Class: OpenAI::Models::Realtime::RealtimeResponseCreateAudioOutput::Output

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

Overview

See Also:

  • OpenAI::Models::Realtime::RealtimeResponseCreateAudioOutput#output

Defined Under Namespace

Modules: Voice

Instance Attribute Summary collapse

Attributes inherited from Internal::Type::BaseModel

#last_response

Instance Method Summary collapse

Methods inherited from Internal::Type::BaseModel

==, #==, #[], #_request_id, #_set_last_response, coerce, #deconstruct_keys, #deep_to_h, dump, #encode_with, 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, coerce_with_error, 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(format_: nil, voice: nil) ⇒ Object

Parameters:

  • format_ (defaults to: nil) —

    The format of the output audio.

  • voice (defaults to: nil) —

    The voice the model uses to respond. Supported built-in voices are alloy, ash, ballad, coral, echo, sage, shimmer, verse, marin, and cedar. You may also provide a custom voice object with an id, for example { "id": "voice_1234" }. Voice cannot be changed during the session once the model has responded with audio at least once. We recommend marin and cedar for best quality.




# File 'lib/openai/models/realtime/realtime_response_create_audio_output.rb', line 36

Instance Attribute Details

#format_ ⇒ OpenAI::Models::Realtime::realtime_audio_formats?

The format of the output audio.

Returns:

  • (OpenAI::Models::Realtime::realtime_audio_formats, nil) 


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

optional :format_, union: -> { OpenAI::Realtime::RealtimeAudioFormats }, api_name: :format

#voice ⇒ OpenAI::Models::Realtime::RealtimeResponseCreateAudioOutput::Output::voice?

The voice the model uses to respond. Supported built-in voices are alloy, ash, ballad, coral, echo, sage, shimmer, verse, marin, and cedar. You may also provide a custom voice object with an id, for example { "id": "voice_1234" }. Voice cannot be changed during the session once the model has responded with audio at least once. We recommend marin and cedar for best quality.

Returns:

  • (OpenAI::Models::Realtime::RealtimeResponseCreateAudioOutput::Output::voice, nil) 


34
 
# File 'lib/openai/models/realtime/realtime_response_create_audio_output.rb', line 34

optional :voice, union: -> { OpenAI::Realtime::RealtimeResponseCreateAudioOutput::Output::Voice }

Instance Method Details

#to_hash ⇒ {

Returns:

  • ({) 


69
 
# File 'sig/openai/models/realtime/realtime_response_create_audio_output.rbs', line 69

def to_hash: -> {