Module: OpenAI::Models::Realtime::AudioTranscription::Model

Extended by:

Internal::Type::Union

Defined in:

lib/openai/models/realtime/audio_transcription.rb

Overview

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`, and `gpt-4o-transcribe-diarize`. Use `gpt-4o-transcribe-diarize` when you need diarization with speaker labels.

See Also:

• #model

WHISPER_1 =

:"whisper-1"

GPT_4O_MINI_TRANSCRIBE =

:"gpt-4o-mini-transcribe"

GPT_4O_MINI_TRANSCRIBE_2025_12_15 =

:"gpt-4o-mini-transcribe-2025-12-15"

GPT_4O_TRANSCRIBE =

:"gpt-4o-transcribe"

GPT_4O_TRANSCRIBE_DIARIZE =

:"gpt-4o-transcribe-diarize"

Class Method Summary

• .variants ⇒ Array(String, Symbol)

Methods included from Internal::Type::Union

==, ===, coerce, dump, hash, inspect, to_sorbet_type, variants

Methods included from Internal::Util::SorbetRuntimeSupport

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

Methods included from Internal::Type::Converter

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

Class Method Details

.variants ⇒ Array(String, Symbol)

Returns:

• (Array(String, Symbol))

# File 'lib/openai/models/realtime/audio_transcription.rb', line 68

define_sorbet_constant!(:Variants) do
  T.type_alias { T.any(String, OpenAI::Realtime::AudioTranscription::Model::TaggedSymbol) }
end