:

  • The text of the utterance, plus any alternative interpretations of the spoken word.

  • The character range of the segment within the formattedString of its parent SFTranscription.

  • A confidence value, indicating how likely it is that the specified string matches the audible speech.

  • A timestamp and duration value, indicating the position of the segment within the provided audio stream.

  • A voiceAnalytics metric, indicating the likelihood of a voice in a segment, and that voice’s pitch, jitter, and shimmer properties.


Transcribing the Segment

var substring: String

The string representation of the utterance in the transcription segment.

var substringRange: NSRange

The range information for the transcription segment’s substring, relative to the overall transcription.

var alternativeSubstrings: [String]

An array of alternate interpretations of the utterance in the transcription segment.

Assessing the Recognition Confidence Level

var confidence: Float

The level of confidence the speech recognizer has in its recognition of the speech transcribed for the segment.

Getting the Audio Timing Information

var timestamp: TimeInterval

The start time of the segment in the processed audio stream.

var duration: TimeInterval

The number of seconds it took for the user to speak the utterance represented by the segment.

Analyzing Voice

var voiceAnalytics: SFVoiceAnalytics?

An analysis of the transcription segment’s vocal properties.

class SFVoiceAnalytics

A collection of vocal analysis metrics.


Inherits From

See Also

Transcription Results

class SFSpeechRecognitionResult

An object containing the partial or final results of a speech recognition request.

class SFTranscription

A textual representation of the given speech it its entirety, as recognized by the speech recognizer.