File size: 8,503 Bytes
b82d373
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import { isMobile } from '../../RossAscends-mods.js';
import { getPreviewString } from './index.js';
import { talkingAnimation } from './index.js';
import { saveTtsProviderSettings } from './index.js';
export { SystemTtsProvider };

/**
 * Chunkify
 * Google Chrome Speech Synthesis Chunking Pattern
 * Fixes inconsistencies with speaking long texts in speechUtterance objects
 * Licensed under the MIT License
 *
 * Peter Woolley and Brett Zamir
 * Modified by Haaris for bug fixes
 */

var speechUtteranceChunker = function (utt, settings, callback) {
    settings = settings || {};
    var newUtt;
    var txt = (settings && settings.offset !== undefined ? utt.text.substring(settings.offset) : utt.text);
    if (utt.voice && utt.voice.voiceURI === 'native') { // Not part of the spec
        newUtt = utt;
        newUtt.text = txt;
        newUtt.addEventListener('end', function () {
            if (speechUtteranceChunker.cancel) {
                speechUtteranceChunker.cancel = false;
            }
            if (callback !== undefined) {
                callback();
            }
        });
    }
    else {
        var chunkLength = (settings && settings.chunkLength) || 160;
        var pattRegex = new RegExp('^[\\s\\S]{' + Math.floor(chunkLength / 2) + ',' + chunkLength + '}[.!?,]{1}|^[\\s\\S]{1,' + chunkLength + '}$|^[\\s\\S]{1,' + chunkLength + '} ');
        var chunkArr = txt.match(pattRegex);

        if (chunkArr == null || chunkArr[0] === undefined || chunkArr[0].length <= 2) {
            //call once all text has been spoken...
            if (callback !== undefined) {
                callback();
            }
            return;
        }
        var chunk = chunkArr[0];
        newUtt = new SpeechSynthesisUtterance(chunk);
        var x;
        for (x in utt) {
            if (Object.hasOwn(utt, x) && x !== 'text') {
                newUtt[x] = utt[x];
            }
        }
        newUtt.lang = utt.lang;
        newUtt.voice = utt.voice;
        newUtt.addEventListener('end', function () {
            if (speechUtteranceChunker.cancel) {
                speechUtteranceChunker.cancel = false;
                return;
            }
            settings.offset = settings.offset || 0;
            settings.offset += chunk.length;
            speechUtteranceChunker(utt, settings, callback);
        });
    }

    if (settings.modifier) {
        settings.modifier(newUtt);
    }
    console.log(newUtt); //IMPORTANT!! Do not remove: Logging the object out fixes some onend firing issues.
    //placing the speak invocation inside a callback fixes ordering and onend issues.
    setTimeout(function () {
        speechSynthesis.speak(newUtt);
        talkingAnimation(true);
    }, 0);
};

class SystemTtsProvider {
    //########//
    // Config //
    //########//

    settings;
    ready = false;
    voices = [];
    separator = ' ... ';

    defaultSettings = {
        voiceMap: {},
        rate: 1,
        pitch: 1,
    };

    get settingsHtml() {
        if (!('speechSynthesis' in window)) {
            return 'Your browser or operating system doesn\'t support speech synthesis';
        }

        return `<p>Uses the voices provided by your operating system</p>
        <label for="system_tts_rate">Rate: <span id="system_tts_rate_output"></span></label>
        <input id="system_tts_rate" type="range" value="${this.defaultSettings.rate}" min="0.1" max="2" step="0.01" />
        <label for="system_tts_pitch">Pitch: <span id="system_tts_pitch_output"></span></label>
        <input id="system_tts_pitch" type="range" value="${this.defaultSettings.pitch}" min="0" max="2" step="0.01" />`;
    }

    onSettingsChange() {
        this.settings.rate = Number($('#system_tts_rate').val());
        this.settings.pitch = Number($('#system_tts_pitch').val());
        $('#system_tts_pitch_output').text(this.settings.pitch);
        $('#system_tts_rate_output').text(this.settings.rate);
        saveTtsProviderSettings();
    }

    async loadSettings(settings) {
        // Populate Provider UI given input settings
        if (Object.keys(settings).length == 0) {
            console.info('Using default TTS Provider settings');
        }

        // iOS should only allows speech synthesis trigged by user interaction
        if (isMobile()) {
            let hasEnabledVoice = false;

            document.addEventListener('click', () => {
                if (hasEnabledVoice) {
                    return;
                }
                const utterance = new SpeechSynthesisUtterance(' . ');
                utterance.volume = 0;
                speechSynthesis.speak(utterance);
                hasEnabledVoice = true;
            });
        }

        // Only accept keys defined in defaultSettings
        this.settings = this.defaultSettings;

        for (const key in settings) {
            if (key in this.settings) {
                this.settings[key] = settings[key];
            } else {
                throw `Invalid setting passed to TTS Provider: ${key}`;
            }
        }

        $('#system_tts_rate').val(this.settings.rate || this.defaultSettings.rate);
        $('#system_tts_pitch').val(this.settings.pitch || this.defaultSettings.pitch);

        // Trigger updates
        $('#system_tts_rate').on('input', () => { this.onSettingsChange(); });
        $('#system_tts_pitch').on('input', () => { this.onSettingsChange(); });

        $('#system_tts_pitch_output').text(this.settings.pitch);
        $('#system_tts_rate_output').text(this.settings.rate);
        console.debug('SystemTTS: Settings loaded');
    }

    // Perform a simple readiness check by trying to fetch voiceIds
    async checkReady() {
        await this.fetchTtsVoiceObjects();
    }

    async onRefreshClick() {
        return;
    }

    //#################//
    //  TTS Interfaces //
    //#################//
    fetchTtsVoiceObjects() {
        if (!('speechSynthesis' in window)) {
            return [];
        }

        return new Promise((resolve) => {
            setTimeout(() => {
                const voices = speechSynthesis
                    .getVoices()
                    .sort((a, b) => a.lang.localeCompare(b.lang) || a.name.localeCompare(b.name))
                    .map(x => ({ name: x.name, voice_id: x.voiceURI, preview_url: false, lang: x.lang }));

                resolve(voices);
            }, 1);
        });
    }

    previewTtsVoice(voiceId) {
        if (!('speechSynthesis' in window)) {
            throw 'Speech synthesis API is not supported';
        }

        const voice = speechSynthesis.getVoices().find(x => x.voiceURI === voiceId);

        if (!voice) {
            throw `TTS Voice id ${voiceId} not found`;
        }

        speechSynthesis.cancel();
        const text = getPreviewString(voice.lang);
        const utterance = new SpeechSynthesisUtterance(text);
        utterance.voice = voice;
        utterance.rate = this.settings.rate || 1;
        utterance.pitch = this.settings.pitch || 1;
        speechSynthesis.speak(utterance);
    }

    async getVoice(voiceName) {
        if (!('speechSynthesis' in window)) {
            return { voice_id: null };
        }

        const voices = speechSynthesis.getVoices();
        const match = voices.find(x => x.name == voiceName);

        if (!match) {
            throw `TTS Voice name ${voiceName} not found`;
        }

        return { voice_id: match.voiceURI, name: match.name };
    }

    async generateTts(text, voiceId) {
        if (!('speechSynthesis' in window)) {
            throw 'Speech synthesis API is not supported';
        }

        const silence = await fetch('/sounds/silence.mp3');

        return new Promise((resolve, reject) => {
            const voices = speechSynthesis.getVoices();
            const voice = voices.find(x => x.voiceURI === voiceId);
            const utterance = new SpeechSynthesisUtterance(text);
            utterance.voice = voice;
            utterance.rate = this.settings.rate || 1;
            utterance.pitch = this.settings.pitch || 1;
            utterance.onend = () => resolve(silence);
            utterance.onerror = () => reject();
            speechUtteranceChunker(utterance, {
                chunkLength: 200,
            }, function () {
                //some code to execute when done
                resolve(silence);
                console.log('System TTS done');
                talkingAnimation(false);
            });
        });
    }
}