Struct VoiceTiming 

pub struct VoiceTiming {
    pub reprompt_after_ms: Option<u64>,
    pub reprompt: Option<String>,
    pub filler_after_ms: Option<u64>,
    pub interruptible: Option<bool>,
    pub end_of_speech_ms: Option<u64>,
    pub context_delivery: Option<ContextDelivery>,
}

Voice pacing for one stage. Every field is optional; an unset field leaves the session’s own behaviour alone.

Fields

reprompt_after_ms: Option<u64>

Reprompt once the user has been silent this long (ms) with the floor theirs.

reprompt: Option<String>

What to tell the model when reprompting. Defaults to DEFAULT_REPROMPT.

filler_after_ms: Option<u64>

Cue a filler when a tool call runs longer than this (ms).

interruptible: Option<bool>

Some(false) holds the floor for the model: the user cannot barge in while it speaks (statutory readouts, disclosures).

end_of_speech_ms: Option<u64>

How long a pause must last before the user’s turn ends (ms), under client activity authority.

context_delivery: Option<ContextDelivery>

Context delivery while this stage is active.

Implementations

impl VoiceTiming

pub fn new() -> Self

No timing overrides.

pub fn reprompt_after(self, silence: Duration) -> Self

Reprompt after silence with the default reprompt.

pub fn reprompt_with(self, silence: Duration, text: impl Into<String>) -> Self

Reprompt after silence, telling the model text.

pub fn filler_after(self, after: Duration) -> Self

Cue a filler once a tool call has run for after.

pub fn uninterruptible(self) -> Self

The user cannot interrupt the model in this stage.

pub fn end_of_speech(self, pause: Duration) -> Self

The user’s turn ends after a pause of pause.

pub fn context_delivery(self, delivery: ContextDelivery) -> Self

Deliver steering context this way while the stage is active.

pub fn is_empty(&self) -> bool

Whether nothing is overridden.

pub fn holds_floor(&self) -> bool

Whether the model holds the floor (the user cannot barge in).

pub fn reprompt_text(&self) -> &str

The reprompt text to send.

pub fn merge(&self, other: &Self) -> Self

Combine the timing of two steps active at once, taking the more cautious setting of each: the shorter reprompt and filler waits, the longer end-of-speech pause, and no barge-in if either forbids it. Context delivery and reprompt text come from self when set.

Trait Implementations

impl Clone for VoiceTiming

fn clone(&self) -> VoiceTiming

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for VoiceTiming

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

Formats the value using the given formatter.

impl Default for VoiceTiming

fn default() -> VoiceTiming

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for VoiceTiming

where VoiceTiming: Default,

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl JsonSchema for VoiceTiming

fn schema_name() -> String

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn is_referenceable() -> bool

Whether JSON Schemas generated for this type should be re-used where possible using the $ref keyword.

impl PartialEq for VoiceTiming

fn eq(&self, other: &VoiceTiming) -> 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 VoiceTiming

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Eq for VoiceTiming

impl StructuralPartialEq for VoiceTiming