Add JavaScript API (node-addon) for KittenTTS (#2470)

@@ -10,6 +10,14 @@ arch=$(node -p "require('os').arch()")
 platform=$(node -p "require('os').platform()")
 node_version=$(node -p "process.versions.node.split('.')[0]")
 
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/kitten-nano-en-v0_1-fp16.tar.bz2
+tar xf kitten-nano-en-v0_1-fp16.tar.bz2
+rm kitten-nano-en-v0_1-fp16.tar.bz2
+
+node ./test_tts_non_streaming_kitten_en.js
+
+rm -rf kitten-nano-en-v0_1-fp16
+
 echo "----------non-streaming ASR NeMo Canary----------"
 
 curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-nemo-canary-180m-flash-en-es-de-fr-int8.tar.bz2

@@ -37,9 +37,9 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [macos-latest, ubuntu-latest, ubuntu-latest]
+        os: [macos-latest, ubuntu-latest]
         node-version: ["16", "22"]
-        python-version: ["3.8"]
+        python-version: ["3.10"]
 
     steps:
       - uses: actions/checkout@v4

@@ -36,7 +36,8 @@ export { OnlineStream,
   OnlineRecognizer,
 } from './src/main/ets/components/StreamingAsr';
 
-export { OfflineTtsKokoroModelConfig,
+export { OfflineTtsKittenModelConfig,
+  OfflineTtsKokoroModelConfig,
   OfflineTtsMatchaModelConfig,
   OfflineTtsVitsModelConfig,
   OfflineTtsModelConfig,

@@ -75,6 +75,25 @@ static SherpaOnnxOfflineTtsKokoroModelConfig GetOfflineTtsKokoroModelConfig(
   return c;
 }
 
+static SherpaOnnxOfflineTtsKittenModelConfig GetOfflineTtsKittenModelConfig(
+    Napi::Object obj) {
+  SherpaOnnxOfflineTtsKittenModelConfig c;
+  memset(&c, 0, sizeof(c));
+
+  if (!obj.Has("kitten") || !obj.Get("kitten").IsObject()) {
+    return c;
+  }
+
+  Napi::Object o = obj.Get("kitten").As<Napi::Object>();
+  SHERPA_ONNX_ASSIGN_ATTR_STR(model, model);
+  SHERPA_ONNX_ASSIGN_ATTR_STR(voices, voices);
+  SHERPA_ONNX_ASSIGN_ATTR_STR(tokens, tokens);
+  SHERPA_ONNX_ASSIGN_ATTR_STR(data_dir, dataDir);
+  SHERPA_ONNX_ASSIGN_ATTR_FLOAT(length_scale, lengthScale);
+
+  return c;
+}
+
 static SherpaOnnxOfflineTtsModelConfig GetOfflineTtsModelConfig(
     Napi::Object obj) {
   SherpaOnnxOfflineTtsModelConfig c;
@@ -89,6 +108,7 @@ static SherpaOnnxOfflineTtsModelConfig GetOfflineTtsModelConfig(
   c.vits = GetOfflineTtsVitsModelConfig(o);
   c.matcha = GetOfflineTtsMatchaModelConfig(o);
   c.kokoro = GetOfflineTtsKokoroModelConfig(o);
+  c.kitten = GetOfflineTtsKittenModelConfig(o);
 
   SHERPA_ONNX_ASSIGN_ATTR_INT32(num_threads, numThreads);
 
@@ -172,6 +192,11 @@ static Napi::External<SherpaOnnxOfflineTts> CreateOfflineTtsWrapper(
   SHERPA_ONNX_DELETE_C_STR(c.model.matcha.data_dir);
   SHERPA_ONNX_DELETE_C_STR(c.model.matcha.dict_dir);
 
+  SHERPA_ONNX_DELETE_C_STR(c.model.kitten.model);
+  SHERPA_ONNX_DELETE_C_STR(c.model.kitten.voices);
+  SHERPA_ONNX_DELETE_C_STR(c.model.kitten.tokens);
+  SHERPA_ONNX_DELETE_C_STR(c.model.kitten.data_dir);
+
   SHERPA_ONNX_DELETE_C_STR(c.model.kokoro.model);
   SHERPA_ONNX_DELETE_C_STR(c.model.kokoro.voices);
   SHERPA_ONNX_DELETE_C_STR(c.model.kokoro.tokens);

@@ -39,10 +39,19 @@ export class OfflineTtsKokoroModelConfig {
   public lang: string = '';
 }
 
+export class OfflineTtsKittenModelConfig {
+  public model: string = '';
+  public voices: string = '';
+  public tokens: string = '';
+  public dataDir: string = '';
+  public lengthScale: number = 1.0;
+}
+
 export class OfflineTtsModelConfig {
   public vits: OfflineTtsVitsModelConfig = new OfflineTtsVitsModelConfig();
   public matcha: OfflineTtsMatchaModelConfig = new OfflineTtsMatchaModelConfig();
   public kokoro: OfflineTtsKokoroModelConfig = new OfflineTtsKokoroModelConfig();
+  public kitten: OfflineTtsKittenModelConfig = new OfflineTtsKittenModelConfig();
   public numThreads: number = 1;
   public debug: boolean = false;
   public provider: string = 'cpu';

@@ -147,6 +147,7 @@ The following tables list the examples in this folder.
 
 |File| Description|
 |---|---|
+|[./test_tts_non_streaming_kitten_en.js](./test_tts_non_streaming_kitten_en.js)| Text-to-speech with a KittenTTS English Model|
 |[./test_tts_non_streaming_kokoro_en.js](./test_tts_non_streaming_kokoro_en.js)| Text-to-speech with a Kokoro English Model|
 |[./test_tts_non_streaming_kokoro_zh_en.js](./test_tts_non_streaming_kokoro_zh_en.js)| Text-to-speech with a Kokoro Model supporting Chinese and English|
 |[./test_tts_non_streaming_matcha_icefall_en.js](./test_tts_non_streaming_matcha_icefall_en.js)| Text-to-speech with a [MatchaTTS English Model](https://k2-fsa.github.io/sherpa/onnx/tts/pretrained_models/matcha.html#matcha-icefall-en-us-ljspeech-american-english-1-female-speaker)|
@@ -458,6 +459,16 @@ npm install naudiodon2
 node ./test_vad_asr_non_streaming_sense_voice_microphone.js
 ```
 
+### Text-to-speech with KittenTTS models (English TTS)
+
+```bash
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/kitten-nano-en-v0_1-fp16.tar.bz2
+tar xf kitten-nano-en-v0_1-fp16.tar.bz2
+rm kitten-nano-en-v0_1-fp16.tar.bz2
+
+node ./test_tts_non_streaming_kitten_en.js
+```
+
 ### Text-to-speech with Kokoro TTS models (Chinese + English TTS)
 
 ```bash

+// Copyright (c)  2025  Xiaomi Corporation
+const sherpa_onnx = require('sherpa-onnx-node');
+
+// please refer to
+// https://k2-fsa.github.io/sherpa/onnx/tts/pretrained_models/kitten.html
+// to download model files
+function createOfflineTts() {
+  const config = {
+    model: {
+      kitten: {
+        model: './kitten-nano-en-v0_1-fp16/model.fp16.onnx',
+        voices: './kitten-nano-en-v0_1-fp16/voices.bin',
+        tokens: './kitten-nano-en-v0_1-fp16/tokens.txt',
+        dataDir: './kitten-nano-en-v0_1-fp16/espeak-ng-data',
+      },
+      debug: true,
+      numThreads: 1,
+      provider: 'cpu',
+    },
+    maxNumSentences: 1,
+  };
+  return new sherpa_onnx.OfflineTts(config);
+}
+
+const tts = createOfflineTts();
+
+const text =
+    'Today as always, men fall into two groups: slaves and free men. Whoever does not have two-thirds of his day for himself, is a slave, whatever he may be: a statesman, a businessman, an official, or a scholar.'
+
+
+let start = Date.now();
+const audio = tts.generate({text: text, sid: 6, speed: 1.0});
+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-kitten-en-6.wav';
+sherpa_onnx.writeWave(
+    filename, {samples: audio.samples, sampleRate: audio.sampleRate});
+
+console.log(`Saved to ${filename}`);