Model download address

https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/sherpa-onnx-supertonic-3-tts-int8-2026-05-11.tar.bz2

The following table shows the Android TTS Engine APK with this model for sherpa-onnx v1.13.2

If you don’t know what ABI is, you probably need to select arm64-v8a.

The source code for the APK can be found at

https://github.com/k2-fsa/sherpa-onnx/tree/master/android/SherpaOnnxTtsEngine

Please refer to the documentation for how to build the APK from source code.

More Android APKs can be found at

https://k2-fsa.github.io/sherpa/onnx/tts/apk-engine.html

Assume you have installed sherpa-onnx via

pip install sherpa-onnx

and you have downloaded the model from

https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/sherpa-onnx-supertonic-3-tts-int8-2026-05-11.tar.bz2

You can use the following code to play with supertonic-3

import sherpa_onnx
import soundfile as sf

tts_config = sherpa_onnx.OfflineTtsConfig(
    model=sherpa_onnx.OfflineTtsModelConfig(
        supertonic=sherpa_onnx.OfflineTtsSupertonicModelConfig(
            duration_predictor="sherpa-onnx-supertonic-3-tts-int8-2026-05-11/duration_predictor.int8.onnx",
            text_encoder="sherpa-onnx-supertonic-3-tts-int8-2026-05-11/text_encoder.int8.onnx",
            vector_estimator="sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vector_estimator.int8.onnx",
            vocoder="sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vocoder.int8.onnx",
            tts_json="sherpa-onnx-supertonic-3-tts-int8-2026-05-11/tts.json",
            unicode_indexer="sherpa-onnx-supertonic-3-tts-int8-2026-05-11/unicode_indexer.bin",
            voice_style="sherpa-onnx-supertonic-3-tts-int8-2026-05-11/voice.bin",
        ),
        debug=False,
        num_threads=2,
        provider="cpu",
    ),
)

tts = sherpa_onnx.OfflineTts(tts_config)

gen_config = sherpa_onnx.GenerationConfig()
gen_config.sid = 0
gen_config.num_steps = 8
gen_config.speed = 1.0
gen_config.extra["lang"] = "en"

audio = tts.generate("How are you doing today? This is a text-to-speech engine using next generation Kaldi.", gen_config)

sf.write("test.wav", audio.samples, samplerate=audio.sample_rate)

You can use the following code to play with supertonic-3 with C API.

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include "sherpa-onnx/c-api/c-api.h"

static int32_t ProgressCallback(const float *samples, int32_t num_samples,
                                float progress, void *arg) {
  fprintf(stderr, "Progress: %.3f%%\n", progress * 100);
  // return 1 to continue generating
  // return 0 to stop generating
  return 1;
}

int32_t main(int32_t argc, char *argv[]) {
  SherpaOnnxOfflineTtsConfig config;
  memset(&config, 0, sizeof(config));
  config.model.supertonic.duration_predictor = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/duration_predictor.int8.onnx";
  config.model.supertonic.text_encoder = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/text_encoder.int8.onnx";
  config.model.supertonic.vector_estimator = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vector_estimator.int8.onnx";
  config.model.supertonic.vocoder = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vocoder.int8.onnx";
  config.model.supertonic.tts_json = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/tts.json";
  config.model.supertonic.unicode_indexer = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/unicode_indexer.bin";
  config.model.supertonic.voice_style = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/voice.bin";

  config.model.num_threads = 2;

  // If you don't want to see debug messages, please set it to 0
  config.model.debug = 1;

  const char *text = "How are you doing today? This is a text-to-speech engine using next generation Kaldi.";

  const SherpaOnnxOfflineTts *tts = SherpaOnnxCreateOfflineTts(&config);

  SherpaOnnxGenerationConfig gen_cfg;
  memset(&gen_cfg, 0, sizeof(gen_cfg));
  gen_cfg.sid = 0;
  gen_cfg.num_steps = 8;
  gen_cfg.speed = 1.0;
  gen_cfg.extra = "{\"lang\": \"en\"}";

  const SherpaOnnxGeneratedAudio *audio =
      SherpaOnnxOfflineTtsGenerateWithConfig(tts, text, &gen_cfg,
                                             ProgressCallback, NULL);

  SherpaOnnxWriteWave(audio->samples, audio->n, audio->sample_rate,
                      "./test.wav");

  // You need to free the pointers to avoid memory leak in your app
  SherpaOnnxDestroyOfflineTtsGeneratedAudio(audio);
  SherpaOnnxDestroyOfflineTts(tts);

  printf("Saved to ./test.wav\n");

  return 0;
}

Use shared library (dynamic link)

cd /tmp
git clone https://github.com/k2-fsa/sherpa-onnx
cd sherpa-onnx
mkdir build-shared
cd build-shared

cmake \
 -DSHERPA_ONNX_ENABLE_C_API=ON \
 -DCMAKE_BUILD_TYPE=Release \
 -DBUILD_SHARED_LIBS=ON \
 -DCMAKE_INSTALL_PREFIX=/tmp/sherpa-onnx/shared \
 ..

make
make install

You can find required header file and library files inside /tmp/sherpa-onnx/shared.

Assume you have saved the above example file as /tmp/test-supertonic.c. Then you can compile it with the following command:

gcc \
  -I /tmp/sherpa-onnx/shared/include \
  -L /tmp/sherpa-onnx/shared/lib \
  -lsherpa-onnx-c-api \
  -lonnxruntime \
  -o /tmp/test-supertonic \
  /tmp/test-supertonic.c

Now you can run

cd /tmp

# Assume you have downloaded the model and extracted it to /tmp
./test-supertonic

You probably need to run

# For Linux
export LD_LIBRARY_PATH=/tmp/sherpa-onnx/shared/lib:$LD_LIBRARY_PATH

# For macOS
export DYLD_LIBRARY_PATH=/tmp/sherpa-onnx/shared/lib:$DYLD_LIBRARY_PATH

before you run /tmp/test-supertonic.

Use static library (static link)

Please see the documentation at

https://k2-fsa.github.io/sherpa/onnx/c-api/index.html

You can use the following code to play with supertonic-3 with C++ API.

#include <cstdint>
#include <cstdio>
#include <string>

#include "sherpa-onnx/c-api/cxx-api.h"

static int32_t ProgressCallback(const float *samples, int32_t num_samples,
                                float progress, void *arg) {
  fprintf(stderr, "Progress: %.3f%%\n", progress * 100);
  // return 1 to continue generating
  // return 0 to stop generating
  return 1;
}

int32_t main(int32_t argc, char *argv[]) {
  using namespace sherpa_onnx::cxx; // NOLINT
  OfflineTtsConfig config;

  config.model.supertonic.duration_predictor = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/duration_predictor.int8.onnx";
  config.model.supertonic.text_encoder = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/text_encoder.int8.onnx";
  config.model.supertonic.vector_estimator = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vector_estimator.int8.onnx";
  config.model.supertonic.vocoder = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vocoder.int8.onnx";
  config.model.supertonic.tts_json = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/tts.json";
  config.model.supertonic.unicode_indexer = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/unicode_indexer.bin";
  config.model.supertonic.voice_style = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/voice.bin";

  config.model.num_threads = 2;

  // If you don't want to see debug messages, please set it to 0
  config.model.debug = 1;

  std::string filename = "./test.wav";
  std::string text = "How are you doing today? This is a text-to-speech engine using next generation Kaldi.";

  auto tts = OfflineTts::Create(config);

  GenerationConfig gen_cfg;
  gen_cfg.sid = 0;
  gen_cfg.num_steps = 8;
  gen_cfg.speed = 1.0; // larger -> faster in speech speed
  gen_cfg.extra = R"({"lang": "en"})";

  GeneratedAudio audio = tts.Generate(text, gen_cfg, ProgressCallback);

  WriteWave(filename, {audio.samples, audio.sample_rate});

  fprintf(stderr, "Input text is: %s\n", text.c_str());
  fprintf(stderr, "Speaker ID is: %d\n", gen_cfg.sid);
  fprintf(stderr, "Saved to: %s\n", filename.c_str());

  return 0;
}

Use shared library (dynamic link)

cd /tmp
git clone https://github.com/k2-fsa/sherpa-onnx
cd sherpa-onnx
mkdir build-shared
cd build-shared

cmake \
 -DSHERPA_ONNX_ENABLE_C_API=ON \
 -DCMAKE_BUILD_TYPE=Release \
 -DBUILD_SHARED_LIBS=ON \
 -DCMAKE_INSTALL_PREFIX=/tmp/sherpa-onnx/shared \
 ..

make
make install

You can find required header file and library files inside /tmp/sherpa-onnx/shared.

Assume you have saved the above example file as /tmp/test-supertonic.cc. Then you can compile it with the following command:

g++ \
  -std=c++17 \
  -I /tmp/sherpa-onnx/shared/include \
  -L /tmp/sherpa-onnx/shared/lib \
  -lsherpa-onnx-cxx-api \
  -lsherpa-onnx-c-api \
  -lonnxruntime \
  -o /tmp/test-supertonic \
  /tmp/test-supertonic.cc

Now you can run

cd /tmp

# Assume you have downloaded the model and extracted it to /tmp
./test-supertonic

You probably need to run

# For Linux
export LD_LIBRARY_PATH=/tmp/sherpa-onnx/shared/lib:$LD_LIBRARY_PATH

# For macOS
export DYLD_LIBRARY_PATH=/tmp/sherpa-onnx/shared/lib:$DYLD_LIBRARY_PATH

before you run /tmp/test-supertonic.

Use static library (static link)

Please see the documentation at

https://k2-fsa.github.io/sherpa/onnx/c-api/index.html

You can use the following code to play with supertonic-3 with Rust API.

use sherpa_onnx::{
    GenerationConfig, OfflineTts, OfflineTtsConfig, OfflineTtsSupertonicModelConfig,
};

fn main() {
    let config = OfflineTtsConfig {
        model: sherpa_onnx::OfflineTtsModelConfig {
            supertonic: OfflineTtsSupertonicModelConfig {
                duration_predictor: Some("sherpa-onnx-supertonic-3-tts-int8-2026-05-11/duration_predictor.int8.onnx".into()),
                text_encoder: Some("sherpa-onnx-supertonic-3-tts-int8-2026-05-11/text_encoder.int8.onnx".into()),
                vector_estimator: Some("sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vector_estimator.int8.onnx".into()),
                vocoder: Some("sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vocoder.int8.onnx".into()),
                tts_json: Some("sherpa-onnx-supertonic-3-tts-int8-2026-05-11/tts.json".into()),
                unicode_indexer: Some("sherpa-onnx-supertonic-3-tts-int8-2026-05-11/unicode_indexer.bin".into()),
                voice_style: Some("sherpa-onnx-supertonic-3-tts-int8-2026-05-11/voice.bin".into()),
                ..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 = "How are you doing today? This is a text-to-speech engine using next generation Kaldi.";

    let gen_config = GenerationConfig {
        sid: 0,
        num_steps: 8,
        speed: 1.0,
        extra: Some(r#"{"lang": "en"}"#.into()),
        ..Default::default()
    };

    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 filename = "./test.wav";
    if audio.save(filename) {
        println!("Saved to: {}", filename);
    } else {
        eprintln!("Failed to save {}", filename);
    }
}

Please refer to the Rust API documentation for how to build and run the above Rust example.

You need to install the sherpa-onnx-node npm package first:

npm install sherpa-onnx-node

You can use the following code to play with supertonic-3 with the Node.js addon API.

const sherpa_onnx = require('sherpa-onnx-node');

function createOfflineTts() {
  const config = {
    model: {
      supertonic: {
        durationPredictor: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/duration_predictor.int8.onnx',
        textEncoder: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/text_encoder.int8.onnx',
        vectorEstimator: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vector_estimator.int8.onnx',
        vocoder: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vocoder.int8.onnx',
        ttsJson: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/tts.json',
        unicodeIndexer: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/unicode_indexer.bin',
        voiceStyle: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/voice.bin',
      },
      debug: true,
      numThreads: 2,
      provider: 'cpu',
    },
  };
  return new sherpa_onnx.OfflineTts(config);
}

const tts = createOfflineTts();

const text = 'How are you doing today? This is a text-to-speech engine using next generation Kaldi.';

const generationConfig = new sherpa_onnx.GenerationConfig({
  sid: 0,
  numSteps: 8,
  speed: 1.0,
  extra: {lang: 'en'},
});

let start = Date.now();
const audio = tts.generate({text, generationConfig});
let stop = Date.now();
const elapsed_seconds = (stop - start) / 1000;
const duration = audio.samples.length / audio.sampleRate;
const real_time_factor = elapsed_seconds / duration;
console.log('Wave duration', duration.toFixed(3), 'seconds');
console.log('Elapsed', elapsed_seconds.toFixed(3), 'seconds');
console.log(
    `RTF = ${elapsed_seconds.toFixed(3)}/${duration.toFixed(3)} =`,
    real_time_factor.toFixed(3));

const filename = 'test.wav';
sherpa_onnx.writeWave(
    filename, {samples: audio.samples, sampleRate: audio.sampleRate});

console.log(`Saved to ${filename}`);

Please refer to the Node.js addon API documentation for more details.

You can use the following code to play with supertonic-3 with Dart API.

import 'package:sherpa_onnx/sherpa_onnx.dart' as sherpa_onnx;

void main() {
  final supertonic = sherpa_onnx.OfflineTtsSupertonicModelConfig(
    durationPredictor: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/duration_predictor.int8.onnx',
    textEncoder: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/text_encoder.int8.onnx',
    vectorEstimator: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vector_estimator.int8.onnx',
    vocoder: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vocoder.int8.onnx',
    ttsJson: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/tts.json',
    unicodeIndexer: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/unicode_indexer.bin',
    voiceStyle: 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/voice.bin',
  );

  final modelConfig = sherpa_onnx.OfflineTtsModelConfig(
    supertonic: supertonic,
    numThreads: 2,
    debug: true,
  );
  final config = sherpa_onnx.OfflineTtsConfig(
    model: modelConfig,
  );

  final tts = sherpa_onnx.OfflineTts(config);
  final genConfig = sherpa_onnx.OfflineTtsGenerationConfig(
    sid: 0,
    numSteps: 8,
    speed: 1.0,
    extra: {'lang': 'en'},
  );
  final audio = tts.generateWithConfig(text: 'How are you doing today? This is a text-to-speech engine using next generation Kaldi.', config: genConfig);
  tts.free();

  sherpa_onnx.writeWave(
    filename: 'test.wav',
    samples: audio.samples,
    sampleRate: audio.sampleRate,
  );
  print('Saved to test.wav');
}

Please refer to the Dart API documentation for more details.

You can use the following code to play with supertonic-3 with Swift API.

func run() {
  let supertonic = sherpaOnnxOfflineTtsSupertonicModelConfig(
    durationPredictor: "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/duration_predictor.int8.onnx",
    textEncoder: "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/text_encoder.int8.onnx",
    vectorEstimator: "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vector_estimator.int8.onnx",
    vocoder: "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vocoder.int8.onnx",
    ttsJson: "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/tts.json",
    unicodeIndexer: "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/unicode_indexer.bin",
    voiceStyle: "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/voice.bin"
  )
  let modelConfig = sherpaOnnxOfflineTtsModelConfig(supertonic: supertonic)
  var ttsConfig = sherpaOnnxOfflineTtsConfig(model: modelConfig)

  let tts = SherpaOnnxOfflineTtsWrapper(config: &ttsConfig)

  let text = "How are you doing today? This is a text-to-speech engine using next generation Kaldi."
  var genConfig = SherpaOnnxGenerationConfigSwift()
  genConfig.sid = 0
  genConfig.numSteps = 8
  genConfig.speed = 1.0
  genConfig.extra = ["lang": "en"]

  let audio = tts.generateWithConfig(text: text, config: genConfig, callback: nil, arg: nil)
  let filename = "test.wav"
  let ok = audio.save(filename: filename)
  if ok == 1 {
    print("Saved to \(filename)")
  } else {
    print("Failed to save \(filename)")
  }
}

@main
struct App {
  static func main() {
    run()
  }
}

Please refer to the Swift API documentation for more details.

You can use the following code to play with supertonic-3 with C# API.

using SherpaOnnx;

var config = new OfflineTtsConfig();
config.Model.Supertonic.DurationPredictor = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/duration_predictor.int8.onnx";
config.Model.Supertonic.TextEncoder = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/text_encoder.int8.onnx";
config.Model.Supertonic.VectorEstimator = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vector_estimator.int8.onnx";
config.Model.Supertonic.Vocoder = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vocoder.int8.onnx";
config.Model.Supertonic.TtsJson = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/tts.json";
config.Model.Supertonic.UnicodeIndexer = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/unicode_indexer.bin";
config.Model.Supertonic.VoiceStyle = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/voice.bin";

config.Model.NumThreads = 2;
config.Model.Debug = 1;
config.Model.Provider = "cpu";

var tts = new OfflineTts(config);
var text = "How are you doing today? This is a text-to-speech engine using next generation Kaldi.";

OfflineTtsGenerationConfig genConfig = new OfflineTtsGenerationConfig();
genConfig.Sid = 0;
genConfig.NumSteps = 8;
genConfig.Speed = 1.0f;
genConfig.Extra = "{\"lang\": \"en\"}";

var audio = tts.GenerateWithConfig(text, genConfig, null);
var ok = audio.SaveToWaveFile("./test.wav");

if (ok)
{
  Console.WriteLine("Saved to ./test.wav");
}
else
{
  Console.WriteLine("Failed to save ./test.wav");
}

Please refer to the C# API documentation for more details.

You can use the following code to play with supertonic-3 with Kotlin API.

package com.k2fsa.sherpa.onnx

fun main() {
  var config = OfflineTtsConfig(
    model = OfflineTtsModelConfig(
      supertonic = OfflineTtsSupertonicModelConfig(
        durationPredictor = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/duration_predictor.int8.onnx",
        textEncoder = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/text_encoder.int8.onnx",
        vectorEstimator = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vector_estimator.int8.onnx",
        vocoder = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vocoder.int8.onnx",
        ttsJson = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/tts.json",
        unicodeIndexer = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/unicode_indexer.bin",
        voiceStyle = "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/voice.bin",
      ),
      numThreads = 2,
      debug = true,
    ),
  )
  val tts = OfflineTts(config = config)
  val genConfig = GenerationConfig(
    sid = 0,
    numSteps = 8,
    speed = 1.0f,
    extra = mapOf("lang" to "en"),
  )
  val audio = tts.generateWithConfigAndCallback(
    text = "How are you doing today? This is a text-to-speech engine using next generation Kaldi.",
    config = genConfig,
    callback = ::callback,
  )
  audio.save(filename = "test.wav")
  tts.release()
  println("Saved to test.wav")
}

fun callback(samples: FloatArray): Int {
  // 1 means to continue
  // 0 means to stop
  return 1
}

Please refer to the Kotlin API documentation for more details.

You can use the following code to play with supertonic-3 with Java API.

import com.k2fsa.sherpa.onnx.*;

public class TtsDemo {
  public static void main(String[] args) {
    var supertonic = new OfflineTtsSupertonicModelConfig();
    supertonic.setDurationPredictor("sherpa-onnx-supertonic-3-tts-int8-2026-05-11/duration_predictor.int8.onnx");
    supertonic.setTextEncoder("sherpa-onnx-supertonic-3-tts-int8-2026-05-11/text_encoder.int8.onnx");
    supertonic.setVectorEstimator("sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vector_estimator.int8.onnx");
    supertonic.setVocoder("sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vocoder.int8.onnx");
    supertonic.setTtsJson("sherpa-onnx-supertonic-3-tts-int8-2026-05-11/tts.json");
    supertonic.setUnicodeIndexer("sherpa-onnx-supertonic-3-tts-int8-2026-05-11/unicode_indexer.bin");
    supertonic.setVoiceStyle("sherpa-onnx-supertonic-3-tts-int8-2026-05-11/voice.bin");

    var modelConfig = new OfflineTtsModelConfig();
    modelConfig.setSupertonic(supertonic);
    modelConfig.setNumThreads(2);
    modelConfig.setDebug(true);

    var config = new OfflineTtsConfig();
    config.setModel(modelConfig);

    var tts = new OfflineTts(config);
    var text = "How are you doing today? This is a text-to-speech engine using next generation Kaldi.";

    var genConfig = new GenerationConfig();
    genConfig.setSid(0);
    genConfig.setNumSteps(8);
    genConfig.setSpeed(1.0f);
    genConfig.setExtra("{\"lang\": \"en\"}");

    var audio = tts.generateWithConfigAndCallback(text, genConfig, (samples) -> {
      // 1 means to continue, 0 means to stop
      return 1;
    });

    audio.save("test.wav");
    tts.release();
    System.out.println("Saved to test.wav");
  }
}

Please refer to the Java API documentation for more details.

You can use the following code to play with supertonic-3 with Pascal API.

program test_supertonic;

{$mode objfpc}

uses
  SysUtils,
  sherpa_onnx;

var
  Config: TSherpaOnnxOfflineTtsConfig;
  Tts: TSherpaOnnxOfflineTts;
  Audio: TSherpaOnnxGeneratedAudio;
  GenConfig: TSherpaOnnxGenerationConfig;

begin
  FillChar(Config, SizeOf(Config), 0);

  Config.Model.Supertonic.DurationPredictor := 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/duration_predictor.int8.onnx';
  Config.Model.Supertonic.TextEncoder := 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/text_encoder.int8.onnx';
  Config.Model.Supertonic.VectorEstimator := 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vector_estimator.int8.onnx';
  Config.Model.Supertonic.Vocoder := 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vocoder.int8.onnx';
  Config.Model.Supertonic.TtsJson := 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/tts.json';
  Config.Model.Supertonic.UnicodeIndexer := 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/unicode_indexer.bin';
  Config.Model.Supertonic.VoiceStyle := 'sherpa-onnx-supertonic-3-tts-int8-2026-05-11/voice.bin';

  Config.Model.NumThreads := 2;
  Config.Model.Debug := True;

  Tts := TSherpaOnnxOfflineTts.Create(@Config);

  GenConfig.Sid := 0;
  GenConfig.NumSteps := 8;
  GenConfig.Speed := 1.0;
  GenConfig.Extra := '{"lang": "en"}';

  Audio := Tts.GenerateWithConfig('How are you doing today? This is a text-to-speech engine using next generation Kaldi.', @GenConfig, nil);

  WriteWave('./test.wav', Audio.Samples, Audio.N, Audio.SampleRate);

  WriteLn('Saved to ./test.wav');

  Audio.Free;
  Tts.Free;
end.

Please refer to the Pascal API documentation for more details.

You can use the following code to play with supertonic-3 with Go API.

package main

import (
	"fmt"
	sherpa "github.com/k2-fsa/sherpa-onnx-go/sherpa_onnx"
)

func main() {
	config := sherpa.OfflineTtsConfig{
		Model: sherpa.OfflineTtsModelConfig{
			Supertonic: sherpa.OfflineTtsSupertonicModelConfig{
				DurationPredictor: "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/duration_predictor.int8.onnx",
				TextEncoder:       "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/text_encoder.int8.onnx",
				VectorEstimator:   "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vector_estimator.int8.onnx",
				Vocoder:           "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/vocoder.int8.onnx",
				TtsJson:           "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/tts.json",
				UnicodeIndexer:    "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/unicode_indexer.bin",
				VoiceStyle:        "sherpa-onnx-supertonic-3-tts-int8-2026-05-11/voice.bin",
			},
			NumThreads: 2,
			Debug:      true,
		},
	}

	tts := sherpa.NewOfflineTts(&config)
	defer tts.Delete()

	text := "How are you doing today? This is a text-to-speech engine using next generation Kaldi."

	genConfig := sherpa.GenerationConfig{
		Sid:       0,
		NumSteps:  8,
		Speed:     1.0,
		Extra:     `{"lang": "en"}`,
	}

	audio := tts.GenerateWithConfig(text, &genConfig, nil)

	filename := "./test.wav"
	sherpa.WriteWave(filename, audio.Samples, audio.SampleRate)

	fmt.Printf("Saved to %s\n", filename)
}

Please refer to the Go API documentation for more details.