Struct RealtimeSpeechConfig 

pub struct RealtimeSpeechConfig { /* private fields */ }

Static codec-token geometry shared by every session of one realtime model.

Implementations

impl RealtimeSpeechConfig

pub fn new( total_audio_codebooks: usize, input_audio_codebooks: usize, generated_audio_codebooks: usize, depth_audio_codebooks: usize, text_padding_token: i32, audio_padding_token: i32, frame_convention: RealtimeFrameConvention, delays: Vec<usize>, ) -> Result<Self, RealtimeConfigError>

Creates and validates portable realtime codec geometry.

pub const fn total_audio_codebooks(&self) -> usize

Total number of temporal-model audio codebooks.

pub const fn input_audio_codebooks(&self) -> usize

Number of live input-side codebooks per frame.

pub const fn generated_audio_codebooks(&self) -> usize

Number of generated-side codebooks per frame.

pub const fn depth_audio_codebooks(&self) -> usize

Number of depth-transformer codebooks per frame.

pub const fn text_padding_token(&self) -> i32

Text token used before sampled text is available.

pub const fn audio_padding_token(&self) -> i32

Audio token used while delayed streams warm up.

pub const fn frame_convention(&self) -> RealtimeFrameConvention

Explicit delayed-frame coordinate convention.

pub fn delays(&self) -> &[usize]

Complete text-plus-audio delay schedule in canonical slot order.

pub fn text_delay(&self) -> usize

Leading text-stream delay.

pub fn audio_delays(&self) -> &[usize]

Per-codebook delays following the leading text delay.

pub fn max_delay(&self) -> usize

Largest delay across the complete text-plus-audio schedule.

pub fn max_audio_delay(&self) -> usize

Largest audio delay in frames.

Trait Implementations

impl Clone for RealtimeSpeechConfig

fn clone(&self) -> RealtimeSpeechConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RealtimeSpeechConfig

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for RealtimeSpeechConfig

fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>

where D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for RealtimeSpeechConfig

impl PartialEq for RealtimeSpeechConfig

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for RealtimeSpeechConfig

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 RealtimeSpeechConfig