class

OpenAI::RealtimeBetaServerEventConversationItemInputAudioTranscriptionCompleted

Inherits JSON::Serializable < Reference < Object

This event is the output of audio transcription for user audio written to the user audio buffer. Transcription begins when the input audio buffer is committed by the client or server (in server_vad mode). Transcription runs asynchronously with Response creation, so this event may come before or after the Response events.

Realtime API models accept audio natively, and thus input transcription is a separate process run on a separate ASR (Automatic Speech Recognition) model. The transcript may diverge somewhat from the model's interpretation, and should be treated as a rough guide.

Constructors

new(pull : JSON::PullParser)
Source
new(event_id : String = "", type_value : RealtimeBetaServerEventConversationItemInputAudioTranscriptionCompletedType = RealtimeBetaServerEventConversationItemInputAudioTranscriptionCompletedType::ConversationItemInputAudioTranscriptionCompleted, item_id : String = "", content_index : Int64 = 0, transcript : String = "", logprobs : RealtimeBetaServerEventConversationItemInputAudioTranscriptionCompletedLogprobs | Nil = nil, usage : RealtimeBetaServerEventConversationItemInputAudioTranscriptionCompletedUsage = TranscriptTextUsageTokens.new)
Source
new(*, __pull_for_json_serializable pull : JSON::PullParser)
Source

Instance methods

content_index

The index of the content part containing the audio.

Source
content_index=(content_index : Int64)

The index of the content part containing the audio.

Source
event_id

The unique ID of the server event.

Source
event_id=(event_id : String)

The unique ID of the server event.

Source
item_id

The ID of the user message item containing the audio.

Source
item_id=(item_id : String)

The ID of the user message item containing the audio.

Source
logprobs
Source
logprobs=(logprobs : RealtimeBetaServerEventConversationItemInputAudioTranscriptionCompletedLogprobs | Nil)
Source
transcript

The transcribed text.

Source
transcript=(transcript : String)

The transcribed text.

Source
type_value

The event type, must be conversation.item.input_audio_transcription.completed.

Source
type_value=(type_value : RealtimeBetaServerEventConversationItemInputAudioTranscriptionCompletedType)

The event type, must be conversation.item.input_audio_transcription.completed.

Source
usage

Usage statistics for the transcription.

Source
usage=(usage : RealtimeBetaServerEventConversationItemInputAudioTranscriptionCompletedUsage)

Usage statistics for the transcription.

Source