Class: Telnyx::Models::AI::Assistants::UpdateAssistant::InterruptionSettings::StartSpeakingPlan

Inherits:

Internal::Type::BaseModel

• Object
• Internal::Type::BaseModel
• Telnyx::Models::AI::Assistants::UpdateAssistant::InterruptionSettings::StartSpeakingPlan

Defined in:

lib/telnyx/models/ai/assistants/update_assistant.rb

Overview

See Also:

• #start_speaking_plan

Defined Under Namespace

Classes: TranscriptionEndpointingPlan

Instance Attribute Summary

• #transcription_endpointing_plan ⇒ Telnyx::Models::AI::Assistants::UpdateAssistant::InterruptionSettings::StartSpeakingPlan::TranscriptionEndpointingPlan^?

  Endpointing thresholds used to decide when the user has finished speaking.

• #wait_seconds ⇒ Float^?

  Minimum seconds to wait before the assistant starts speaking.

Instance Method Summary

• #initialize(transcription_endpointing_plan: nil, wait_seconds: nil) ⇒ Object constructor

  Some parameter documentations has been truncated, see StartSpeakingPlan for more details.

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(transcription_endpointing_plan: nil, wait_seconds: nil) ⇒ Object

Some parameter documentations has been truncated, see Telnyx::Models::AI::Assistants::UpdateAssistant::InterruptionSettings::StartSpeakingPlan for more details.

Controls when the assistant starts speaking after the user stops. These thresholds primarily apply to non turn-taking transcription models. For turn-taking models like ‘deepgram/flux`, end-of-turn detection is driven by the transcription end-of-turn settings under `transcription.settings` instead.

Parameters:

• transcription_endpointing_plan (Telnyx::Models::AI::Assistants::UpdateAssistant::InterruptionSettings::StartSpeakingPlan::TranscriptionEndpointingPlan) (defaults to: nil) —

  Endpointing thresholds used to decide when the user has finished speaking. Appli

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

  Minimum seconds to wait before the assistant starts speaking.

# File 'lib/telnyx/models/ai/assistants/update_assistant.rb', line 554

Instance Attribute Details

#transcription_endpointing_plan ⇒ Telnyx::Models::AI::Assistants::UpdateAssistant::InterruptionSettings::StartSpeakingPlan::TranscriptionEndpointingPlan^?

Endpointing thresholds used to decide when the user has finished speaking. Applies to non turn-taking transcription models. For ‘deepgram/flux`, use `transcription.settings.eot_threshold` / `eot_timeout_ms` / `eager_eot_threshold`.

Returns:

• (Telnyx::Models::AI::Assistants::UpdateAssistant::InterruptionSettings::StartSpeakingPlan::TranscriptionEndpointingPlan, nil)

# File 'lib/telnyx/models/ai/assistants/update_assistant.rb', line 545

optional :transcription_endpointing_plan,
-> { Telnyx::AI::Assistants::UpdateAssistant::InterruptionSettings::StartSpeakingPlan::TranscriptionEndpointingPlan }

#wait_seconds ⇒ Float^?

Minimum seconds to wait before the assistant starts speaking.

Returns:

• (Float, nil)

# File 'lib/telnyx/models/ai/assistants/update_assistant.rb', line 552

optional :wait_seconds, Float