Class: OpenAI::Models::Realtime::ConversationItemInputAudioTranscriptionCompletedEvent

Inherits:
Internal::Type::BaseModel show all
Defined in:
lib/openai/models/realtime/conversation_item_input_audio_transcription_completed_event.rb

Defined Under Namespace

Modules: Usage

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods inherited from Internal::Type::BaseModel

==, #==, #[], coerce, #deconstruct_keys, #deep_to_h, dump, fields, hash, #hash, inherited, inspect, #inspect, known_fields, optional, recursively_to_h, required, #to_h, #to_json, #to_s, to_sorbet_type, #to_yaml

Methods included from Internal::Type::Converter

#coerce, coerce, #dump, dump, inspect, #inspect, meta_info, new_coerce_state, type_info

Methods included from Internal::Util::SorbetRuntimeSupport

#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type

Constructor Details

#initialize(content_index:, event_id:, item_id:, transcript:, usage:, logprobs: nil, type: :"conversation.item.input_audio_transcription.completed") ⇒ Object

Some parameter documentations has been truncated, see OpenAI::Models::Realtime::ConversationItemInputAudioTranscriptionCompletedEvent for more details.

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.

Parameters:




# File 'lib/openai/models/realtime/conversation_item_input_audio_transcription_completed_event.rb', line 53

Instance Attribute Details

#content_index ⇒ Integer

The index of the content part containing the audio.

Returns:

  • (Integer) 


11
 
# File 'lib/openai/models/realtime/conversation_item_input_audio_transcription_completed_event.rb', line 11

required :content_index, Integer

#event_id ⇒ String

The unique ID of the server event.

Returns:

  • (String) 


17
 
# File 'lib/openai/models/realtime/conversation_item_input_audio_transcription_completed_event.rb', line 17

required :event_id, String

#item_id ⇒ String

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

Returns:

  • (String) 


23
 
# File 'lib/openai/models/realtime/conversation_item_input_audio_transcription_completed_event.rb', line 23

required :item_id, String

#logprobs ⇒ Array<OpenAI::Models::Realtime::LogProbProperties>?

The log probabilities of the transcription.

Returns:



49
50
51
 
# File 'lib/openai/models/realtime/conversation_item_input_audio_transcription_completed_event.rb', line 49

optional :logprobs,
-> { OpenAI::Internal::Type::ArrayOf[OpenAI::Realtime::LogProbProperties] },
nil?: true

#transcript ⇒ String

The transcribed text.

Returns:

  • (String) 


29
 
# File 'lib/openai/models/realtime/conversation_item_input_audio_transcription_completed_event.rb', line 29

required :transcript, String

#type ⇒ Symbol, :"conversation.item.input_audio_transcription.completed"

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

Returns:

  • (Symbol, :"conversation.item.input_audio_transcription.completed") 


35
 
# File 'lib/openai/models/realtime/conversation_item_input_audio_transcription_completed_event.rb', line 35

required :type, const: :"conversation.item.input_audio_transcription.completed"

#usage ⇒ OpenAI::Models::Realtime::ConversationItemInputAudioTranscriptionCompletedEvent::Usage::TranscriptTextUsageTokens, OpenAI::Models::Realtime::ConversationItemInputAudioTranscriptionCompletedEvent::Usage::TranscriptTextUsageDuration

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

Returns:



42
43
 
# File 'lib/openai/models/realtime/conversation_item_input_audio_transcription_completed_event.rb', line 42

required :usage,
union: -> { OpenAI::Realtime::ConversationItemInputAudioTranscriptionCompletedEvent::Usage }