kitten-tts-en-c-api.c
2.8 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
// 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->expr-voice-2-m, 1->expr-voice-2-f, 2->expr-voice-3-m
// 3->expr-voice-3-f, 4->expr-voice-4-m, 5->expr-voice-4-f
// 6->expr-voice-5-m, 7->expr-voice-5-f
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;
}