MedicalItem - Amazon Transcribe

MedicalItem

A word, phrase, or punctuation mark that is transcribed from the input audio.

Contents

Confidence

A value between 0 and 1 for an item that is a confidence score that Amazon Transcribe Medical assigns to each word that it transcribes.

Type: Double

Required: No

Content

The word or punctuation mark that was recognized in the input audio.

Type: String

Required: No

EndTime

The number of seconds into an audio stream that indicates the creation time of an item.

Type: Double

Required: No

Speaker

If speaker identification is enabled, shows the integer values that correspond to the different speakers identified in the stream. For example, if the value of Speaker in the stream is either a 0 or a 1, that indicates that Amazon Transcribe Medical has identified two speakers in the stream. The value of 0 corresponds to one speaker and the value of 1 corresponds to the other speaker.

Type: String

Required: No

StartTime

The number of seconds into an audio stream that indicates the creation time of an item.

Type: Double

Required: No

Type

The type of the item. PRONUNCIATION indicates that the item is a word that was recognized in the input audio. PUNCTUATION indicates that the item was interpreted as a pause in the input audio, such as a period to indicate the end of a sentence.

Type: String

Valid Values: pronunciation | punctuation

Required: No

See Also

For more information about using this API in one of the language-specific AWS SDKs, see the following: