Class: OpenAI::Models::Realtime::RealtimeTranscriptionSessionTurnDetection
- Inherits:
-
Internal::Type::BaseModel
- Object
- Internal::Type::BaseModel
- OpenAI::Models::Realtime::RealtimeTranscriptionSessionTurnDetection
- Defined in:
- lib/openai/models/realtime/realtime_transcription_session_turn_detection.rb
Instance Attribute Summary collapse
-
#prefix_padding_ms ⇒ Integer?
Amount of audio to include before the VAD detected speech (in milliseconds).
-
#silence_duration_ms ⇒ Integer?
Duration of silence to detect speech stop (in milliseconds).
-
#threshold ⇒ Float?
Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5.
-
#type ⇒ String?
Type of turn detection, only ‘server_vad` is currently supported.
Method Summary
Methods inherited from Internal::Type::BaseModel
#==, ==, #[], coerce, #deconstruct_keys, #deep_to_h, dump, fields, hash, #hash, inherited, #initialize, 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
This class inherits a constructor from OpenAI::Internal::Type::BaseModel
Instance Attribute Details
#prefix_padding_ms ⇒ Integer?
Amount of audio to include before the VAD detected speech (in milliseconds). Defaults to 300ms.
12 |
# File 'lib/openai/models/realtime/realtime_transcription_session_turn_detection.rb', line 12 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.
20 |
# File 'lib/openai/models/realtime/realtime_transcription_session_turn_detection.rb', line 20 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.
28 |
# File 'lib/openai/models/realtime/realtime_transcription_session_turn_detection.rb', line 28 optional :threshold, Float |
#type ⇒ String?
Type of turn detection, only ‘server_vad` is currently supported.
34 |
# File 'lib/openai/models/realtime/realtime_transcription_session_turn_detection.rb', line 34 optional :type, String |