Trait TtsEngine 

pub trait TtsEngine: InferenceEngine {
    // Required methods
    fn synthesize_speech<'life0, 'life1, 'life2, 'async_trait>(
        &'life0 self,
        text: &'life1 str,
        language: Option<&'life2 str>,
        chunk_frames: usize,
    ) -> Pin<Box<dyn Future<Output = Result<Vec<Vec<f32>>>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait,
             'life2: 'async_trait;
    fn tts_sample_rate(&self) -> u32;
}

Text-to-speech (Qwen3-TTS, etc.) engine.

Backs /v1/audio/speech.

Required Methods

fn synthesize_speech<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, text: &'life1 str, language: Option<&'life2 str>, chunk_frames: usize, ) -> Pin<Box<dyn Future<Output = Result<Vec<Vec<f32>>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Synthesize speech → PCM audio chunks (streaming). Returns Vec of PCM f32 samples per chunk.

fn tts_sample_rate(&self) -> u32

Get TTS sample rate.

Dyn Compatibility

This trait is dyn compatible.

In older versions of Rust, dyn compatibility was called "object safety".

Implementors