Speech
data class SpeechToTextRequest(val audio: ByteArray, val fileName: String = "audio.mp3", val contentType: String = "audio/mpeg", val modelId: String = "scribe_v2", val languageCode: String? = null, val tagAudioEvents: Boolean = true, val numberOfSpeakers: Int? = null, val timestampsGranularity: TimestampsGranularity = TimestampsGranularity.Word, val diarize: Boolean = false, val fileFormat: SpeechToTextFileFormat = SpeechToTextFileFormat.Other, val enableLogging: Boolean = true)(source)
Input for transcribing one complete audio or video file.
Constructors
Link copied to clipboard
constructor(audio: ByteArray, fileName: String = "audio.mp3", contentType: String = "audio/mpeg", modelId: String = "scribe_v2", languageCode: String? = null, tagAudioEvents: Boolean = true, numberOfSpeakers: Int? = null, timestampsGranularity: TimestampsGranularity = TimestampsGranularity.Word, diarize: Boolean = false, fileFormat: SpeechToTextFileFormat = SpeechToTextFileFormat.Other, enableLogging: Boolean = true)
Properties
Link copied to clipboard
MIME type included in the multipart upload.
Link copied to clipboard
Whether request logging is enabled.
Link copied to clipboard
Hint describing the uploaded file's raw or container format.
Link copied to clipboard
Expected language code, or null for automatic detection.
Link copied to clipboard
Expected speaker count from 1 through 32, or null when unknown.
Link copied to clipboard
Whether identifiable non-speech audio events should be tagged in the transcript.
Link copied to clipboard
Requested timestamp detail.