class

OpenAI::VadConfig

Inherits JSON::Serializable < Reference < Object

Constructors

new(pull : JSON::PullParser)
Source
new(type_value : VadConfigType = VadConfigType::ServerVad, prefix_padding_ms : Int64 | Nil = nil, silence_duration_ms : Int64 | Nil = nil, threshold : Float64 | Nil = nil)
Source
new(*, __pull_for_json_serializable pull : JSON::PullParser)
Source

Instance methods

prefix_padding_ms

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

Source
prefix_padding_ms=(prefix_padding_ms : Int64 | Nil)

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

Source
silence_duration_ms

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

Source
silence_duration_ms=(silence_duration_ms : Int64 | Nil)

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

Source
threshold

Sensitivity threshold (0.0 to 1.0) for voice activity detection. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments.

Source
threshold=(threshold : Float64 | Nil)

Sensitivity threshold (0.0 to 1.0) for voice activity detection. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments.

Source
type_value

Must be set to server_vad to enable manual chunking using server side VAD.

Source
type_value=(type_value : VadConfigType)

Must be set to server_vad to enable manual chunking using server side VAD.

Source