sherpa-onnx/rust-api-examples/examples/kokoro_tts_zh_en_lexicon.rs

// Copyright (c) 2026 Xiaomi Corporation
//
// This file demonstrates how to use Kokoro TTS with sherpa-onnx's Rust API
// for offline Chinese + English text-to-speech.

use sherpa_onnx::{
    GenerationConfig, OfflineTts, OfflineTtsConfig, OfflineTtsKokoroModelConfig,
};
use std::time::Instant;

fn main() {
    let config = OfflineTtsConfig {
        model: sherpa_onnx::OfflineTtsModelConfig {
            kokoro: OfflineTtsKokoroModelConfig {
                model: Some("./kokoro-multi-lang-v1_0/model.onnx".into()),
                voices: Some("./kokoro-multi-lang-v1_0/voices.bin".into()),
                tokens: Some("./kokoro-multi-lang-v1_0/tokens.txt".into()),
                lexicon: Some(
                    "./kokoro-multi-lang-v1_0/lexicon-us-en.txt,./kokoro-multi-lang-v1_0/lexicon-zh.txt".into(),
                ),
                length_scale: 1.0,
                ..Default::default()
            },
            num_threads: 2,
            debug: false,
            ..Default::default()
        },
        ..Default::default()
    };

    let tts = OfflineTts::create(&config).expect("Failed to create OfflineTts");

    println!("Sample rate: {}", tts.sample_rate());
    println!("Num speakers: {}", tts.num_speakers());

    let text = "中英文语音合成测试。This is generated by next generation Kaldi using \
        Kokoro without Misaki. 你觉得中英文说的如何呢？";

    let gen_config = GenerationConfig {
        sid: 0,
        speed: 1.0,
        ..Default::default()
    };

    let start = Instant::now();

    let audio = tts
        .generate_with_config(
            text,
            &gen_config,
            Some(|_samples: &[f32], progress: f32| -> bool {
                println!("Progress: {:.1}%", progress * 100.0);
                true
            }),
        )
        .expect("Generation failed");

    let elapsed_seconds = start.elapsed().as_secs_f32();
    let duration = audio.samples().len() as f32 / audio.sample_rate() as f32;
    let rtf = elapsed_seconds / duration;

    println!("Number of threads: {}", config.model.num_threads);
    println!("Elapsed seconds: {:.3} s", elapsed_seconds);
    println!("Audio duration: {:.3} s", duration);
    println!(
        "Real-time factor (RTF): {:.3}/{:.3} = {:.3}",
        elapsed_seconds, duration, rtf
    );

    let filename = "./generated-kokoro-zh-en-lexicon-rust.wav";
    if audio.save(filename) {
        println!("Saved to: {}", filename);
    } else {
        eprintln!("Failed to save {}", filename);
    }
}