sarvamai 1.1.6-alpha.1 → 1.1.6
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/README.md +433 -3
- package/dist/cjs/api/resources/pronunciationDictionary/client/Client.d.ts +9 -29
- package/dist/cjs/api/resources/pronunciationDictionary/client/Client.js +6 -26
- package/dist/cjs/api/resources/textToSpeech/client/Client.d.ts +1 -1
- package/dist/cjs/api/resources/textToSpeech/client/Client.js +1 -1
- package/dist/cjs/api/resources/textToSpeech/client/requests/TextToSpeechRequest.d.ts +1 -3
- package/dist/cjs/api/resources/textToSpeech/client/requests/TextToSpeechStreamRequest.d.ts +2 -2
- package/dist/esm/api/resources/pronunciationDictionary/client/Client.d.mts +9 -29
- package/dist/esm/api/resources/pronunciationDictionary/client/Client.mjs +6 -26
- package/dist/esm/api/resources/textToSpeech/client/Client.d.mts +1 -1
- package/dist/esm/api/resources/textToSpeech/client/Client.mjs +1 -1
- package/dist/esm/api/resources/textToSpeech/client/requests/TextToSpeechRequest.d.mts +1 -3
- package/dist/esm/api/resources/textToSpeech/client/requests/TextToSpeechStreamRequest.d.mts +2 -2
- package/package.json +1 -1
- package/reference.md +7 -27
package/README.md
CHANGED
|
@@ -5,6 +5,28 @@
|
|
|
5
5
|
|
|
6
6
|
The Sarvam TypeScript library provides convenient access to the Sarvam APIs from TypeScript.
|
|
7
7
|
|
|
8
|
+
## Table of Contents
|
|
9
|
+
|
|
10
|
+
- [Documentation](#documentation)
|
|
11
|
+
- [Installation](#installation)
|
|
12
|
+
- [Reference](#reference)
|
|
13
|
+
- [Usage](#usage)
|
|
14
|
+
- [Request and Response Types](#request-and-response-types)
|
|
15
|
+
- [Exception Handling](#exception-handling)
|
|
16
|
+
- [File Uploads](#file-uploads)
|
|
17
|
+
- [Binary Response](#binary-response)
|
|
18
|
+
- [Advanced](#advanced)
|
|
19
|
+
- [Subpackage Exports](#subpackage-exports)
|
|
20
|
+
- [Additional Headers](#additional-headers)
|
|
21
|
+
- [Additional Query String Parameters](#additional-query-string-parameters)
|
|
22
|
+
- [Retries](#retries)
|
|
23
|
+
- [Timeouts](#timeouts)
|
|
24
|
+
- [Aborting Requests](#aborting-requests)
|
|
25
|
+
- [Access Raw Response Data](#access-raw-response-data)
|
|
26
|
+
- [Logging](#logging)
|
|
27
|
+
- [Runtime Compatibility](#runtime-compatibility)
|
|
28
|
+
- [Contributing](#contributing)
|
|
29
|
+
|
|
8
30
|
## Documentation
|
|
9
31
|
|
|
10
32
|
API reference documentation is available [here](https://www.sarvam.ai/).
|
|
@@ -34,7 +56,7 @@ await client.text.translate({
|
|
|
34
56
|
});
|
|
35
57
|
```
|
|
36
58
|
|
|
37
|
-
## Request
|
|
59
|
+
## Request and Response Types
|
|
38
60
|
|
|
39
61
|
The SDK exports all request and response types as TypeScript interfaces. Simply import them with the
|
|
40
62
|
following namespace:
|
|
@@ -73,8 +95,8 @@ You can upload files using the client:
|
|
|
73
95
|
|
|
74
96
|
```typescript
|
|
75
97
|
import { createReadStream } from "fs";
|
|
76
|
-
import { SarvamAIClient } from "sarvamai";
|
|
77
98
|
import * as fs from "fs";
|
|
99
|
+
import { SarvamAIClient } from "sarvamai";
|
|
78
100
|
|
|
79
101
|
const client = new SarvamAIClient({ apiSubscriptionKey: "YOUR_API_SUBSCRIPTION_KEY" });
|
|
80
102
|
await client.speechToText.transcribe({
|
|
@@ -111,13 +133,421 @@ The metadata is used to set the `Content-Length`, `Content-Type`, and `Content-D
|
|
|
111
133
|
For example, `fs.ReadStream` has a `path` property which the SDK uses to retrieve the file size from the filesystem without loading it into memory.
|
|
112
134
|
|
|
113
135
|
|
|
136
|
+
## Binary Response
|
|
137
|
+
|
|
138
|
+
You can consume binary data from endpoints using the `BinaryResponse` type which lets you choose how to consume the data:
|
|
139
|
+
|
|
140
|
+
```typescript
|
|
141
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
142
|
+
const stream: ReadableStream<Uint8Array> = response.stream();
|
|
143
|
+
// const arrayBuffer: ArrayBuffer = await response.arrayBuffer();
|
|
144
|
+
// const blob: Blob = response.blob();
|
|
145
|
+
// const bytes: Uint8Array = response.bytes();
|
|
146
|
+
// You can only use the response body once, so you must choose one of the above methods.
|
|
147
|
+
// If you want to check if the response body has been used, you can use the following property.
|
|
148
|
+
const bodyUsed = response.bodyUsed;
|
|
149
|
+
```
|
|
150
|
+
<details>
|
|
151
|
+
<summary>Save binary response to a file</summary>
|
|
152
|
+
|
|
153
|
+
<blockquote>
|
|
154
|
+
<details>
|
|
155
|
+
<summary>Node.js</summary>
|
|
156
|
+
|
|
157
|
+
<blockquote>
|
|
158
|
+
<details>
|
|
159
|
+
<summary>ReadableStream (most-efficient)</summary>
|
|
160
|
+
|
|
161
|
+
```ts
|
|
162
|
+
import { createWriteStream } from 'fs';
|
|
163
|
+
import { Readable } from 'stream';
|
|
164
|
+
import { pipeline } from 'stream/promises';
|
|
165
|
+
|
|
166
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
167
|
+
|
|
168
|
+
const stream = response.stream();
|
|
169
|
+
const nodeStream = Readable.fromWeb(stream);
|
|
170
|
+
const writeStream = createWriteStream('path/to/file');
|
|
171
|
+
|
|
172
|
+
await pipeline(nodeStream, writeStream);
|
|
173
|
+
```
|
|
174
|
+
|
|
175
|
+
</details>
|
|
176
|
+
</blockquote>
|
|
177
|
+
|
|
178
|
+
<blockquote>
|
|
179
|
+
<details>
|
|
180
|
+
<summary>ArrayBuffer</summary>
|
|
181
|
+
|
|
182
|
+
```ts
|
|
183
|
+
import { writeFile } from 'fs/promises';
|
|
184
|
+
|
|
185
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
186
|
+
|
|
187
|
+
const arrayBuffer = await response.arrayBuffer();
|
|
188
|
+
await writeFile('path/to/file', Buffer.from(arrayBuffer));
|
|
189
|
+
```
|
|
190
|
+
|
|
191
|
+
</details>
|
|
192
|
+
</blockquote>
|
|
193
|
+
|
|
194
|
+
<blockquote>
|
|
195
|
+
<details>
|
|
196
|
+
<summary>Blob</summary>
|
|
197
|
+
|
|
198
|
+
```ts
|
|
199
|
+
import { writeFile } from 'fs/promises';
|
|
200
|
+
|
|
201
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
202
|
+
|
|
203
|
+
const blob = await response.blob();
|
|
204
|
+
const arrayBuffer = await blob.arrayBuffer();
|
|
205
|
+
await writeFile('output.bin', Buffer.from(arrayBuffer));
|
|
206
|
+
```
|
|
207
|
+
|
|
208
|
+
</details>
|
|
209
|
+
</blockquote>
|
|
210
|
+
|
|
211
|
+
<blockquote>
|
|
212
|
+
<details>
|
|
213
|
+
<summary>Bytes (UIntArray8)</summary>
|
|
214
|
+
|
|
215
|
+
```ts
|
|
216
|
+
import { writeFile } from 'fs/promises';
|
|
217
|
+
|
|
218
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
219
|
+
|
|
220
|
+
const bytes = await response.bytes();
|
|
221
|
+
await writeFile('path/to/file', bytes);
|
|
222
|
+
```
|
|
223
|
+
|
|
224
|
+
</details>
|
|
225
|
+
</blockquote>
|
|
226
|
+
|
|
227
|
+
</details>
|
|
228
|
+
</blockquote>
|
|
229
|
+
|
|
230
|
+
<blockquote>
|
|
231
|
+
<details>
|
|
232
|
+
<summary>Bun</summary>
|
|
233
|
+
|
|
234
|
+
<blockquote>
|
|
235
|
+
<details>
|
|
236
|
+
<summary>ReadableStream (most-efficient)</summary>
|
|
237
|
+
|
|
238
|
+
```ts
|
|
239
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
240
|
+
|
|
241
|
+
const stream = response.stream();
|
|
242
|
+
await Bun.write('path/to/file', stream);
|
|
243
|
+
```
|
|
244
|
+
|
|
245
|
+
</details>
|
|
246
|
+
</blockquote>
|
|
247
|
+
|
|
248
|
+
<blockquote>
|
|
249
|
+
<details>
|
|
250
|
+
<summary>ArrayBuffer</summary>
|
|
251
|
+
|
|
252
|
+
```ts
|
|
253
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
254
|
+
|
|
255
|
+
const arrayBuffer = await response.arrayBuffer();
|
|
256
|
+
await Bun.write('path/to/file', arrayBuffer);
|
|
257
|
+
```
|
|
258
|
+
|
|
259
|
+
</details>
|
|
260
|
+
</blockquote>
|
|
261
|
+
|
|
262
|
+
<blockquote>
|
|
263
|
+
<details>
|
|
264
|
+
<summary>Blob</summary>
|
|
265
|
+
|
|
266
|
+
```ts
|
|
267
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
268
|
+
|
|
269
|
+
const blob = await response.blob();
|
|
270
|
+
await Bun.write('path/to/file', blob);
|
|
271
|
+
```
|
|
272
|
+
|
|
273
|
+
</details>
|
|
274
|
+
</blockquote>
|
|
275
|
+
|
|
276
|
+
<blockquote>
|
|
277
|
+
<details>
|
|
278
|
+
<summary>Bytes (UIntArray8)</summary>
|
|
279
|
+
|
|
280
|
+
```ts
|
|
281
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
282
|
+
|
|
283
|
+
const bytes = await response.bytes();
|
|
284
|
+
await Bun.write('path/to/file', bytes);
|
|
285
|
+
```
|
|
286
|
+
|
|
287
|
+
</details>
|
|
288
|
+
</blockquote>
|
|
289
|
+
|
|
290
|
+
</details>
|
|
291
|
+
</blockquote>
|
|
292
|
+
|
|
293
|
+
<blockquote>
|
|
294
|
+
<details>
|
|
295
|
+
<summary>Deno</summary>
|
|
296
|
+
|
|
297
|
+
<blockquote>
|
|
298
|
+
<details>
|
|
299
|
+
<summary>ReadableStream (most-efficient)</summary>
|
|
300
|
+
|
|
301
|
+
```ts
|
|
302
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
303
|
+
|
|
304
|
+
const stream = response.stream();
|
|
305
|
+
const file = await Deno.open('path/to/file', { write: true, create: true });
|
|
306
|
+
await stream.pipeTo(file.writable);
|
|
307
|
+
```
|
|
308
|
+
|
|
309
|
+
</details>
|
|
310
|
+
</blockquote>
|
|
311
|
+
|
|
312
|
+
<blockquote>
|
|
313
|
+
<details>
|
|
314
|
+
<summary>ArrayBuffer</summary>
|
|
315
|
+
|
|
316
|
+
```ts
|
|
317
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
318
|
+
|
|
319
|
+
const arrayBuffer = await response.arrayBuffer();
|
|
320
|
+
await Deno.writeFile('path/to/file', new Uint8Array(arrayBuffer));
|
|
321
|
+
```
|
|
322
|
+
|
|
323
|
+
</details>
|
|
324
|
+
</blockquote>
|
|
325
|
+
|
|
326
|
+
<blockquote>
|
|
327
|
+
<details>
|
|
328
|
+
<summary>Blob</summary>
|
|
329
|
+
|
|
330
|
+
```ts
|
|
331
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
332
|
+
|
|
333
|
+
const blob = await response.blob();
|
|
334
|
+
const arrayBuffer = await blob.arrayBuffer();
|
|
335
|
+
await Deno.writeFile('path/to/file', new Uint8Array(arrayBuffer));
|
|
336
|
+
```
|
|
337
|
+
|
|
338
|
+
</details>
|
|
339
|
+
</blockquote>
|
|
340
|
+
|
|
341
|
+
<blockquote>
|
|
342
|
+
<details>
|
|
343
|
+
<summary>Bytes (UIntArray8)</summary>
|
|
344
|
+
|
|
345
|
+
```ts
|
|
346
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
347
|
+
|
|
348
|
+
const bytes = await response.bytes();
|
|
349
|
+
await Deno.writeFile('path/to/file', bytes);
|
|
350
|
+
```
|
|
351
|
+
|
|
352
|
+
</details>
|
|
353
|
+
</blockquote>
|
|
354
|
+
|
|
355
|
+
</details>
|
|
356
|
+
</blockquote>
|
|
357
|
+
|
|
358
|
+
<blockquote>
|
|
359
|
+
<details>
|
|
360
|
+
<summary>Browser</summary>
|
|
361
|
+
|
|
362
|
+
<blockquote>
|
|
363
|
+
<details>
|
|
364
|
+
<summary>Blob (most-efficient)</summary>
|
|
365
|
+
|
|
366
|
+
```ts
|
|
367
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
368
|
+
|
|
369
|
+
const blob = await response.blob();
|
|
370
|
+
const url = URL.createObjectURL(blob);
|
|
371
|
+
|
|
372
|
+
// trigger download
|
|
373
|
+
const a = document.createElement('a');
|
|
374
|
+
a.href = url;
|
|
375
|
+
a.download = 'filename';
|
|
376
|
+
a.click();
|
|
377
|
+
URL.revokeObjectURL(url);
|
|
378
|
+
```
|
|
379
|
+
|
|
380
|
+
</details>
|
|
381
|
+
</blockquote>
|
|
382
|
+
|
|
383
|
+
<blockquote>
|
|
384
|
+
<details>
|
|
385
|
+
<summary>ReadableStream</summary>
|
|
386
|
+
|
|
387
|
+
```ts
|
|
388
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
389
|
+
|
|
390
|
+
const stream = response.stream();
|
|
391
|
+
const reader = stream.getReader();
|
|
392
|
+
const chunks = [];
|
|
393
|
+
|
|
394
|
+
while (true) {
|
|
395
|
+
const { done, value } = await reader.read();
|
|
396
|
+
if (done) break;
|
|
397
|
+
chunks.push(value);
|
|
398
|
+
}
|
|
399
|
+
|
|
400
|
+
const blob = new Blob(chunks);
|
|
401
|
+
const url = URL.createObjectURL(blob);
|
|
402
|
+
|
|
403
|
+
// trigger download
|
|
404
|
+
const a = document.createElement('a');
|
|
405
|
+
a.href = url;
|
|
406
|
+
a.download = 'filename';
|
|
407
|
+
a.click();
|
|
408
|
+
URL.revokeObjectURL(url);
|
|
409
|
+
```
|
|
410
|
+
|
|
411
|
+
</details>
|
|
412
|
+
</blockquote>
|
|
413
|
+
|
|
414
|
+
<blockquote>
|
|
415
|
+
<details>
|
|
416
|
+
<summary>ArrayBuffer</summary>
|
|
417
|
+
|
|
418
|
+
```ts
|
|
419
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
420
|
+
|
|
421
|
+
const arrayBuffer = await response.arrayBuffer();
|
|
422
|
+
const blob = new Blob([arrayBuffer]);
|
|
423
|
+
const url = URL.createObjectURL(blob);
|
|
424
|
+
|
|
425
|
+
// trigger download
|
|
426
|
+
const a = document.createElement('a');
|
|
427
|
+
a.href = url;
|
|
428
|
+
a.download = 'filename';
|
|
429
|
+
a.click();
|
|
430
|
+
URL.revokeObjectURL(url);
|
|
431
|
+
```
|
|
432
|
+
|
|
433
|
+
</details>
|
|
434
|
+
</blockquote>
|
|
435
|
+
|
|
436
|
+
<blockquote>
|
|
437
|
+
<details>
|
|
438
|
+
<summary>Bytes (UIntArray8)</summary>
|
|
439
|
+
|
|
440
|
+
```ts
|
|
441
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
442
|
+
|
|
443
|
+
const bytes = await response.bytes();
|
|
444
|
+
const blob = new Blob([bytes]);
|
|
445
|
+
const url = URL.createObjectURL(blob);
|
|
446
|
+
|
|
447
|
+
// trigger download
|
|
448
|
+
const a = document.createElement('a');
|
|
449
|
+
a.href = url;
|
|
450
|
+
a.download = 'filename';
|
|
451
|
+
a.click();
|
|
452
|
+
URL.revokeObjectURL(url);
|
|
453
|
+
```
|
|
454
|
+
|
|
455
|
+
</details>
|
|
456
|
+
</blockquote>
|
|
457
|
+
|
|
458
|
+
</details>
|
|
459
|
+
</blockquote>
|
|
460
|
+
|
|
461
|
+
</details>
|
|
462
|
+
</blockquote>
|
|
463
|
+
|
|
464
|
+
<details>
|
|
465
|
+
<summary>Convert binary response to text</summary>
|
|
466
|
+
|
|
467
|
+
<blockquote>
|
|
468
|
+
<details>
|
|
469
|
+
<summary>ReadableStream</summary>
|
|
470
|
+
|
|
471
|
+
```ts
|
|
472
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
473
|
+
|
|
474
|
+
const stream = response.stream();
|
|
475
|
+
const text = await new Response(stream).text();
|
|
476
|
+
```
|
|
477
|
+
|
|
478
|
+
</details>
|
|
479
|
+
</blockquote>
|
|
480
|
+
|
|
481
|
+
<blockquote>
|
|
482
|
+
<details>
|
|
483
|
+
<summary>ArrayBuffer</summary>
|
|
484
|
+
|
|
485
|
+
```ts
|
|
486
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
487
|
+
|
|
488
|
+
const arrayBuffer = await response.arrayBuffer();
|
|
489
|
+
const text = new TextDecoder().decode(arrayBuffer);
|
|
490
|
+
```
|
|
491
|
+
|
|
492
|
+
</details>
|
|
493
|
+
</blockquote>
|
|
494
|
+
|
|
495
|
+
<blockquote>
|
|
496
|
+
<details>
|
|
497
|
+
<summary>Blob</summary>
|
|
498
|
+
|
|
499
|
+
```ts
|
|
500
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
501
|
+
|
|
502
|
+
const blob = await response.blob();
|
|
503
|
+
const text = await blob.text();
|
|
504
|
+
```
|
|
505
|
+
|
|
506
|
+
</details>
|
|
507
|
+
</blockquote>
|
|
508
|
+
|
|
509
|
+
<blockquote>
|
|
510
|
+
<details>
|
|
511
|
+
<summary>Bytes (UIntArray8)</summary>
|
|
512
|
+
|
|
513
|
+
```ts
|
|
514
|
+
const response = await client.textToSpeech.convertStream(...);
|
|
515
|
+
|
|
516
|
+
const bytes = await response.bytes();
|
|
517
|
+
const text = new TextDecoder().decode(bytes);
|
|
518
|
+
```
|
|
519
|
+
|
|
520
|
+
</details>
|
|
521
|
+
</blockquote>
|
|
522
|
+
|
|
523
|
+
</details>
|
|
524
|
+
|
|
114
525
|
## Advanced
|
|
115
526
|
|
|
527
|
+
### Subpackage Exports
|
|
528
|
+
|
|
529
|
+
This SDK supports direct imports of subpackage clients, which allows JavaScript bundlers to tree-shake and include only the imported subpackage code. This results in much smaller bundle sizes.
|
|
530
|
+
|
|
531
|
+
```typescript
|
|
532
|
+
import { TextClient } from 'sarvamai/text';
|
|
533
|
+
|
|
534
|
+
const client = new TextClient({...});
|
|
535
|
+
```
|
|
536
|
+
|
|
116
537
|
### Additional Headers
|
|
117
538
|
|
|
118
539
|
If you would like to send additional headers as part of the request, use the `headers` request option.
|
|
119
540
|
|
|
120
541
|
```typescript
|
|
542
|
+
import { SarvamAIClient } from "sarvamai";
|
|
543
|
+
|
|
544
|
+
const client = new SarvamAIClient({
|
|
545
|
+
...
|
|
546
|
+
headers: {
|
|
547
|
+
'X-Custom-Header': 'custom value'
|
|
548
|
+
}
|
|
549
|
+
});
|
|
550
|
+
|
|
121
551
|
const response = await client.text.translate(..., {
|
|
122
552
|
headers: {
|
|
123
553
|
'X-Custom-Header': 'custom value'
|
|
@@ -290,4 +720,4 @@ otherwise they would be overwritten upon the next generated release. Feel free t
|
|
|
290
720
|
a proof of concept, but know that we will not be able to merge it as-is. We suggest opening
|
|
291
721
|
an issue first to discuss with us!
|
|
292
722
|
|
|
293
|
-
On the other hand, contributions to the README are always very welcome!
|
|
723
|
+
On the other hand, contributions to the README are always very welcome!
|
|
@@ -27,31 +27,13 @@ export declare class PronunciationDictionaryClient {
|
|
|
27
27
|
list(requestOptions?: PronunciationDictionaryClient.RequestOptions): core.HttpResponsePromise<SarvamAI.PronunciationDictionaryGetResponse>;
|
|
28
28
|
private __list;
|
|
29
29
|
/**
|
|
30
|
-
* Upload a
|
|
31
|
-
*
|
|
32
|
-
* The
|
|
33
|
-
*
|
|
34
|
-
*
|
|
35
|
-
*
|
|
36
|
-
*
|
|
37
|
-
* - Max 1 MB file size
|
|
38
|
-
*
|
|
39
|
-
* **JSON file format:**
|
|
40
|
-
* ```json
|
|
41
|
-
* {
|
|
42
|
-
* "pronunciations": {
|
|
43
|
-
* "hi-IN": {
|
|
44
|
-
* "B2B": "B to B",
|
|
45
|
-
* "my name": "mera naam"
|
|
46
|
-
* },
|
|
47
|
-
* "en-IN": {
|
|
48
|
-
* "teting": "testing"
|
|
49
|
-
* }
|
|
50
|
-
* }
|
|
51
|
-
* }
|
|
52
|
-
* ```
|
|
53
|
-
*
|
|
54
|
-
* Save this as a `.json` file and upload it via the `file` field. The returned `dictionary_id` can then be passed as `dict_id` in text-to-speech requests (REST, streaming, and WebSocket).
|
|
30
|
+
* Upload a `.json` file to create a new pronunciation dictionary. Only supported by **bulbul:v3**.
|
|
31
|
+
*
|
|
32
|
+
* The file should contain a JSON object with a `pronunciations` key mapping language codes to word-pronunciation pairs. See the [Pronunciation Dictionary guide](/api-reference-docs/api-guides-tutorials/text-to-speech/pronunciation-dictionary) for format details and examples.
|
|
33
|
+
*
|
|
34
|
+
* The returned `dictionary_id` can be passed as `dict_id` in text-to-speech requests (REST, HTTP Stream, and WebSocket).
|
|
35
|
+
*
|
|
36
|
+
* **Limits:** Max 10 dictionaries per user, 100 words per dictionary, 1 MB file size.
|
|
55
37
|
*
|
|
56
38
|
* @param {SarvamAI.CreatePronunciationDictionaryRequest} request
|
|
57
39
|
* @param {PronunciationDictionaryClient.RequestOptions} requestOptions - Request-specific configuration.
|
|
@@ -72,11 +54,9 @@ export declare class PronunciationDictionaryClient {
|
|
|
72
54
|
create(request: SarvamAI.CreatePronunciationDictionaryRequest, requestOptions?: PronunciationDictionaryClient.RequestOptions): core.HttpResponsePromise<SarvamAI.PronunciationDictionaryResponse>;
|
|
73
55
|
private __create;
|
|
74
56
|
/**
|
|
75
|
-
*
|
|
57
|
+
* Update an existing pronunciation dictionary by uploading a JSON file. You can add new words, change existing pronunciations, or both — entries not included in the uploaded file remain unchanged.
|
|
76
58
|
*
|
|
77
|
-
* **Limits:**
|
|
78
|
-
* - Max 100 words per dictionary
|
|
79
|
-
* - Max 1 MB file size
|
|
59
|
+
* **Limits:** Max 100 words per dictionary, 1 MB file size.
|
|
80
60
|
*
|
|
81
61
|
* The response includes the `dictionary_id` and the updated pronunciation mappings for verification.
|
|
82
62
|
*
|
|
@@ -118,31 +118,13 @@ class PronunciationDictionaryClient {
|
|
|
118
118
|
});
|
|
119
119
|
}
|
|
120
120
|
/**
|
|
121
|
-
* Upload a
|
|
121
|
+
* Upload a `.json` file to create a new pronunciation dictionary. Only supported by **bulbul:v3**.
|
|
122
122
|
*
|
|
123
|
-
* The
|
|
123
|
+
* The file should contain a JSON object with a `pronunciations` key mapping language codes to word-pronunciation pairs. See the [Pronunciation Dictionary guide](/api-reference-docs/api-guides-tutorials/text-to-speech/pronunciation-dictionary) for format details and examples.
|
|
124
124
|
*
|
|
125
|
-
*
|
|
126
|
-
* - Max 10 dictionaries per user
|
|
127
|
-
* - Max 100 words per dictionary
|
|
128
|
-
* - Max 1 MB file size
|
|
125
|
+
* The returned `dictionary_id` can be passed as `dict_id` in text-to-speech requests (REST, HTTP Stream, and WebSocket).
|
|
129
126
|
*
|
|
130
|
-
* **
|
|
131
|
-
* ```json
|
|
132
|
-
* {
|
|
133
|
-
* "pronunciations": {
|
|
134
|
-
* "hi-IN": {
|
|
135
|
-
* "B2B": "B to B",
|
|
136
|
-
* "my name": "mera naam"
|
|
137
|
-
* },
|
|
138
|
-
* "en-IN": {
|
|
139
|
-
* "teting": "testing"
|
|
140
|
-
* }
|
|
141
|
-
* }
|
|
142
|
-
* }
|
|
143
|
-
* ```
|
|
144
|
-
*
|
|
145
|
-
* Save this as a `.json` file and upload it via the `file` field. The returned `dictionary_id` can then be passed as `dict_id` in text-to-speech requests (REST, streaming, and WebSocket).
|
|
127
|
+
* **Limits:** Max 10 dictionaries per user, 100 words per dictionary, 1 MB file size.
|
|
146
128
|
*
|
|
147
129
|
* @param {SarvamAI.CreatePronunciationDictionaryRequest} request
|
|
148
130
|
* @param {PronunciationDictionaryClient.RequestOptions} requestOptions - Request-specific configuration.
|
|
@@ -217,11 +199,9 @@ class PronunciationDictionaryClient {
|
|
|
217
199
|
});
|
|
218
200
|
}
|
|
219
201
|
/**
|
|
220
|
-
*
|
|
202
|
+
* Update an existing pronunciation dictionary by uploading a JSON file. You can add new words, change existing pronunciations, or both — entries not included in the uploaded file remain unchanged.
|
|
221
203
|
*
|
|
222
|
-
* **Limits:**
|
|
223
|
-
* - Max 100 words per dictionary
|
|
224
|
-
* - Max 1 MB file size
|
|
204
|
+
* **Limits:** Max 100 words per dictionary, 1 MB file size.
|
|
225
205
|
*
|
|
226
206
|
* The response includes the `dictionary_id` and the updated pronunciation mappings for verification.
|
|
227
207
|
*
|
|
@@ -46,7 +46,7 @@ export declare class TextToSpeechClient {
|
|
|
46
46
|
*
|
|
47
47
|
* This endpoint supports streaming audio using the specified output codec (e.g., `audio/mpeg` for MP3). The response is returned as a binary audio stream, which can be played or saved directly by the client.
|
|
48
48
|
*
|
|
49
|
-
* Supports the `dict_id` parameter to apply a pronunciation dictionary during synthesis.
|
|
49
|
+
* Supports the `dict_id` parameter to apply a [pronunciation dictionary](/api-reference-docs/text-to-speech/pronunciation-dictionary/create) during synthesis.
|
|
50
50
|
* @throws {@link SarvamAI.BadRequestError}
|
|
51
51
|
* @throws {@link SarvamAI.ForbiddenError}
|
|
52
52
|
* @throws {@link SarvamAI.UnprocessableEntityError}
|
|
@@ -137,7 +137,7 @@ class TextToSpeechClient {
|
|
|
137
137
|
*
|
|
138
138
|
* This endpoint supports streaming audio using the specified output codec (e.g., `audio/mpeg` for MP3). The response is returned as a binary audio stream, which can be played or saved directly by the client.
|
|
139
139
|
*
|
|
140
|
-
* Supports the `dict_id` parameter to apply a pronunciation dictionary during synthesis.
|
|
140
|
+
* Supports the `dict_id` parameter to apply a [pronunciation dictionary](/api-reference-docs/text-to-speech/pronunciation-dictionary/create) during synthesis.
|
|
141
141
|
* @throws {@link SarvamAI.BadRequestError}
|
|
142
142
|
* @throws {@link SarvamAI.ForbiddenError}
|
|
143
143
|
* @throws {@link SarvamAI.UnprocessableEntityError}
|
|
@@ -96,9 +96,7 @@ export interface TextToSpeechRequest {
|
|
|
96
96
|
/**
|
|
97
97
|
* The ID of a pronunciation dictionary to apply during synthesis. When provided, matching words in the input text will be replaced with their custom pronunciations before generating speech.
|
|
98
98
|
*
|
|
99
|
-
* Create and manage dictionaries via the
|
|
100
|
-
*
|
|
101
|
-
* **Note:** Only supported by **bulbul:v3**.
|
|
99
|
+
* Create and manage dictionaries via the [Pronunciation Dictionary API](/api-reference-docs/text-to-speech/pronunciation-dictionary/create). Only supported by **bulbul:v3**.
|
|
102
100
|
*/
|
|
103
101
|
dict_id?: string;
|
|
104
102
|
/**
|
|
@@ -67,9 +67,9 @@ export interface TextToSpeechStreamRequest {
|
|
|
67
67
|
/** Enable caching for the request. Default is false. Currently in beta. */
|
|
68
68
|
enable_cached_responses?: boolean;
|
|
69
69
|
/**
|
|
70
|
-
* The ID of a pronunciation dictionary to apply during synthesis.
|
|
70
|
+
* The ID of a pronunciation dictionary to apply during synthesis. When provided, matching words in the input text will be replaced with their custom pronunciations before generating speech.
|
|
71
71
|
*
|
|
72
|
-
*
|
|
72
|
+
* Create and manage dictionaries via the [Pronunciation Dictionary API](/api-reference-docs/text-to-speech/pronunciation-dictionary/create). Only supported by **bulbul:v3**.
|
|
73
73
|
*/
|
|
74
74
|
dict_id?: string;
|
|
75
75
|
/** Specifies the codec for the streamed output audio (e.g., 'mp3'). */
|
|
@@ -27,31 +27,13 @@ export declare class PronunciationDictionaryClient {
|
|
|
27
27
|
list(requestOptions?: PronunciationDictionaryClient.RequestOptions): core.HttpResponsePromise<SarvamAI.PronunciationDictionaryGetResponse>;
|
|
28
28
|
private __list;
|
|
29
29
|
/**
|
|
30
|
-
* Upload a
|
|
31
|
-
*
|
|
32
|
-
* The
|
|
33
|
-
*
|
|
34
|
-
*
|
|
35
|
-
*
|
|
36
|
-
*
|
|
37
|
-
* - Max 1 MB file size
|
|
38
|
-
*
|
|
39
|
-
* **JSON file format:**
|
|
40
|
-
* ```json
|
|
41
|
-
* {
|
|
42
|
-
* "pronunciations": {
|
|
43
|
-
* "hi-IN": {
|
|
44
|
-
* "B2B": "B to B",
|
|
45
|
-
* "my name": "mera naam"
|
|
46
|
-
* },
|
|
47
|
-
* "en-IN": {
|
|
48
|
-
* "teting": "testing"
|
|
49
|
-
* }
|
|
50
|
-
* }
|
|
51
|
-
* }
|
|
52
|
-
* ```
|
|
53
|
-
*
|
|
54
|
-
* Save this as a `.json` file and upload it via the `file` field. The returned `dictionary_id` can then be passed as `dict_id` in text-to-speech requests (REST, streaming, and WebSocket).
|
|
30
|
+
* Upload a `.json` file to create a new pronunciation dictionary. Only supported by **bulbul:v3**.
|
|
31
|
+
*
|
|
32
|
+
* The file should contain a JSON object with a `pronunciations` key mapping language codes to word-pronunciation pairs. See the [Pronunciation Dictionary guide](/api-reference-docs/api-guides-tutorials/text-to-speech/pronunciation-dictionary) for format details and examples.
|
|
33
|
+
*
|
|
34
|
+
* The returned `dictionary_id` can be passed as `dict_id` in text-to-speech requests (REST, HTTP Stream, and WebSocket).
|
|
35
|
+
*
|
|
36
|
+
* **Limits:** Max 10 dictionaries per user, 100 words per dictionary, 1 MB file size.
|
|
55
37
|
*
|
|
56
38
|
* @param {SarvamAI.CreatePronunciationDictionaryRequest} request
|
|
57
39
|
* @param {PronunciationDictionaryClient.RequestOptions} requestOptions - Request-specific configuration.
|
|
@@ -72,11 +54,9 @@ export declare class PronunciationDictionaryClient {
|
|
|
72
54
|
create(request: SarvamAI.CreatePronunciationDictionaryRequest, requestOptions?: PronunciationDictionaryClient.RequestOptions): core.HttpResponsePromise<SarvamAI.PronunciationDictionaryResponse>;
|
|
73
55
|
private __create;
|
|
74
56
|
/**
|
|
75
|
-
*
|
|
57
|
+
* Update an existing pronunciation dictionary by uploading a JSON file. You can add new words, change existing pronunciations, or both — entries not included in the uploaded file remain unchanged.
|
|
76
58
|
*
|
|
77
|
-
* **Limits:**
|
|
78
|
-
* - Max 100 words per dictionary
|
|
79
|
-
* - Max 1 MB file size
|
|
59
|
+
* **Limits:** Max 100 words per dictionary, 1 MB file size.
|
|
80
60
|
*
|
|
81
61
|
* The response includes the `dictionary_id` and the updated pronunciation mappings for verification.
|
|
82
62
|
*
|
|
@@ -82,31 +82,13 @@ export class PronunciationDictionaryClient {
|
|
|
82
82
|
});
|
|
83
83
|
}
|
|
84
84
|
/**
|
|
85
|
-
* Upload a
|
|
85
|
+
* Upload a `.json` file to create a new pronunciation dictionary. Only supported by **bulbul:v3**.
|
|
86
86
|
*
|
|
87
|
-
* The
|
|
87
|
+
* The file should contain a JSON object with a `pronunciations` key mapping language codes to word-pronunciation pairs. See the [Pronunciation Dictionary guide](/api-reference-docs/api-guides-tutorials/text-to-speech/pronunciation-dictionary) for format details and examples.
|
|
88
88
|
*
|
|
89
|
-
*
|
|
90
|
-
* - Max 10 dictionaries per user
|
|
91
|
-
* - Max 100 words per dictionary
|
|
92
|
-
* - Max 1 MB file size
|
|
89
|
+
* The returned `dictionary_id` can be passed as `dict_id` in text-to-speech requests (REST, HTTP Stream, and WebSocket).
|
|
93
90
|
*
|
|
94
|
-
* **
|
|
95
|
-
* ```json
|
|
96
|
-
* {
|
|
97
|
-
* "pronunciations": {
|
|
98
|
-
* "hi-IN": {
|
|
99
|
-
* "B2B": "B to B",
|
|
100
|
-
* "my name": "mera naam"
|
|
101
|
-
* },
|
|
102
|
-
* "en-IN": {
|
|
103
|
-
* "teting": "testing"
|
|
104
|
-
* }
|
|
105
|
-
* }
|
|
106
|
-
* }
|
|
107
|
-
* ```
|
|
108
|
-
*
|
|
109
|
-
* Save this as a `.json` file and upload it via the `file` field. The returned `dictionary_id` can then be passed as `dict_id` in text-to-speech requests (REST, streaming, and WebSocket).
|
|
91
|
+
* **Limits:** Max 10 dictionaries per user, 100 words per dictionary, 1 MB file size.
|
|
110
92
|
*
|
|
111
93
|
* @param {SarvamAI.CreatePronunciationDictionaryRequest} request
|
|
112
94
|
* @param {PronunciationDictionaryClient.RequestOptions} requestOptions - Request-specific configuration.
|
|
@@ -181,11 +163,9 @@ export class PronunciationDictionaryClient {
|
|
|
181
163
|
});
|
|
182
164
|
}
|
|
183
165
|
/**
|
|
184
|
-
*
|
|
166
|
+
* Update an existing pronunciation dictionary by uploading a JSON file. You can add new words, change existing pronunciations, or both — entries not included in the uploaded file remain unchanged.
|
|
185
167
|
*
|
|
186
|
-
* **Limits:**
|
|
187
|
-
* - Max 100 words per dictionary
|
|
188
|
-
* - Max 1 MB file size
|
|
168
|
+
* **Limits:** Max 100 words per dictionary, 1 MB file size.
|
|
189
169
|
*
|
|
190
170
|
* The response includes the `dictionary_id` and the updated pronunciation mappings for verification.
|
|
191
171
|
*
|
|
@@ -46,7 +46,7 @@ export declare class TextToSpeechClient {
|
|
|
46
46
|
*
|
|
47
47
|
* This endpoint supports streaming audio using the specified output codec (e.g., `audio/mpeg` for MP3). The response is returned as a binary audio stream, which can be played or saved directly by the client.
|
|
48
48
|
*
|
|
49
|
-
* Supports the `dict_id` parameter to apply a pronunciation dictionary during synthesis.
|
|
49
|
+
* Supports the `dict_id` parameter to apply a [pronunciation dictionary](/api-reference-docs/text-to-speech/pronunciation-dictionary/create) during synthesis.
|
|
50
50
|
* @throws {@link SarvamAI.BadRequestError}
|
|
51
51
|
* @throws {@link SarvamAI.ForbiddenError}
|
|
52
52
|
* @throws {@link SarvamAI.UnprocessableEntityError}
|
|
@@ -101,7 +101,7 @@ export class TextToSpeechClient {
|
|
|
101
101
|
*
|
|
102
102
|
* This endpoint supports streaming audio using the specified output codec (e.g., `audio/mpeg` for MP3). The response is returned as a binary audio stream, which can be played or saved directly by the client.
|
|
103
103
|
*
|
|
104
|
-
* Supports the `dict_id` parameter to apply a pronunciation dictionary during synthesis.
|
|
104
|
+
* Supports the `dict_id` parameter to apply a [pronunciation dictionary](/api-reference-docs/text-to-speech/pronunciation-dictionary/create) during synthesis.
|
|
105
105
|
* @throws {@link SarvamAI.BadRequestError}
|
|
106
106
|
* @throws {@link SarvamAI.ForbiddenError}
|
|
107
107
|
* @throws {@link SarvamAI.UnprocessableEntityError}
|
|
@@ -96,9 +96,7 @@ export interface TextToSpeechRequest {
|
|
|
96
96
|
/**
|
|
97
97
|
* The ID of a pronunciation dictionary to apply during synthesis. When provided, matching words in the input text will be replaced with their custom pronunciations before generating speech.
|
|
98
98
|
*
|
|
99
|
-
* Create and manage dictionaries via the
|
|
100
|
-
*
|
|
101
|
-
* **Note:** Only supported by **bulbul:v3**.
|
|
99
|
+
* Create and manage dictionaries via the [Pronunciation Dictionary API](/api-reference-docs/text-to-speech/pronunciation-dictionary/create). Only supported by **bulbul:v3**.
|
|
102
100
|
*/
|
|
103
101
|
dict_id?: string;
|
|
104
102
|
/**
|
|
@@ -67,9 +67,9 @@ export interface TextToSpeechStreamRequest {
|
|
|
67
67
|
/** Enable caching for the request. Default is false. Currently in beta. */
|
|
68
68
|
enable_cached_responses?: boolean;
|
|
69
69
|
/**
|
|
70
|
-
* The ID of a pronunciation dictionary to apply during synthesis.
|
|
70
|
+
* The ID of a pronunciation dictionary to apply during synthesis. When provided, matching words in the input text will be replaced with their custom pronunciations before generating speech.
|
|
71
71
|
*
|
|
72
|
-
*
|
|
72
|
+
* Create and manage dictionaries via the [Pronunciation Dictionary API](/api-reference-docs/text-to-speech/pronunciation-dictionary/create). Only supported by **bulbul:v3**.
|
|
73
73
|
*/
|
|
74
74
|
dict_id?: string;
|
|
75
75
|
/** Specifies the codec for the streamed output audio (e.g., 'mp3'). */
|
package/package.json
CHANGED
package/reference.md
CHANGED
|
@@ -500,7 +500,7 @@ Converts the input text into a streamed spoken audio response.
|
|
|
500
500
|
|
|
501
501
|
This endpoint supports streaming audio using the specified output codec (e.g., `audio/mpeg` for MP3). The response is returned as a binary audio stream, which can be played or saved directly by the client.
|
|
502
502
|
|
|
503
|
-
Supports the `dict_id` parameter to apply a pronunciation dictionary during synthesis.
|
|
503
|
+
Supports the `dict_id` parameter to apply a [pronunciation dictionary](/api-reference-docs/text-to-speech/pronunciation-dictionary/create) during synthesis.
|
|
504
504
|
</dd>
|
|
505
505
|
</dl>
|
|
506
506
|
</dd>
|
|
@@ -621,31 +621,13 @@ await client.pronunciationDictionary.list();
|
|
|
621
621
|
<dl>
|
|
622
622
|
<dd>
|
|
623
623
|
|
|
624
|
-
Upload a
|
|
624
|
+
Upload a `.json` file to create a new pronunciation dictionary. Only supported by **bulbul:v3**.
|
|
625
625
|
|
|
626
|
-
The
|
|
626
|
+
The file should contain a JSON object with a `pronunciations` key mapping language codes to word-pronunciation pairs. See the [Pronunciation Dictionary guide](/api-reference-docs/api-guides-tutorials/text-to-speech/pronunciation-dictionary) for format details and examples.
|
|
627
627
|
|
|
628
|
-
|
|
629
|
-
- Max 10 dictionaries per user
|
|
630
|
-
- Max 100 words per dictionary
|
|
631
|
-
- Max 1 MB file size
|
|
628
|
+
The returned `dictionary_id` can be passed as `dict_id` in text-to-speech requests (REST, HTTP Stream, and WebSocket).
|
|
632
629
|
|
|
633
|
-
**
|
|
634
|
-
```json
|
|
635
|
-
{
|
|
636
|
-
"pronunciations": {
|
|
637
|
-
"hi-IN": {
|
|
638
|
-
"B2B": "B to B",
|
|
639
|
-
"my name": "mera naam"
|
|
640
|
-
},
|
|
641
|
-
"en-IN": {
|
|
642
|
-
"teting": "testing"
|
|
643
|
-
}
|
|
644
|
-
}
|
|
645
|
-
}
|
|
646
|
-
```
|
|
647
|
-
|
|
648
|
-
Save this as a `.json` file and upload it via the `file` field. The returned `dictionary_id` can then be passed as `dict_id` in text-to-speech requests (REST, streaming, and WebSocket).
|
|
630
|
+
**Limits:** Max 10 dictionaries per user, 100 words per dictionary, 1 MB file size.
|
|
649
631
|
</dd>
|
|
650
632
|
</dl>
|
|
651
633
|
</dd>
|
|
@@ -710,11 +692,9 @@ await client.pronunciationDictionary.create({
|
|
|
710
692
|
<dl>
|
|
711
693
|
<dd>
|
|
712
694
|
|
|
713
|
-
|
|
695
|
+
Update an existing pronunciation dictionary by uploading a JSON file. You can add new words, change existing pronunciations, or both — entries not included in the uploaded file remain unchanged.
|
|
714
696
|
|
|
715
|
-
**Limits:**
|
|
716
|
-
- Max 100 words per dictionary
|
|
717
|
-
- Max 1 MB file size
|
|
697
|
+
**Limits:** Max 100 words per dictionary, 1 MB file size.
|
|
718
698
|
|
|
719
699
|
The response includes the `dictionary_id` and the updated pronunciation mappings for verification.
|
|
720
700
|
</dd>
|