Class: OpenAI::Models::Realtime::RealtimeSessionCreateResponse::Audio::Input

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

Overview

See Also:

  • OpenAI::Models::Realtime::RealtimeSessionCreateResponse::Audio#input

Defined Under Namespace

Modules: TurnDetection Classes: NoiseReduction

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(type: nil) ⇒ Object

Parameters:

  • format_ —

    The format of the input audio.

  • noise_reduction —

    Configuration for input audio noise reduction. This can be set to null to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

  • turn_detection —

    Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to null to turn off, in which case the client must manually trigger model response.

    Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

    Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency.

    For gpt-realtime-whisper transcription sessions, turn detection must be set to null; VAD is not supported.




# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 323

Instance Attribute Details

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

The format of the input audio.

Returns:

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


276
 
# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 276

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

#noise_reduction ⇒ OpenAI::Realtime::RealtimeSessionCreateResponse::Audio::Input::NoiseReduction?

Configuration for input audio noise reduction. This can be set to null to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

Returns:

  • (OpenAI::Realtime::RealtimeSessionCreateResponse::Audio::Input::NoiseReduction, nil) 


286
287
288
289
 
# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 286

optional(
  :noise_reduction,
  -> { OpenAI::Realtime::RealtimeSessionCreateResponse::Audio::Input::NoiseReduction }
)

#transcription ⇒ OpenAI::Models::Realtime::AudioTranscription?

Returns:



294
 
# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 294

optional :transcription, -> { OpenAI::Realtime::AudioTranscription }

#turn_detection ⇒ OpenAI::Models::Realtime::RealtimeSessionCreateResponse::Audio::Input::turn_detection?

Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to null to turn off, in which case the client must manually trigger model response.

Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

Semantic VAD is more advanced and uses a turn detection model (in conjunction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency.

For gpt-realtime-whisper transcription sessions, turn detection must be set to null; VAD is not supported.

Returns:

  • (OpenAI::Models::Realtime::RealtimeSessionCreateResponse::Audio::Input::turn_detection, nil) 


315
316
317
318
319
320
321
 
# File 'lib/openai/models/realtime/realtime_session_create_response.rb', line 315

optional(
  :turn_detection,
  union: -> {
    OpenAI::Realtime::RealtimeSessionCreateResponse::Audio::Input::TurnDetection
  },
  nil?: true
)

Instance Method Details

#to_hash ⇒ {

Returns:

  • ({) 


436
 
# File 'sig/openai/models/realtime/realtime_session_create_response.rbs', line 436

def to_hash: -> {