Struct StartSpeakingPlan

pub struct StartSpeakingPlan {
    pub wait_seconds: Option<f64>,
    pub smart_endpointing_enabled: Option<SmartEndpointingEnabled>,
    pub custom_endpointing_rules: Option<Vec<StartSpeakingPlanCustomEndpointingRulesInner>>,
    pub transcription_endpointing_plan: Option<Box<TranscriptionEndpointingPlan>>,
}

Fields

wait_seconds: Option<f64>

This is how long assistant waits before speaking. Defaults to 0.4. This is the minimum it will wait but if there is latency is the pipeline, this minimum will be exceeded. This is intended as a stopgap in case the pipeline is moving too fast. Example: - If model generates tokens and voice generates bytes within 100ms, the pipeline still waits 300ms before outputting speech. Usage: - If the customer is taking long pauses, set this to a higher value. - If the assistant is accidentally jumping in too much, set this to a higher value. @default 0.4

smart_endpointing_enabled: Option<SmartEndpointingEnabled>

This determines if a customer speech is considered done (endpointing) using a Vapi custom-trained model on customer’s speech. This is good for middle-of-thought detection. Alternatively, you can use LiveKit’s smart endpointing model (it only supports English, though) Once an endpoint is triggered, the request is sent to assistant.model. Usage: - If your conversations are long-form and you want assistant to wait smartly even if customer pauses for a bit to think, you can use this instead. This overrides transcriptionEndpointingPlan. @default false

custom_endpointing_rules: Option<Vec<StartSpeakingPlanCustomEndpointingRulesInner>>

These are the custom endpointing rules to set an endpointing timeout based on a regex on the customer’s speech or the assistant’s last message. Usage: - If you have yes/no questions like "are you interested in a loan?", you can set a shorter timeout. - If you have questions where the customer may pause to look up information like "what’s my account number?", you can set a longer timeout. - If you want to wait longer while customer is enumerating a list of numbers, you can set a longer timeout. These override transcriptionEndpointingPlan and smartEndpointingEnabled when a rule is matched. The rules are evaluated in order and the first one that matches will be used. @default []

transcription_endpointing_plan: Option<Box<TranscriptionEndpointingPlan>>

This determines how a customer speech is considered done (endpointing) using the transcription of customer’s speech. Once an endpoint is triggered, the request is sent to assistant.model.

Implementations

impl StartSpeakingPlan

pub fn new() -> StartSpeakingPlan

Trait Implementations

impl Clone for StartSpeakingPlan

fn clone(&self) -> StartSpeakingPlan

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for StartSpeakingPlan

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

Formats the value using the given formatter.

impl Default for StartSpeakingPlan

fn default() -> StartSpeakingPlan

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for StartSpeakingPlan

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for StartSpeakingPlan

fn eq(&self, other: &StartSpeakingPlan) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for StartSpeakingPlan

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for StartSpeakingPlan