Class: OpenAI::Models::Realtime::AudioTranscription

Inherits:
Internal::Type::BaseModel show all
Defined in:
lib/openai/models/realtime/audio_transcription.rb,
sig/openai/models/realtime/audio_transcription.rbs

Defined Under Namespace

Modules: Delay, Model

Instance Attribute Summary collapse

Class Method 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(delay: nil, language: nil, model: nil, prompt: nil) ⇒ Object

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

Parameters:

  • delay (Symbol, OpenAI::Models::Realtime::AudioTranscription::Delay) (defaults to: nil) —

    Controls how long the model waits before emitting transcription text.

  • language (String) (defaults to: nil) —

    The language of the input audio. Supplying the input language in

  • model (String, Symbol, OpenAI::Models::Realtime::AudioTranscription::Model) (defaults to: nil) —

    The model to use for transcription. Current options are whisper-1, `gpt-4o-min

  • prompt (String) (defaults to: nil) —

    An optional text to guide the model's style or continue a previous audio




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

Instance Attribute Details

#delay ⇒ Symbol, ...

Controls how long the model waits before emitting transcription text. Higher values can improve transcription accuracy at the cost of latency. Only supported with gpt-realtime-whisper in GA Realtime sessions.

Returns:



13
 
# File 'lib/openai/models/realtime/audio_transcription.rb', line 13

optional :delay, enum: -> { OpenAI::Realtime::AudioTranscription::Delay }

#language ⇒ String?

The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.

Parameters:

  • (String)

Returns:

  • (String, nil) 


21
 
# File 'lib/openai/models/realtime/audio_transcription.rb', line 21

optional :language, String

#model ⇒ String, ...

The model to use for transcription. Current options are whisper-1, gpt-4o-mini-transcribe, gpt-4o-mini-transcribe-2025-12-15, gpt-4o-transcribe, gpt-4o-transcribe-diarize, and gpt-realtime-whisper. Use gpt-4o-transcribe-diarize when you need diarization with speaker labels.

Returns:



30
 
# File 'lib/openai/models/realtime/audio_transcription.rb', line 30

optional :model, union: -> { OpenAI::Realtime::AudioTranscription::Model }

#prompt ⇒ String?

An optional text to guide the model's style or continue a previous audio segment. For whisper-1, the prompt is a list of keywords. For gpt-4o-transcribe models (excluding gpt-4o-transcribe-diarize), the prompt is a free text string, for example "expect words related to technology". Prompt is not supported with gpt-realtime-whisper in GA Realtime sessions.

Parameters:

  • (String)

Returns:

  • (String, nil) 


41
 
# File 'lib/openai/models/realtime/audio_transcription.rb', line 41

optional :prompt, String

Class Method Details

.values ⇒ Array<Symbol>

Returns:

  • (Array<Symbol>) 



# File 'lib/openai/models/realtime/audio_transcription.rb', line 69

Instance Method Details

#to_hash ⇒ {

Returns:

  • ({) 


40
 
# File 'sig/openai/models/realtime/audio_transcription.rbs', line 40

def to_hash: -> {