class

OpenAI::RealtimeServerEventConversationItemInputAudioTranscriptionCompleted

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 (when VAD is enabled). 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)

new(event_id : String = "", type_value : RealtimeServerEventConversationItemInputAudioTranscriptionCompletedType = RealtimeServerEventConversationItemInputAudioTranscriptionCompletedType::ConversationItemInputAudioTranscriptionCompleted, item_id : String = "", content_index : Int64 = 0, transcript : String = "", logprobs : RealtimeServerEventConversationItemInputAudioTranscriptionCompletedLogprobs | Nil = nil, usage : RealtimeServerEventConversationItemInputAudioTranscriptionCompletedUsage = TranscriptTextUsageTokens.new)

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

Instance methods

content_index

The index of the content part containing the audio.

content_index=(content_index : Int64)

The index of the content part containing the audio.

event_id

The unique ID of the server event.

event_id=(event_id : String)

The unique ID of the server event.

item_id

The ID of the item containing the audio that is being transcribed.

item_id=(item_id : String)

The ID of the item containing the audio that is being transcribed.

logprobs

logprobs=(logprobs : RealtimeServerEventConversationItemInputAudioTranscriptionCompletedLogprobs | Nil)

transcript

The transcribed text.

transcript=(transcript : String)

The transcribed text.

type_value

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

type_value=(type_value : RealtimeServerEventConversationItemInputAudioTranscriptionCompletedType)

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

usage

Usage statistics for the transcription, this is billed according to the ASR model's pricing rather than the realtime model's pricing.

usage=(usage : RealtimeServerEventConversationItemInputAudioTranscriptionCompletedUsage)

Usage statistics for the transcription, this is billed according to the ASR model's pricing rather than the realtime model's pricing.