class

OpenAI::RealtimeTranscriptionSessionCreateResponse

Inherits JSON::Serializable < Reference < Object

A new Realtime transcription session configuration.

When a session is created on the server via REST API, the session object also contains an ephemeral key. Default TTL for keys is 10 minutes. This property is not present when a session is updated via the WebSocket API.

Constructors

new(pull : JSON::PullParser)
Source
new(client_secret : RealtimeTranscriptionSessionCreateResponseClientSecret = RealtimeTranscriptionSessionCreateResponseClientSecret.new, modalities : Hash(String, JSON::Any) | Nil = nil, input_audio_format : String | Nil = nil, input_audio_transcription : AudioTranscription | Nil = nil, turn_detection : RealtimeTranscriptionSessionCreateResponseTurnDetection | Nil = nil)
Source
new(*, __pull_for_json_serializable pull : JSON::PullParser)
Source

Instance methods

client_secret

Ephemeral key returned by the API. Only present when the session is created on the server via REST API.

Source
client_secret=(client_secret : RealtimeTranscriptionSessionCreateResponseClientSecret)

Ephemeral key returned by the API. Only present when the session is created on the server via REST API.

Source
input_audio_format

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.

Source
input_audio_format=(input_audio_format : String | Nil)

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.

Source
input_audio_transcription

Configuration of the transcription model.

Source
input_audio_transcription=(input_audio_transcription : AudioTranscription | Nil)

Configuration of the transcription model.

Source
modalities

The set of modalities the model can respond with. To disable audio, set this to ["text"].

Source
modalities=(modalities : Hash(String, JSON::Any) | Nil)

The set of modalities the model can respond with. To disable audio, set this to ["text"].

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 : RealtimeTranscriptionSessionCreateResponseTurnDetection | 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