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
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257 | /**************************************************************************/
/* tts_linux.cpp */
/**************************************************************************/
/* This file is part of: */
/* GODOT ENGINE */
/* https://godotengine.org */
/**************************************************************************/
/* Copyright (c) 2014-present Godot Engine contributors (see AUTHORS.md). */
/* Copyright (c) 2007-2014 Juan Linietsky, Ariel Manzur. */
/* */
/* Permission is hereby granted, free of charge, to any person obtaining */
/* a copy of this software and associated documentation files (the */
/* "Software"), to deal in the Software without restriction, including */
/* without limitation the rights to use, copy, modify, merge, publish, */
/* distribute, sublicense, and/or sell copies of the Software, and to */
/* permit persons to whom the Software is furnished to do so, subject to */
/* the following conditions: */
/* */
/* The above copyright notice and this permission notice shall be */
/* included in all copies or substantial portions of the Software. */
/* */
/* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, */
/* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF */
/* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. */
/* IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY */
/* CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, */
/* TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE */
/* SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. */
/**************************************************************************/
#include "tts_linux.h"
#include "core/project_settings.h"
TTS_Linux *TTS_Linux::singleton = nullptr;
static bool _is_whitespace(CharType c) {
return c == '\t' || c == ' ';
}
void TTS_Linux::speech_init_thread_func(void *p_userdata) {
TTS_Linux *tts = (TTS_Linux *)p_userdata;<--- C-style pointer casting [+]C-style pointer casting detected. C++ offers four different kinds of casts as replacements: static_cast, const_cast, dynamic_cast and reinterpret_cast. A C-style cast could evaluate to any of those automatically, thus it is considered safer if the programmer explicitly states which kind of cast is expected. See also: https://www.securecoding.cert.org/confluence/display/cplusplus/EXP05-CPP.+Do+not+use+C-style+casts.
if (tts) {
MutexLock thread_safe_method(tts->_thread_safe_);
#ifdef DEBUG_ENABLED
int dylibloader_verbose = 1;
#else
int dylibloader_verbose = 0;
#endif
if (initialize_speechd(dylibloader_verbose) == 0) {
CharString class_str;
String config_name = GLOBAL_GET("application/config/name");
if (config_name.length() == 0) {
class_str = "Godot_Engine";
} else {
class_str = config_name.utf8();
}
tts->synth = spd_open(class_str, "Godot_Engine_Speech_API", "Godot_Engine", SPD_MODE_THREADED);
if (tts->synth) {
tts->synth->callback_end = &speech_event_callback;
tts->synth->callback_cancel = &speech_event_callback;
tts->synth->callback_im = &speech_event_index_mark;
spd_set_notification_on(tts->synth, SPD_END);
spd_set_notification_on(tts->synth, SPD_CANCEL);
print_verbose("Text-to-Speech: Speech Dispatcher initialized.");
} else {
print_verbose("Text-to-Speech: Cannot initialize Speech Dispatcher synthesizer!");
}
} else {
print_verbose("Text-to-Speech: Cannot load Speech Dispatcher library!");
}
}
}
void TTS_Linux::speech_event_index_mark(size_t p_msg_id, size_t p_client_id, SPDNotificationType p_type, char *p_index_mark) {
TTS_Linux *tts = TTS_Linux::get_singleton();
if (tts && tts->ids.has(p_msg_id)) {
MutexLock thread_safe_method(tts->_thread_safe_);
// Get word offset from the index mark injected to the text stream.
String mark = String::utf8(p_index_mark);
OS::get_singleton()->tts_post_utterance_event(OS::TTS_UTTERANCE_BOUNDARY, tts->ids[p_msg_id], mark.to_int());
}
}
void TTS_Linux::speech_event_callback(size_t p_msg_id, size_t p_client_id, SPDNotificationType p_type) {
TTS_Linux *tts = TTS_Linux::get_singleton();
if (tts) {
MutexLock thread_safe_method(tts->_thread_safe_);
List<OS::TTSUtterance> &queue = tts->queue;
if (!tts->paused && tts->ids.has(p_msg_id)) {
if (p_type == SPD_EVENT_END) {
OS::get_singleton()->tts_post_utterance_event(OS::TTS_UTTERANCE_ENDED, tts->ids[p_msg_id]);
tts->ids.erase(p_msg_id);
tts->last_msg_id = -1;
tts->speaking = false;
} else if (p_type == SPD_EVENT_CANCEL) {
OS::get_singleton()->tts_post_utterance_event(OS::TTS_UTTERANCE_CANCELED, tts->ids[p_msg_id]);
tts->ids.erase(p_msg_id);
tts->last_msg_id = -1;
tts->speaking = false;
}
}
if (!tts->speaking && queue.size() > 0) {
OS::TTSUtterance &message = queue.front()->get();
// Inject index mark after each word.
String text;
PoolIntArray breaks;
for (int i = 0; i < message.text.size(); i++) {
if (_is_whitespace(message.text[i])) {
breaks.push_back(i);
}
}
int prev = 0;
for (int i = 0; i < breaks.size(); i++) {
text += message.text.substr(prev, breaks[i] - prev);
text += "<mark name=\"" + String::num_int64(breaks[i], 10) + "\"/>";
prev = breaks[i];
}
text += message.text.substr(prev, -1);
spd_set_synthesis_voice(tts->synth, message.voice.utf8().get_data());
spd_set_volume(tts->synth, message.volume * 2 - 100);
spd_set_voice_pitch(tts->synth, (message.pitch - 1) * 100);
float rate = 0;
if (message.rate > 1.f) {
rate = log10(MIN(message.rate, 2.5f)) / log10(2.5f) * 100;
} else if (message.rate < 1.f) {
rate = log10(MAX(message.rate, 0.5f)) / log10(0.5f) * -100;
}
spd_set_voice_rate(tts->synth, rate);
spd_set_data_mode(tts->synth, SPD_DATA_SSML);
tts->last_msg_id = spd_say(tts->synth, SPD_TEXT, text.utf8().get_data());
tts->ids[tts->last_msg_id] = message.id;
OS::get_singleton()->tts_post_utterance_event(OS::TTS_UTTERANCE_STARTED, message.id);
queue.pop_front();
tts->speaking = true;
}
}
}
bool TTS_Linux::is_speaking() const {
return speaking;
}
bool TTS_Linux::is_paused() const {
return paused;
}
Array TTS_Linux::get_voices() const {
_THREAD_SAFE_METHOD_
ERR_FAIL_COND_V(!synth, Array());
Array list;
SPDVoice **voices = spd_list_synthesis_voices(synth);
if (voices != nullptr) {
SPDVoice **voices_ptr = voices;
while (*voices_ptr != nullptr) {
Dictionary voice_d;
voice_d["name"] = String::utf8((*voices_ptr)->name);
voice_d["id"] = String::utf8((*voices_ptr)->name);
voice_d["language"] = String::utf8((*voices_ptr)->language) + "_" + String::utf8((*voices_ptr)->variant);
list.push_back(voice_d);
voices_ptr++;
}
free_spd_voices(voices);
}
return list;
}
void TTS_Linux::speak(const String &p_text, const String &p_voice, int p_volume, float p_pitch, float p_rate, int p_utterance_id, bool p_interrupt) {
_THREAD_SAFE_METHOD_
ERR_FAIL_COND(!synth);
if (p_interrupt) {
stop();
}
if (p_text.empty()) {
OS::get_singleton()->tts_post_utterance_event(OS::TTS_UTTERANCE_CANCELED, p_utterance_id);
return;
}
OS::TTSUtterance message;
message.text = p_text;
message.voice = p_voice;
message.volume = CLAMP(p_volume, 0, 100);
message.pitch = CLAMP(p_pitch, 0.f, 2.f);
message.rate = CLAMP(p_rate, 0.1f, 10.f);
message.id = p_utterance_id;
queue.push_back(message);
if (is_paused()) {
resume();
} else {
speech_event_callback(0, 0, SPD_EVENT_BEGIN);
}
}
void TTS_Linux::pause() {
_THREAD_SAFE_METHOD_
ERR_FAIL_COND(!synth);
if (spd_pause(synth) == 0) {
paused = true;
}
}
void TTS_Linux::resume() {
_THREAD_SAFE_METHOD_
ERR_FAIL_COND(!synth);
spd_resume(synth);
paused = false;
}
void TTS_Linux::stop() {
_THREAD_SAFE_METHOD_
ERR_FAIL_COND(!synth);
for (List<OS::TTSUtterance>::Element *E = queue.front(); E; E = E->next()) {
OS::TTSUtterance &message = E->get();
OS::get_singleton()->tts_post_utterance_event(OS::TTS_UTTERANCE_CANCELED, message.id);
}
if ((last_msg_id != -1) && ids.has(last_msg_id)) {
OS::get_singleton()->tts_post_utterance_event(OS::TTS_UTTERANCE_CANCELED, ids[last_msg_id]);
}
queue.clear();
ids.clear();
last_msg_id = -1;
spd_cancel(synth);
spd_resume(synth);
speaking = false;
paused = false;
}
TTS_Linux *TTS_Linux::get_singleton() {
return singleton;
}
TTS_Linux::TTS_Linux() {
singleton = this;
// Speech Dispatcher init can be slow, it might wait for helper process to start on background, so run it in the thread.
init_thread.start(speech_init_thread_func, this);
}
TTS_Linux::~TTS_Linux() {
init_thread.wait_to_finish();
if (synth) {
spd_close(synth);
}
singleton = nullptr;
}
|