web-speech-cognitive-services 8.1.3-main.b33949a → 8.1.4-main.202512240452.5ddefc2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/web-speech-cognitive-services.d.mts +10 -10
- package/dist/web-speech-cognitive-services.d.ts +10 -10
- package/dist/web-speech-cognitive-services.development.js +26 -23
- package/dist/web-speech-cognitive-services.development.js.map +1 -1
- package/dist/web-speech-cognitive-services.js +26 -23
- package/dist/web-speech-cognitive-services.js.map +1 -1
- package/dist/web-speech-cognitive-services.mjs +26 -23
- package/dist/web-speech-cognitive-services.mjs.map +1 -1
- package/dist/web-speech-cognitive-services.production.min.js +10 -10
- package/dist/web-speech-cognitive-services.production.min.js.map +1 -1
- package/package.json +11 -9
|
@@ -166,7 +166,7 @@ type PatchOptionsInit = {
|
|
|
166
166
|
textNormalization?: 'display' | 'itn' | 'lexical' | 'maskeditn' | undefined;
|
|
167
167
|
};
|
|
168
168
|
|
|
169
|
-
declare function createSpeechRecognitionPonyfill(options: PatchOptionsInit): {
|
|
169
|
+
declare function createSpeechRecognitionPonyfill$1(options: PatchOptionsInit): {
|
|
170
170
|
SpeechGrammarList: typeof SpeechGrammarList;
|
|
171
171
|
SpeechRecognition: {
|
|
172
172
|
new (): {
|
|
@@ -267,7 +267,7 @@ declare function createSpeechRecognitionPonyfillFromRecognizer({ createRecognize
|
|
|
267
267
|
SpeechRecognitionEvent: typeof SpeechRecognitionEvent;
|
|
268
268
|
};
|
|
269
269
|
|
|
270
|
-
declare class
|
|
270
|
+
declare class AudioContextConsumer {
|
|
271
271
|
constructor(audioContext: any);
|
|
272
272
|
audioContext: any;
|
|
273
273
|
pause(): void;
|
|
@@ -277,12 +277,12 @@ declare class _default$2 {
|
|
|
277
277
|
stop(): void;
|
|
278
278
|
}
|
|
279
279
|
|
|
280
|
-
declare class
|
|
280
|
+
declare class AudioContextQueue {
|
|
281
281
|
constructor({ audioContext, ponyfill }: {
|
|
282
282
|
audioContext: any;
|
|
283
283
|
ponyfill: any;
|
|
284
284
|
});
|
|
285
|
-
consumer:
|
|
285
|
+
consumer: AudioContextConsumer | null;
|
|
286
286
|
paused: boolean;
|
|
287
287
|
queue: any[];
|
|
288
288
|
getAudioContext: memoize_one.MemoizedFn<() => any>;
|
|
@@ -341,13 +341,13 @@ declare class SpeechSynthesisUtterance {
|
|
|
341
341
|
stop(): void;
|
|
342
342
|
}
|
|
343
343
|
|
|
344
|
-
declare function
|
|
345
|
-
speechSynthesis?:
|
|
346
|
-
SpeechSynthesisEvent?:
|
|
347
|
-
SpeechSynthesisUtterance?:
|
|
344
|
+
declare function createSpeechRecognitionPonyfill(options: any): {
|
|
345
|
+
speechSynthesis?: undefined;
|
|
346
|
+
SpeechSynthesisEvent?: undefined;
|
|
347
|
+
SpeechSynthesisUtterance?: undefined;
|
|
348
348
|
} | {
|
|
349
349
|
speechSynthesis: {
|
|
350
|
-
queue:
|
|
350
|
+
queue: AudioContextQueue;
|
|
351
351
|
cancel(): void;
|
|
352
352
|
getVoices(): any[];
|
|
353
353
|
onvoiceschanged: any;
|
|
@@ -369,4 +369,4 @@ declare function fetchAuthorizationToken({ region, subscriptionKey }: FetchAutho
|
|
|
369
369
|
|
|
370
370
|
declare function createSpeechServicesPonyfill(options?: any): any;
|
|
371
371
|
|
|
372
|
-
export { createSpeechRecognitionPonyfill, createSpeechRecognitionPonyfillFromRecognizer, createSpeechServicesPonyfill,
|
|
372
|
+
export { createSpeechRecognitionPonyfill$1 as createSpeechRecognitionPonyfill, createSpeechRecognitionPonyfillFromRecognizer, createSpeechServicesPonyfill, createSpeechRecognitionPonyfill as createSpeechSynthesisPonyfill, fetchAuthorizationToken };
|
|
@@ -166,7 +166,7 @@ type PatchOptionsInit = {
|
|
|
166
166
|
textNormalization?: 'display' | 'itn' | 'lexical' | 'maskeditn' | undefined;
|
|
167
167
|
};
|
|
168
168
|
|
|
169
|
-
declare function createSpeechRecognitionPonyfill(options: PatchOptionsInit): {
|
|
169
|
+
declare function createSpeechRecognitionPonyfill$1(options: PatchOptionsInit): {
|
|
170
170
|
SpeechGrammarList: typeof SpeechGrammarList;
|
|
171
171
|
SpeechRecognition: {
|
|
172
172
|
new (): {
|
|
@@ -267,7 +267,7 @@ declare function createSpeechRecognitionPonyfillFromRecognizer({ createRecognize
|
|
|
267
267
|
SpeechRecognitionEvent: typeof SpeechRecognitionEvent;
|
|
268
268
|
};
|
|
269
269
|
|
|
270
|
-
declare class
|
|
270
|
+
declare class AudioContextConsumer {
|
|
271
271
|
constructor(audioContext: any);
|
|
272
272
|
audioContext: any;
|
|
273
273
|
pause(): void;
|
|
@@ -277,12 +277,12 @@ declare class _default$2 {
|
|
|
277
277
|
stop(): void;
|
|
278
278
|
}
|
|
279
279
|
|
|
280
|
-
declare class
|
|
280
|
+
declare class AudioContextQueue {
|
|
281
281
|
constructor({ audioContext, ponyfill }: {
|
|
282
282
|
audioContext: any;
|
|
283
283
|
ponyfill: any;
|
|
284
284
|
});
|
|
285
|
-
consumer:
|
|
285
|
+
consumer: AudioContextConsumer | null;
|
|
286
286
|
paused: boolean;
|
|
287
287
|
queue: any[];
|
|
288
288
|
getAudioContext: memoize_one.MemoizedFn<() => any>;
|
|
@@ -341,13 +341,13 @@ declare class SpeechSynthesisUtterance {
|
|
|
341
341
|
stop(): void;
|
|
342
342
|
}
|
|
343
343
|
|
|
344
|
-
declare function
|
|
345
|
-
speechSynthesis?:
|
|
346
|
-
SpeechSynthesisEvent?:
|
|
347
|
-
SpeechSynthesisUtterance?:
|
|
344
|
+
declare function createSpeechRecognitionPonyfill(options: any): {
|
|
345
|
+
speechSynthesis?: undefined;
|
|
346
|
+
SpeechSynthesisEvent?: undefined;
|
|
347
|
+
SpeechSynthesisUtterance?: undefined;
|
|
348
348
|
} | {
|
|
349
349
|
speechSynthesis: {
|
|
350
|
-
queue:
|
|
350
|
+
queue: AudioContextQueue;
|
|
351
351
|
cancel(): void;
|
|
352
352
|
getVoices(): any[];
|
|
353
353
|
onvoiceschanged: any;
|
|
@@ -369,4 +369,4 @@ declare function fetchAuthorizationToken({ region, subscriptionKey }: FetchAutho
|
|
|
369
369
|
|
|
370
370
|
declare function createSpeechServicesPonyfill(options?: any): any;
|
|
371
371
|
|
|
372
|
-
export { createSpeechRecognitionPonyfill, createSpeechRecognitionPonyfillFromRecognizer, createSpeechServicesPonyfill,
|
|
372
|
+
export { createSpeechRecognitionPonyfill$1 as createSpeechRecognitionPonyfill, createSpeechRecognitionPonyfillFromRecognizer, createSpeechServicesPonyfill, createSpeechRecognitionPonyfill as createSpeechSynthesisPonyfill, fetchAuthorizationToken };
|
|
@@ -24883,13 +24883,14 @@
|
|
|
24883
24883
|
|
|
24884
24884
|
// src/SpeechServices/SpeechSDK.ts
|
|
24885
24885
|
var import_microsoft_cognitiveservices_speech_sdk = __toESM(require_microsoft_cognitiveservices_speech_sdk());
|
|
24886
|
-
var
|
|
24886
|
+
var SpeechSDK = {
|
|
24887
24887
|
AudioConfig: import_microsoft_cognitiveservices_speech_sdk.AudioConfig,
|
|
24888
24888
|
OutputFormat: import_microsoft_cognitiveservices_speech_sdk.OutputFormat,
|
|
24889
24889
|
ResultReason: import_microsoft_cognitiveservices_speech_sdk.ResultReason,
|
|
24890
24890
|
SpeechConfig: import_microsoft_cognitiveservices_speech_sdk.SpeechConfig,
|
|
24891
24891
|
SpeechRecognizer: import_microsoft_cognitiveservices_speech_sdk.SpeechRecognizer
|
|
24892
24892
|
};
|
|
24893
|
+
var SpeechSDK_default = SpeechSDK;
|
|
24893
24894
|
|
|
24894
24895
|
// src/SpeechServices/SpeechToText/validation/credentialsSchema.ts
|
|
24895
24896
|
var credentialsSchema = pipe(
|
|
@@ -25022,7 +25023,7 @@
|
|
|
25022
25023
|
}
|
|
25023
25024
|
|
|
25024
25025
|
// src/Util/createPromiseQueue.js
|
|
25025
|
-
function
|
|
25026
|
+
function createPromiseQueue() {
|
|
25026
25027
|
let shiftDeferred;
|
|
25027
25028
|
const queue = [];
|
|
25028
25029
|
const push = (value) => {
|
|
@@ -25103,7 +25104,7 @@
|
|
|
25103
25104
|
var {
|
|
25104
25105
|
ResultReason: { RecognizingSpeech, RecognizedSpeech }
|
|
25105
25106
|
} = SpeechSDK_default;
|
|
25106
|
-
function
|
|
25107
|
+
function cognitiveServiceEventResultToWebSpeechRecognitionResult(result, init) {
|
|
25107
25108
|
const { maxAlternatives = Infinity, textNormalization = "display" } = init || {};
|
|
25108
25109
|
const json = typeof result.json === "string" ? JSON.parse(result.json) : result.json;
|
|
25109
25110
|
if (result.reason === RecognizingSpeech || result.reason === RecognizedSpeech && !json.NBest) {
|
|
@@ -25468,7 +25469,7 @@
|
|
|
25468
25469
|
const recognizer = await createRecognizer(this.lang);
|
|
25469
25470
|
const { pause, unprepare } = prepareAudioConfig(recognizer["audioConfig"]);
|
|
25470
25471
|
try {
|
|
25471
|
-
const queue =
|
|
25472
|
+
const queue = createPromiseQueue();
|
|
25472
25473
|
let soundStarted;
|
|
25473
25474
|
let speechStarted;
|
|
25474
25475
|
let stopping;
|
|
@@ -25619,7 +25620,7 @@
|
|
|
25619
25620
|
speechStarted = true;
|
|
25620
25621
|
}
|
|
25621
25622
|
if (recognized) {
|
|
25622
|
-
const result =
|
|
25623
|
+
const result = cognitiveServiceEventResultToWebSpeechRecognitionResult(recognized.result, {
|
|
25623
25624
|
maxAlternatives: this.maxAlternatives,
|
|
25624
25625
|
textNormalization
|
|
25625
25626
|
});
|
|
@@ -25651,7 +25652,7 @@
|
|
|
25651
25652
|
new SpeechRecognitionEvent("result", {
|
|
25652
25653
|
results: new SpeechRecognitionResultList([
|
|
25653
25654
|
...finalizedResults,
|
|
25654
|
-
|
|
25655
|
+
cognitiveServiceEventResultToWebSpeechRecognitionResult(recognizing.result, {
|
|
25655
25656
|
maxAlternatives: this.maxAlternatives,
|
|
25656
25657
|
textNormalization
|
|
25657
25658
|
})
|
|
@@ -26648,7 +26649,7 @@
|
|
|
26648
26649
|
}
|
|
26649
26650
|
|
|
26650
26651
|
// src/SpeechServices/TextToSpeech/AudioContextConsumer.js
|
|
26651
|
-
var
|
|
26652
|
+
var AudioContextConsumer = class {
|
|
26652
26653
|
constructor(audioContext) {
|
|
26653
26654
|
this.audioContext = audioContext;
|
|
26654
26655
|
}
|
|
@@ -26677,7 +26678,7 @@
|
|
|
26677
26678
|
};
|
|
26678
26679
|
|
|
26679
26680
|
// src/SpeechServices/TextToSpeech/AudioContextQueue.js
|
|
26680
|
-
var
|
|
26681
|
+
var AudioContextQueue = class {
|
|
26681
26682
|
constructor({ audioContext, ponyfill: ponyfill2 }) {
|
|
26682
26683
|
this.consumer = null;
|
|
26683
26684
|
this.paused = false;
|
|
@@ -26705,7 +26706,7 @@
|
|
|
26705
26706
|
}
|
|
26706
26707
|
async startConsumer() {
|
|
26707
26708
|
while (!this.paused && this.queue.length && !this.consumer) {
|
|
26708
|
-
this.consumer = new
|
|
26709
|
+
this.consumer = new AudioContextConsumer(this.getAudioContext());
|
|
26709
26710
|
await this.consumer.start(this.queue);
|
|
26710
26711
|
this.consumer = null;
|
|
26711
26712
|
}
|
|
@@ -26830,7 +26831,7 @@
|
|
|
26830
26831
|
var DEFAULT_OUTPUT_FORMAT = "riff-16khz-16bit-mono-pcm";
|
|
26831
26832
|
var DEFAULT_VOICE = "Microsoft Server Speech Text to Speech Voice (en-US, AriaNeural)";
|
|
26832
26833
|
var EMPTY_MP3_BASE64 = "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";
|
|
26833
|
-
async function
|
|
26834
|
+
async function fetchSpeechData({
|
|
26834
26835
|
deploymentId,
|
|
26835
26836
|
fetchCredentials,
|
|
26836
26837
|
lang = DEFAULT_LANGUAGE,
|
|
@@ -26998,7 +26999,7 @@
|
|
|
26998
26999
|
this._volume = value;
|
|
26999
27000
|
}
|
|
27000
27001
|
preload({ deploymentId, fetchCredentials, outputFormat }) {
|
|
27001
|
-
this.arrayBufferPromise =
|
|
27002
|
+
this.arrayBufferPromise = fetchSpeechData({
|
|
27002
27003
|
fetchCredentials,
|
|
27003
27004
|
deploymentId,
|
|
27004
27005
|
lang: this.lang || window.navigator.language,
|
|
@@ -27031,7 +27032,7 @@
|
|
|
27031
27032
|
var SpeechSynthesisUtterance_default = SpeechSynthesisUtterance;
|
|
27032
27033
|
|
|
27033
27034
|
// src/SpeechServices/TextToSpeech/SpeechSynthesisVoice.js
|
|
27034
|
-
var
|
|
27035
|
+
var SpeechSynthesisVoice = class {
|
|
27035
27036
|
constructor({ gender, lang, voiceURI }) {
|
|
27036
27037
|
this._default = false;
|
|
27037
27038
|
this._gender = gender;
|
|
@@ -27061,7 +27062,7 @@
|
|
|
27061
27062
|
};
|
|
27062
27063
|
|
|
27063
27064
|
// src/SpeechServices/TextToSpeech/fetchCustomVoices.js
|
|
27064
|
-
async function
|
|
27065
|
+
async function fetchCustomVoices_({ customVoiceHostname, deploymentId, region, subscriptionKey }) {
|
|
27065
27066
|
const hostname = customVoiceHostname || `${region}.customvoice.api.speech.microsoft.com`;
|
|
27066
27067
|
const res = await fetch(
|
|
27067
27068
|
`https://${encodeURI(hostname)}/api/texttospeech/v2.0/endpoints/${encodeURIComponent(deploymentId)}`,
|
|
@@ -27077,10 +27078,10 @@
|
|
|
27077
27078
|
}
|
|
27078
27079
|
return res.json();
|
|
27079
27080
|
}
|
|
27080
|
-
async function
|
|
27081
|
-
const { models } = await
|
|
27081
|
+
async function fetchCustomVoices({ customVoiceHostname, deploymentId, region, subscriptionKey }) {
|
|
27082
|
+
const { models } = await fetchCustomVoices_({ customVoiceHostname, deploymentId, region, subscriptionKey });
|
|
27082
27083
|
return models.map(
|
|
27083
|
-
({ properties: { Gender: gender }, locale: lang, name: voiceURI }) => new
|
|
27084
|
+
({ properties: { Gender: gender }, locale: lang, name: voiceURI }) => new SpeechSynthesisVoice({ gender, lang, voiceURI })
|
|
27084
27085
|
).sort(({ name: x }, { name: y }) => x > y ? 1 : x < y ? -1 : 0);
|
|
27085
27086
|
}
|
|
27086
27087
|
|
|
@@ -27101,13 +27102,13 @@
|
|
|
27101
27102
|
throw new Error("Failed to fetch voices");
|
|
27102
27103
|
}
|
|
27103
27104
|
const voices = await res.json();
|
|
27104
|
-
return voices.map(({ Gender: gender, Locale: lang, Name: voiceURI }) => new
|
|
27105
|
+
return voices.map(({ Gender: gender, Locale: lang, Name: voiceURI }) => new SpeechSynthesisVoice({ gender, lang, voiceURI })).sort(({ name: x }, { name: y }) => x > y ? 1 : x < y ? -1 : 0);
|
|
27105
27106
|
}
|
|
27106
27107
|
|
|
27107
27108
|
// src/SpeechServices/TextToSpeech/createSpeechSynthesisPonyfill.js
|
|
27108
27109
|
var DEFAULT_OUTPUT_FORMAT2 = "audio-24khz-160kbitrate-mono-mp3";
|
|
27109
27110
|
var EMPTY_ARRAY = [];
|
|
27110
|
-
|
|
27111
|
+
function createSpeechRecognitionPonyfill2(options) {
|
|
27111
27112
|
const {
|
|
27112
27113
|
audioContext,
|
|
27113
27114
|
fetchCredentials,
|
|
@@ -27126,7 +27127,7 @@
|
|
|
27126
27127
|
class SpeechSynthesis extends EventTarget2 {
|
|
27127
27128
|
constructor() {
|
|
27128
27129
|
super();
|
|
27129
|
-
this.queue = new
|
|
27130
|
+
this.queue = new AudioContextQueue({ audioContext, ponyfill: ponyfill2 });
|
|
27130
27131
|
this.updateVoices();
|
|
27131
27132
|
}
|
|
27132
27133
|
cancel() {
|
|
@@ -27181,7 +27182,7 @@
|
|
|
27181
27182
|
"web-speech-cognitive-services: Listing of custom voice models are only available when using subscription key."
|
|
27182
27183
|
);
|
|
27183
27184
|
await onErrorResumeNext(async () => {
|
|
27184
|
-
const voices = await
|
|
27185
|
+
const voices = await fetchCustomVoices({
|
|
27185
27186
|
customVoiceHostname,
|
|
27186
27187
|
deploymentId: speechSynthesisDeploymentId,
|
|
27187
27188
|
region,
|
|
@@ -27205,7 +27206,8 @@
|
|
|
27205
27206
|
SpeechSynthesisEvent,
|
|
27206
27207
|
SpeechSynthesisUtterance: SpeechSynthesisUtterance_default
|
|
27207
27208
|
};
|
|
27208
|
-
}
|
|
27209
|
+
}
|
|
27210
|
+
var createSpeechSynthesisPonyfill_default = createSpeechRecognitionPonyfill2;
|
|
27209
27211
|
|
|
27210
27212
|
// src/SpeechServices/TextToSpeech.js
|
|
27211
27213
|
var TextToSpeech_default = createSpeechSynthesisPonyfill_default;
|
|
@@ -27219,12 +27221,13 @@
|
|
|
27219
27221
|
}
|
|
27220
27222
|
var meta = document.createElement("meta");
|
|
27221
27223
|
meta.setAttribute("name", "web-speech-cognitive-services");
|
|
27222
|
-
meta.setAttribute("content", `version=${"8.1.
|
|
27224
|
+
meta.setAttribute("content", `version=${"8.1.4-main.202512240452.5ddefc2"}`);
|
|
27223
27225
|
document.head.appendChild(meta);
|
|
27226
|
+
var SpeechServices_default = createSpeechServicesPonyfill;
|
|
27224
27227
|
|
|
27225
27228
|
// src/index.umd.js
|
|
27226
27229
|
globalThis.WebSpeechCognitiveServices = {
|
|
27227
|
-
create:
|
|
27230
|
+
create: SpeechServices_default,
|
|
27228
27231
|
createSpeechRecognitionPonyfillFromRecognizer
|
|
27229
27232
|
};
|
|
27230
27233
|
})();
|