Struct RealtimeSessionCreateResponseTurnDetection

pub struct RealtimeSessionCreateResponseTurnDetection {
    pub prefix_padding_ms: Option<i32>,
    pub silence_duration_ms: Option<i32>,
    pub threshold: Option<f32>,
    pub _type: Option<String>,
}

Fields

prefix_padding_ms: Option<i32>

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

silence_duration_ms: Option<i32>

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.

threshold: Option<f32>

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.

_type: Option<String>

Type of turn detection, only server_vad is currently supported.

Trait Implementations

impl Debug for RealtimeSessionCreateResponseTurnDetection

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for RealtimeSessionCreateResponseTurnDetection

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for RealtimeSessionCreateResponseTurnDetection

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.