class

OpenAI::RealtimeTranscriptionSessionCreateRequest

Inherits JSON::Serializable < Reference < Object

Realtime transcription session object configuration.

Constructors

new(pull : JSON::PullParser)
Source
new(turn_detection : RealtimeTranscriptionSessionCreateRequestTurnDetection | Nil = nil, input_audio_noise_reduction : RealtimeTranscriptionSessionCreateRequestInputAudioNoiseReduction | Nil = nil, input_audio_format : RealtimeTranscriptionSessionCreateRequestInputAudioFormat | Nil = nil, input_audio_transcription : AudioTranscription | Nil = nil, include_value : Array(RealtimeTranscriptionSessionCreateRequestIncludeItem) | Nil = nil)
Source
new(*, __pull_for_json_serializable pull : JSON::PullParser)
Source

Instance methods

include_value

The set of items to include in the transcription. Current available items are: item.input_audio_transcription.logprobs

Source
include_value=(include_value : Array(RealtimeTranscriptionSessionCreateRequestIncludeItem) | Nil)

The set of items to include in the transcription. Current available items are: item.input_audio_transcription.logprobs

Source
input_audio_format

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, input audio must be 16-bit PCM at a 24kHz sample rate, single channel (mono), and little-endian byte order.

Source
input_audio_format=(input_audio_format : RealtimeTranscriptionSessionCreateRequestInputAudioFormat | Nil)

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, input audio must be 16-bit PCM at a 24kHz sample rate, single channel (mono), and little-endian byte order.

Source
input_audio_noise_reduction

Configuration for input audio noise reduction. This can be set to null to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

Source
input_audio_noise_reduction=(input_audio_noise_reduction : RealtimeTranscriptionSessionCreateRequestInputAudioNoiseReduction | Nil)

Configuration for input audio noise reduction. This can be set to null to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

Source
input_audio_transcription

Configuration for input audio transcription. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.

Source
input_audio_transcription=(input_audio_transcription : AudioTranscription | Nil)

Configuration for input audio transcription. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.

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 : RealtimeTranscriptionSessionCreateRequestTurnDetection | Nil)

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