Module: OpenAI::Models::Realtime::RealtimeResponse::Audio::Output::Voice

Extended by:

Internal::Type::Union

Defined in:

lib/openai/models/realtime/realtime_response.rb

Overview

The voice the model uses to respond. Voice cannot be changed during the session once the model has responded with audio at least once. Current voice options are alloy, ash, ballad, coral, echo, sage, shimmer, verse, marin, and cedar. We recommend marin and cedar for best quality.

See Also:

• #voice

ALLOY =

:alloy

ASH =

:ash

BALLAD =

:ballad

CORAL =

:coral

ECHO =

:echo

SAGE =

:sage

SHIMMER =

:shimmer

VERSE =

:verse

MARIN =

:marin

CEDAR =

:cedar

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/realtime_response.rb', line 191

define_sorbet_constant!(:Variants) do
  T.type_alias { T.any(String, OpenAI::Realtime::RealtimeResponse::Audio::Output::Voice::TaggedSymbol) }
end