Class: OpenAI::Models::Realtime::TranscriptionSessionUpdate::Session::TurnDetection

Inherits:
Internal::Type::BaseModel show all
Defined in:
lib/openai/models/realtime/transcription_session_update.rb

Overview

See Also:

Defined Under Namespace

Modules: Type

Instance Attribute 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(prefix_padding_ms: nil, silence_duration_ms: nil, threshold: nil, type: nil) ⇒ Object

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

Configuration for turn detection. Can be set to ‘null` to turn off. 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.

Parameters:

  • prefix_padding_ms (Integer) (defaults to: nil) —

    Amount of audio to include before the VAD detected speech (in

  • silence_duration_ms (Integer) (defaults to: nil) —

    Duration of silence to detect speech stop (in milliseconds). Defaults

  • threshold (Float) (defaults to: nil) —

    Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A

  • type (Symbol, OpenAI::Models::Realtime::TranscriptionSessionUpdate::Session::TurnDetection::Type) (defaults to: nil) —

    Type of turn detection. Only ‘server_vad` is currently supported for transcripti




# File 'lib/openai/models/realtime/transcription_session_update.rb', line 178

Instance Attribute Details

#prefix_padding_ms ⇒ Integer?

Amount of audio to include before the VAD detected speech (in milliseconds). Defaults to 300ms.

Returns:

  • (Integer, nil) 


153
 
# File 'lib/openai/models/realtime/transcription_session_update.rb', line 153

optional :prefix_padding_ms, Integer

#silence_duration_ms ⇒ Integer?

Duration of silence to detect speech stop (in milliseconds). Defaults to 500ms. With shorter values the model will respond more quickly, but may jump in on short pauses from the user.

Returns:

  • (Integer, nil) 


161
 
# File 'lib/openai/models/realtime/transcription_session_update.rb', line 161

optional :silence_duration_ms, Integer

#threshold ⇒ Float?

Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments.

Returns:

  • (Float, nil) 


169
 
# File 'lib/openai/models/realtime/transcription_session_update.rb', line 169

optional :threshold, Float

#type ⇒ Symbol, ...

Type of turn detection. Only ‘server_vad` is currently supported for transcription sessions.

Returns:



176
 
# File 'lib/openai/models/realtime/transcription_session_update.rb', line 176

optional :type, enum: -> { OpenAI::Realtime::TranscriptionSessionUpdate::Session::TurnDetection::Type }