speechstate 2.0.0 → 2.0.1

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.
Files changed (20) hide show
  1. package/package.json +1 -1
  2. package/dist/asr.d.ts +0 -117
  3. package/dist/asr.d.ts.map +0 -1
  4. package/dist/asr.js +0 -354
  5. package/dist/getToken.d.ts +0 -2
  6. package/dist/getToken.d.ts.map +0 -1
  7. package/dist/getToken.js +0 -26
  8. package/dist/index.d.ts +0 -3
  9. package/dist/index.d.ts.map +0 -1
  10. package/dist/index.js +0 -5
  11. package/dist/index.js~ +0 -5
  12. package/dist/speechstate.d.ts +0 -48
  13. package/dist/speechstate.d.ts.map +0 -1
  14. package/dist/speechstate.js +0 -292
  15. package/dist/tts.d.ts +0 -120
  16. package/dist/tts.d.ts.map +0 -1
  17. package/dist/tts.js +0 -409
  18. package/dist/types.d.ts +0 -42
  19. package/dist/types.d.ts.map +0 -1
  20. package/dist/types.js +0 -2
package/dist/tts.js DELETED
@@ -1,409 +0,0 @@
1
- "use strict";
2
- Object.defineProperty(exports, "__esModule", { value: true });
3
- exports.ttsMachine = void 0;
4
- const xstate_1 = require("xstate");
5
- const getToken_1 = require("./getToken");
6
- const TextToSpeech_1 = require("web-speech-cognitive-services/lib/SpeechServices/TextToSpeech");
7
- const REGION = "northeurope";
8
- const UTTERANCE_CHUNK_REGEX = /(^.*([!?]+|([.,]+\s)))/;
9
- exports.ttsMachine = (0, xstate_1.setup)({
10
- types: {},
11
- actions: {
12
- ttsStop: ({ context }) => {
13
- context.wsaTTS.cancel();
14
- },
15
- addFiller: (0, xstate_1.assign)(({ context }) => {
16
- const spaceIndex = context.buffer.lastIndexOf(" ");
17
- return {
18
- buffer: context.buffer.substring(0, spaceIndex) +
19
- " um," +
20
- context.buffer.substring(spaceIndex),
21
- };
22
- }),
23
- },
24
- actors: {
25
- getToken: getToken_1.getToken,
26
- createEventsFromStream: (0, xstate_1.fromCallback)(({ sendBack, input }) => {
27
- const eventSource = new EventSource(input.stream);
28
- eventSource.addEventListener("STREAMING_DONE", (_event) => {
29
- console.log("received streaming done - closing event stream");
30
- sendBack({ type: "STREAMING_DONE" });
31
- eventSource.close();
32
- });
33
- eventSource.addEventListener("STREAMING_RESET", (_event) => {
34
- console.log("received streaming reset");
35
- });
36
- eventSource.addEventListener("STREAMING_CHUNK", (event) => {
37
- console.log("received streaming chunk:", event);
38
- sendBack({ type: "STREAMING_CHUNK", value: event.data });
39
- });
40
- }),
41
- ponyfill: (0, xstate_1.fromCallback)(({ sendBack, input }) => {
42
- const ponyfill = (0, TextToSpeech_1.default)({
43
- audioContext: input.audioContext,
44
- credentials: {
45
- region: REGION, // TODO
46
- authorizationToken: input.azureAuthorizationToken,
47
- },
48
- });
49
- const { speechSynthesis, SpeechSynthesisUtterance } = ponyfill;
50
- const tts = speechSynthesis;
51
- const ttsUtterance = SpeechSynthesisUtterance;
52
- tts.addEventListener("voiceschanged", () => {
53
- const voices = tts.getVoices();
54
- if (voices.length > 0) {
55
- console.debug("[TTS] READY");
56
- sendBack({
57
- type: "READY",
58
- value: { wsaTTS: tts, wsaUtt: ttsUtterance },
59
- });
60
- }
61
- else {
62
- console.error("[TTS] No voices available");
63
- sendBack({ type: "ERROR" });
64
- }
65
- });
66
- }),
67
- start: (0, xstate_1.fromCallback)(({ sendBack, input }) => {
68
- if (["", " "].includes(input.utterance)) {
69
- console.debug("[TTS] SPEAK: ", input.utterance);
70
- input.wsaTTS.speak("");
71
- }
72
- else {
73
- console.debug("[TTS] SPEAK: ", input.utterance);
74
- const content = wrapSSML(input.utterance, input.voice, input.ttsLexicon, 1); // todo speech rate;
75
- const utterance = new input.wsaUtt(content);
76
- utterance.addEventListener("start", () => {
77
- sendBack({ type: "TTS_STARTED" });
78
- console.debug("[TTS] TTS_STARTED");
79
- });
80
- utterance.addEventListener("end", () => {
81
- sendBack({ type: "SPEAK_COMPLETE" });
82
- console.debug("[TTS] SPEAK_COMPLETE");
83
- });
84
- input.wsaTTS.speak(utterance);
85
- }
86
- }),
87
- },
88
- guards: {
89
- bufferContainsUtterancePartReadyToBeSpoken: ({ context }) => {
90
- const m = context.buffer.match(UTTERANCE_CHUNK_REGEX);
91
- return !!m;
92
- },
93
- bufferIsNonEmpty: ({ context }) => {
94
- return !!context.buffer;
95
- },
96
- },
97
- delays: {
98
- FILLER_DELAY: ({ context }) => {
99
- return context.agenda.fillerDelay;
100
- },
101
- },
102
- }).createMachine({
103
- id: "tts",
104
- context: ({ input }) => ({
105
- ttsDefaultVoice: input.ttsDefaultVoice || "en-US-DavisNeural",
106
- audioContext: input.audioContext,
107
- azureCredentials: input.azureCredentials,
108
- buffer: "",
109
- }),
110
- initial: "GetToken",
111
- on: {
112
- READY: {
113
- target: ".Ready",
114
- actions: [
115
- (0, xstate_1.assign)({
116
- wsaTTS: ({ event }) => event.value.wsaTTS,
117
- wsaUtt: ({ event }) => event.value.wsaUtt,
118
- }),
119
- (0, xstate_1.sendParent)({ type: "TTS_READY" }),
120
- ],
121
- },
122
- ERROR: { actions: (0, xstate_1.sendParent)({ type: "TTS_ERROR" }) },
123
- },
124
- states: {
125
- Ready: {
126
- initial: "Idle",
127
- states: {
128
- Idle: {
129
- on: {
130
- SPEAK: [
131
- {
132
- target: "BufferedSpeaker",
133
- guard: ({ event }) => !!event.value.stream,
134
- actions: (0, xstate_1.assign)({
135
- agenda: ({ event }) => event.value.fillerDelay
136
- ? event.value
137
- : Object.assign(Object.assign({}, event.value), { fillerDelay: 500 }),
138
- }),
139
- },
140
- {
141
- target: "Speaking",
142
- actions: (0, xstate_1.assign)({ agenda: ({ event }) => event.value }),
143
- },
144
- ],
145
- },
146
- },
147
- BufferedSpeaker: {
148
- type: "parallel",
149
- invoke: {
150
- id: "createEventsFromStream",
151
- src: "createEventsFromStream",
152
- input: ({ context }) => context.agenda,
153
- },
154
- on: {
155
- STOP: {
156
- target: "Idle",
157
- },
158
- SPEAK_COMPLETE: [
159
- {
160
- guard: (0, xstate_1.stateIn)("#BufferingDone"),
161
- target: "Idle",
162
- actions: [(0, xstate_1.sendParent)({ type: "SPEAK_COMPLETE" })],
163
- },
164
- ],
165
- },
166
- states: {
167
- Buffer: {
168
- initial: "BufferIdle",
169
- states: {
170
- BufferIdle: {
171
- id: "BufferIdle",
172
- entry: [
173
- ({ event }) => console.debug("=== Entry BufferIdle", event),
174
- ],
175
- on: {
176
- STREAMING_CHUNK: {
177
- actions: [
178
- ({ event }) => console.debug("=================STREAMING_CHUNK: BufferIdle => Buffering", event),
179
- ],
180
- target: "Buffering",
181
- },
182
- },
183
- },
184
- Buffering: {
185
- id: "Buffering",
186
- on: {
187
- STREAMING_CHUNK: [
188
- {
189
- actions: [
190
- ({ event }) => console.debug("=================STREAMING_CHUNK: Buffering => Buffering", event),
191
- ],
192
- target: "Buffering",
193
- reenter: true,
194
- },
195
- ],
196
- STREAMING_DONE: [
197
- {
198
- target: "BufferingDone",
199
- actions: [
200
- ({ event }) => console.debug("=================STREAMING_DONE: Buffering => BufferingDone", event),
201
- ],
202
- },
203
- ],
204
- },
205
- entry: [
206
- ({ event }) => console.debug("=== Entry Buffering", event),
207
- (0, xstate_1.assign)({
208
- buffer: ({ context, event }) => context.buffer + event.value,
209
- }),
210
- ],
211
- },
212
- BufferingDone: {
213
- entry: [
214
- ({ event }) => console.debug("=== Entry BufferingDone", event),
215
- ],
216
- id: "BufferingDone",
217
- },
218
- },
219
- },
220
- Speaker: {
221
- initial: "SpeakingIdle",
222
- states: {
223
- SpeakingIdle: {
224
- entry: [
225
- ({ event }) => console.debug("=== Entry SpeakingIdle", event),
226
- ],
227
- always: [
228
- {
229
- target: "Speak",
230
- guard: (0, xstate_1.stateIn)("#BufferingDone"),
231
- actions: [
232
- ({ event }) => console.debug("========== in BufferingDone: SpeakingIdle => Speak", event),
233
- (0, xstate_1.assign)({
234
- utteranceFromStream: ({ context }) => context.buffer,
235
- }),
236
- (0, xstate_1.assign)({
237
- buffer: "",
238
- }),
239
- ],
240
- },
241
- {
242
- target: "PrepareSpeech",
243
- guard: "bufferContainsUtterancePartReadyToBeSpoken",
244
- },
245
- ],
246
- after: {
247
- FILLER_DELAY: {
248
- target: "SpeakingIdle",
249
- reenter: true,
250
- actions: "addFiller",
251
- guard: ({ context }) => context.buffer.includes(" "),
252
- },
253
- },
254
- },
255
- PrepareSpeech: {
256
- entry: [
257
- ({ event }) => console.debug("=== Entry PrepareSpeech", event),
258
- (0, xstate_1.assign)(({ context }) => {
259
- let utterancePart;
260
- let restOfBuffer;
261
- const match = context.buffer.match(UTTERANCE_CHUNK_REGEX);
262
- utterancePart = match[0];
263
- restOfBuffer = context.buffer.substring(utterancePart.length);
264
- return {
265
- buffer: restOfBuffer,
266
- utteranceFromStream: utterancePart,
267
- };
268
- }),
269
- ],
270
- always: [
271
- {
272
- target: "Speak",
273
- },
274
- ],
275
- },
276
- Speak: {
277
- entry: [
278
- ({ event }) => console.debug("=== Entry Speak", event),
279
- ],
280
- initial: "Go",
281
- on: {
282
- TTS_STARTED: {
283
- actions: (0, xstate_1.sendParent)({ type: "TTS_STARTED" }),
284
- },
285
- SPEAK_COMPLETE: [
286
- {
287
- guard: (0, xstate_1.stateIn)("#Buffering"),
288
- target: "SpeakingIdle",
289
- },
290
- {
291
- guard: "bufferIsNonEmpty",
292
- target: "SpeakingIdle",
293
- },
294
- ],
295
- },
296
- states: {
297
- Go: {
298
- invoke: {
299
- src: "start",
300
- input: ({ context }) => ({
301
- wsaTTS: context.wsaTTS,
302
- wsaUtt: context.wsaUtt,
303
- ttsLexicon: context.ttsLexicon,
304
- voice: context.agenda.voice || context.ttsDefaultVoice,
305
- utterance: context.utteranceFromStream,
306
- }),
307
- },
308
- on: {
309
- CONTROL: "Paused",
310
- },
311
- exit: "ttsStop",
312
- },
313
- Paused: {
314
- on: {
315
- CONTROL: "Go",
316
- },
317
- },
318
- },
319
- },
320
- },
321
- },
322
- },
323
- },
324
- Speaking: {
325
- initial: "Go",
326
- on: {
327
- STOP: {
328
- target: "Idle",
329
- },
330
- TTS_STARTED: {
331
- actions: (0, xstate_1.sendParent)({ type: "TTS_STARTED" }),
332
- },
333
- SPEAK_COMPLETE: {
334
- target: "Idle",
335
- },
336
- },
337
- exit: (0, xstate_1.sendParent)({ type: "SPEAK_COMPLETE" }),
338
- states: {
339
- Go: {
340
- invoke: {
341
- src: "start",
342
- input: ({ context }) => ({
343
- wsaTTS: context.wsaTTS,
344
- wsaUtt: context.wsaUtt,
345
- ttsLexicon: context.ttsLexicon,
346
- voice: context.agenda.voice || context.ttsDefaultVoice,
347
- // streamURL: context.agenda.streamURL,
348
- utterance: context.agenda.utterance,
349
- }),
350
- },
351
- on: {
352
- CONTROL: "Paused",
353
- },
354
- exit: "ttsStop",
355
- },
356
- Paused: {
357
- on: {
358
- CONTROL: "Go",
359
- },
360
- },
361
- },
362
- },
363
- },
364
- },
365
- Fail: {},
366
- GetToken: {
367
- invoke: {
368
- id: "getAuthorizationToken",
369
- input: ({ context }) => ({
370
- credentials: context.azureCredentials,
371
- }),
372
- src: "getToken",
373
- onDone: {
374
- target: "Ponyfill",
375
- actions: [
376
- (0, xstate_1.assign)(({ event }) => {
377
- return { azureAuthorizationToken: event.output };
378
- }),
379
- ],
380
- },
381
- onError: {
382
- actions: ({ event }) => console.error("[TTS] getToken error", event),
383
- target: "Fail",
384
- },
385
- },
386
- },
387
- Ponyfill: {
388
- invoke: {
389
- id: "ponyTTS",
390
- src: "ponyfill",
391
- input: ({ context }) => ({
392
- audioContext: context.audioContext,
393
- azureAuthorizationToken: context.azureAuthorizationToken,
394
- }),
395
- },
396
- },
397
- },
398
- });
399
- const wrapSSML = (text, voice, lexicon, speechRate) => {
400
- let content = `<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="http://www.w3.org/2001/mstts" xml:lang="en-US"><voice name="${voice}">`;
401
- if (lexicon) {
402
- content = content + `<lexicon uri="${lexicon}"/>`;
403
- }
404
- content =
405
- content +
406
- `<prosody rate="${speechRate}">` +
407
- `${text}</prosody></voice></speak>`;
408
- return content;
409
- };
package/dist/types.d.ts DELETED
@@ -1,42 +0,0 @@
1
- export interface AzureSpeechCredentials {
2
- endpoint: string;
3
- key: string;
4
- }
5
- /**
6
- * @deprecated use `AzureSpeechCredentials` instead
7
- */
8
- export interface AzureCredentials extends AzureSpeechCredentials {
9
- }
10
- export interface AzureLanguageCredentials {
11
- endpoint: string;
12
- key: string;
13
- projectName: string;
14
- deploymentName: string;
15
- }
16
- export interface Settings {
17
- locale?: string;
18
- azureCredentials: string | AzureCredentials | AzureSpeechCredentials;
19
- azureLanguageCredentials?: AzureLanguageCredentials;
20
- asrDefaultCompleteTimeout?: number;
21
- asrDefaultNoInputTimeout?: number;
22
- ttsDefaultVoice?: string;
23
- speechRecognitionEndpointId?: string;
24
- }
25
- export interface Agenda {
26
- utterance: string;
27
- voice?: string;
28
- stream?: string;
29
- fillerDelay?: number;
30
- }
31
- export interface Hypothesis {
32
- utterance: string;
33
- confidence: number;
34
- }
35
- export interface RecogniseParameters {
36
- noInputTimeout?: number;
37
- completeTimeout?: number;
38
- locale?: string;
39
- hints?: string[];
40
- nlu?: boolean | AzureLanguageCredentials;
41
- }
42
- //# sourceMappingURL=types.d.ts.map
package/dist/types.d.ts.map DELETED
@@ -1 +0,0 @@
1
- {"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../src/types.ts"],"names":[],"mappings":"AAAA,MAAM,WAAW,sBAAsB;IACrC,QAAQ,EAAE,MAAM,CAAC;IACjB,GAAG,EAAE,MAAM,CAAC;CACb;AAED;;GAEG;AACH,MAAM,WAAW,gBAAiB,SAAQ,sBAAsB;CAAG;AAEnE,MAAM,WAAW,wBAAwB;IACvC,QAAQ,EAAE,MAAM,CAAC;IACjB,GAAG,EAAE,MAAM,CAAC;IACZ,WAAW,EAAE,MAAM,CAAC;IACpB,cAAc,EAAE,MAAM,CAAC;CACxB;AAED,MAAM,WAAW,QAAQ;IACvB,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,gBAAgB,EAAE,MAAM,GAAG,gBAAgB,GAAG,sBAAsB,CAAC;IACrE,wBAAwB,CAAC,EAAE,wBAAwB,CAAC;IACpD,yBAAyB,CAAC,EAAE,MAAM,CAAC;IACnC,wBAAwB,CAAC,EAAE,MAAM,CAAC;IAClC,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,2BAA2B,CAAC,EAAE,MAAM,CAAC;CACtC;AAED,MAAM,WAAW,MAAM;IACrB,SAAS,EAAE,MAAM,CAAC;IAClB,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,WAAW,CAAC,EAAE,MAAM,CAAC;CACtB;AAED,MAAM,WAAW,UAAU;IACzB,SAAS,EAAE,MAAM,CAAC;IAClB,UAAU,EAAE,MAAM,CAAC;CACpB;AAED,MAAM,WAAW,mBAAmB;IAClC,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,KAAK,CAAC,EAAE,MAAM,EAAE,CAAC;IACjB,GAAG,CAAC,EAAE,OAAO,GAAG,wBAAwB,CAAC;CAC1C"}
package/dist/types.js DELETED
@@ -1,2 +0,0 @@
1
- "use strict";
2
- Object.defineProperty(exports, "__esModule", { value: true });