class

OpenAI::RealtimeTranscriptionSessionCreateResponseGAAudioInput

Inherits JSON::Serializable < Reference < Object

Constructors

new(format : RealtimeAudioFormats | Nil = nil, transcription : AudioTranscription | Nil = nil, noise_reduction : RealtimeTranscriptionSessionCreateResponseGAAudioInputNoiseReduction | Nil = nil, turn_detection : RealtimeTranscriptionSessionCreateResponseGAAudioInputTurnDetection | Nil = nil)

Source

new(*, __pull_for_json_serializable pull : JSON::PullParser)

Source

Instance methods

format

Source

format=(format : RealtimeAudioFormats | Nil)

Source

noise_reduction

Configuration for input audio noise reduction.

Source

noise_reduction=(noise_reduction : RealtimeTranscriptionSessionCreateResponseGAAudioInputNoiseReduction | Nil)

Configuration for input audio noise reduction.

Source

transcription

Configuration of the transcription model.

Source

transcription=(transcription : AudioTranscription | Nil)

Configuration of the transcription model.

Source

turn_detection

Configuration for turn detection. Can be set to null to turn off. Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

Source

turn_detection=(turn_detection : RealtimeTranscriptionSessionCreateResponseGAAudioInputTurnDetection | Nil)

Source