class

OpenAI::RealtimeTurnDetectionVariant1Inner2

Inherits JSON::Serializable < Reference < Object

Server-side semantic turn detection which uses a model to determine when the user has finished speaking.

Constructors

new(pull : JSON::PullParser)
Source
new(type_value : String = "", eagerness : RealtimeTurnDetectionVariant1Inner2Eagerness | Nil = nil, create_response : Bool | Nil = nil, interrupt_response : Bool | Nil = nil)
Source
new(*, __pull_for_json_serializable pull : JSON::PullParser)
Source

Instance methods

create_response

Whether or not to automatically generate a response when a VAD stop event occurs.

Source
create_response=(create_response : Bool | Nil)

Whether or not to automatically generate a response when a VAD stop event occurs.

Source
eagerness

Used only for semantic_vad mode. The eagerness of the model to respond. low will wait longer for the user to continue speaking, high will respond more quickly. auto is the default and is equivalent to medium. low, medium, and high have max timeouts of 8s, 4s, and 2s respectively.

Source
eagerness=(eagerness : RealtimeTurnDetectionVariant1Inner2Eagerness | Nil)

Used only for semantic_vad mode. The eagerness of the model to respond. low will wait longer for the user to continue speaking, high will respond more quickly. auto is the default and is equivalent to medium. low, medium, and high have max timeouts of 8s, 4s, and 2s respectively.

Source
interrupt_response

Whether or not to automatically interrupt any ongoing response with output to the default conversation (i.e. conversation of auto) when a VAD start event occurs.

Source
interrupt_response=(interrupt_response : Bool | Nil)

Whether or not to automatically interrupt any ongoing response with output to the default conversation (i.e. conversation of auto) when a VAD start event occurs.

Source
type_value

Type of turn detection, semantic_vad to turn on Semantic VAD.

Source
type_value=(type_value : String)

Type of turn detection, semantic_vad to turn on Semantic VAD.

Source