Add C API for KittenTTS (#2467)

@@ -85,6 +85,41 @@ jobs:
             otool -L ./install/lib/libsherpa-onnx-c-api.dylib
           fi
 
+      - name: Test KittenTTS
+        shell: bash
+        run: |
+          name=kitten-tts-en-c-api
+          gcc -o $name ./c-api-examples/$name.c \
+            -I ./build/install/include \
+            -L ./build/install/lib/ \
+            -l sherpa-onnx-c-api \
+            -l onnxruntime
+
+          ls -lh $name
+
+          if [[ ${{ matrix.os }} == ubuntu-latest || ${{ matrix.os }} == ubuntu-22.04-arm ]]; then
+            ldd ./$name
+            echo "----"
+            readelf -d ./$name
+          fi
+
+          curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/kitten-nano-en-v0_1-fp16.tar.bz2
+          tar xf kitten-nano-en-v0_1-fp16.tar.bz2
+          rm kitten-nano-en-v0_1-fp16.tar.bz2
+
+          export LD_LIBRARY_PATH=$PWD/build/install/lib:$LD_LIBRARY_PATH
+          export DYLD_LIBRARY_PATH=$PWD/build/install/lib:$DYLD_LIBRARY_PATH
+
+          ./$name
+
+          rm $name
+          rm -rf kitten-nano-en-v0_1-fp16
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: kitten-tts-wavs-${{ matrix.os }}
+          path: ./generated-kitten-en.wav
+
       - name: Test streaming zipformer with homophone replacer
         shell: bash
         run: |

@@ -23,6 +23,9 @@ if(SHERPA_ONNX_ENABLE_TTS)
   add_executable(kokoro-tts-en-c-api kokoro-tts-en-c-api.c)
   target_link_libraries(kokoro-tts-en-c-api sherpa-onnx-c-api)
 
+  add_executable(kitten-tts-en-c-api kitten-tts-en-c-api.c)
+  target_link_libraries(kitten-tts-en-c-api sherpa-onnx-c-api)
+
   add_executable(kokoro-tts-zh-en-c-api kokoro-tts-zh-en-c-api.c)
   target_link_libraries(kokoro-tts-zh-en-c-api sherpa-onnx-c-api)
 endif()

+// c-api-examples/kitten-tts-en-c-api.c
+//
+// Copyright (c)  2025  Xiaomi Corporation
+
+// This file shows how to use sherpa-onnx C API
+// for English TTS with Kitten.
+//
+// clang-format off
+/*
+Usage
+
+wget 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
+
+./kitten-tts-en-c-api
+
+ */
+// clang-format on
+
+#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) {
+  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.kitten.model = "./kitten-nano-en-v0_1-fp16/model.fp16.onnx";
+  config.model.kitten.voices = "./kitten-nano-en-v0_1-fp16/voices.bin";
+  config.model.kitten.tokens = "./kitten-nano-en-v0_1-fp16/tokens.txt";
+  config.model.kitten.data_dir = "./kitten-nano-en-v0_1-fp16/espeak-ng-data";
+
+  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 *filename = "./generated-kitten-en.wav";
+  const char *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. "
+      "Friends fell out often because life was changing so fast. The easiest "
+      "thing in the world was to lose touch with someone.";
+
+  const SherpaOnnxOfflineTts *tts = SherpaOnnxCreateOfflineTts(&config);
+  // mapping of sid to voice name
+  // 0->af, 1->af_bella, 2->af_nicole, 3->af_sarah, 4->af_sky, 5->am_adam
+  // 6->am_michael, 7->bf_emma, 8->bf_isabella, 9->bm_george, 10->bm_lewis
+  int32_t sid = 0;
+  float speed = 1.0;  // larger -> faster in speech speed
+
+#if 0
+  // If you don't want to use a callback, then please enable this branch
+  const SherpaOnnxGeneratedAudio *audio =
+      SherpaOnnxOfflineTtsGenerate(tts, text, sid, speed);
+#else
+  const SherpaOnnxGeneratedAudio *audio =
+      SherpaOnnxOfflineTtsGenerateWithProgressCallback(tts, text, sid, speed,
+                                                       ProgressCallback);
+#endif
+
+  SherpaOnnxWriteWave(audio->samples, audio->n, audio->sample_rate, filename);
+
+  SherpaOnnxDestroyOfflineTtsGeneratedAudio(audio);
+  SherpaOnnxDestroyOfflineTts(tts);
+
+  fprintf(stderr, "Input text is: %s\n", text);
+  fprintf(stderr, "Speaker ID is: %d\n", sid);
+  fprintf(stderr, "Saved to: %s\n", filename);
+
+  return 0;
+}

@@ -77,7 +77,7 @@ int32_t main(int32_t argc, char *argv[]) {
   SherpaOnnxDestroyOfflineTts(tts);
 
   fprintf(stderr, "Input text is: %s\n", text);
-  fprintf(stderr, "Speaker ID is is: %d\n", sid);
+  fprintf(stderr, "Speaker ID is: %d\n", sid);
   fprintf(stderr, "Saved to: %s\n", filename);
 
   return 0;

@@ -75,7 +75,7 @@ int32_t main(int32_t argc, char *argv[]) {
   SherpaOnnxDestroyOfflineTts(tts);
 
   fprintf(stderr, "Input text is: %s\n", text);
-  fprintf(stderr, "Speaker ID is is: %d\n", sid);
+  fprintf(stderr, "Speaker ID is: %d\n", sid);
   fprintf(stderr, "Saved to: %s\n", filename);
 
   return 0;

@@ -80,7 +80,7 @@ int32_t main(int32_t argc, char *argv[]) {
   SherpaOnnxDestroyOfflineTts(tts);
 
   fprintf(stderr, "Input text is: %s\n", text);
-  fprintf(stderr, "Speaker ID is is: %d\n", sid);
+  fprintf(stderr, "Speaker ID is: %d\n", sid);
   fprintf(stderr, "Saved to: %s\n", filename);
 
   return 0;

@@ -80,7 +80,7 @@ int32_t main(int32_t argc, char *argv[]) {
   SherpaOnnxDestroyOfflineTts(tts);
 
   fprintf(stderr, "Input text is: %s\n", text);
-  fprintf(stderr, "Speaker ID is is: %d\n", sid);
+  fprintf(stderr, "Speaker ID is: %d\n", sid);
   fprintf(stderr, "Saved to: %s\n", filename);
 
   return 0;

@@ -240,7 +240,7 @@ int32_t main(int32_t argc, char *argv[]) {
   SherpaOnnxDestroyOfflineTts(tts);
 
   fprintf(stderr, "Input text is: %s\n", text);
-  fprintf(stderr, "Speaker ID is is: %d\n", sid);
+  fprintf(stderr, "Speaker ID is: %d\n", sid);
   fprintf(stderr, "Saved to: %s\n", filename);
 
   free((void *)filename);

@@ -1207,6 +1207,18 @@ static sherpa_onnx::OfflineTtsConfig GetOfflineTtsConfig(
       SHERPA_ONNX_OR(config->model.kokoro.lexicon, "");
   tts_config.model.kokoro.lang = SHERPA_ONNX_OR(config->model.kokoro.lang, "");
 
+  // kitten
+  tts_config.model.kitten.model =
+      SHERPA_ONNX_OR(config->model.kitten.model, "");
+  tts_config.model.kitten.voices =
+      SHERPA_ONNX_OR(config->model.kitten.voices, "");
+  tts_config.model.kitten.tokens =
+      SHERPA_ONNX_OR(config->model.kitten.tokens, "");
+  tts_config.model.kitten.data_dir =
+      SHERPA_ONNX_OR(config->model.kitten.data_dir, "");
+  tts_config.model.kitten.length_scale =
+      SHERPA_ONNX_OR(config->model.kitten.length_scale, 1.0);
+
   tts_config.model.num_threads = SHERPA_ONNX_OR(config->model.num_threads, 1);
   tts_config.model.debug = config->model.debug;
   tts_config.model.provider = SHERPA_ONNX_OR(config->model.provider, "cpu");

@@ -1032,6 +1032,15 @@ SHERPA_ONNX_API typedef struct SherpaOnnxOfflineTtsKokoroModelConfig {
   const char *lang;
 } SherpaOnnxOfflineTtsKokoroModelConfig;
 
+SHERPA_ONNX_API typedef struct SherpaOnnxOfflineTtsKittenModelConfig {
+  const char *model;
+  const char *voices;
+  const char *tokens;
+  const char *data_dir;
+
+  float length_scale;  // < 1, faster in speech speed; > 1, slower in speed
+} SherpaOnnxOfflineTtsKittenModelConfig;
+
 SHERPA_ONNX_API typedef struct SherpaOnnxOfflineTtsModelConfig {
   SherpaOnnxOfflineTtsVitsModelConfig vits;
   int32_t num_threads;
@@ -1039,6 +1048,7 @@ SHERPA_ONNX_API typedef struct SherpaOnnxOfflineTtsModelConfig {
   const char *provider;
   SherpaOnnxOfflineTtsMatchaModelConfig matcha;
   SherpaOnnxOfflineTtsKokoroModelConfig kokoro;
+  SherpaOnnxOfflineTtsKittenModelConfig kitten;
 } SherpaOnnxOfflineTtsModelConfig;
 
 SHERPA_ONNX_API typedef struct SherpaOnnxOfflineTtsConfig {