murf 1.2.3__py3-none-any.whl → 2.0.1__py3-none-any.whl

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.

Potentially problematic release.

This version of murf might be problematic. Click here for more details.

Files changed (62) hide show
  1. murf/__init__.py +37 -1
  2. murf/auth/client.py +11 -9
  3. murf/base_client.py +3 -20
  4. murf/client.py +0 -8
  5. murf/core/__init__.py +4 -0
  6. murf/core/client_wrapper.py +18 -17
  7. murf/core/http_client.py +6 -6
  8. murf/core/pydantic_utilities.py +2 -2
  9. murf/core/unchecked_base_model.py +305 -0
  10. murf/dubbing/jobs/client.py +37 -31
  11. murf/dubbing/languages/client.py +25 -21
  12. murf/dubbing/projects/client.py +37 -31
  13. murf/dubbing_client.py +0 -8
  14. murf/environment.py +10 -3
  15. murf/stream_input/__init__.py +5 -0
  16. murf/stream_input/types/__init__.py +6 -0
  17. murf/stream_input/types/receive_message.py +7 -0
  18. murf/stream_input/types/send_message.py +9 -0
  19. murf/text/client.py +15 -13
  20. murf/text_to_speech/client.py +79 -37
  21. murf/types/__init__.py +44 -0
  22. murf/types/api_job_response.py +2 -2
  23. murf/types/api_project_response.py +2 -2
  24. murf/types/api_voice.py +2 -2
  25. murf/types/audio_output.py +27 -0
  26. murf/types/auth_token_response.py +2 -2
  27. murf/types/character_count.py +2 -2
  28. murf/types/clear_context.py +20 -0
  29. murf/types/dub_api_detail_response.py +2 -2
  30. murf/types/dub_job_status_response.py +2 -2
  31. murf/types/final_output.py +27 -0
  32. murf/types/form_data_content_disposition.py +2 -2
  33. murf/types/generate_speech_response.py +2 -2
  34. murf/types/group_api_project_response.py +2 -2
  35. murf/types/locale_response.py +2 -2
  36. murf/types/metadata.py +2 -2
  37. murf/types/murf_api_translation_response.py +2 -2
  38. murf/types/pronunciation_detail.py +2 -2
  39. murf/types/send_text.py +35 -0
  40. murf/types/send_text_voice_config.py +55 -0
  41. murf/types/send_text_voice_config_pronunciation_dictionary_value.py +30 -0
  42. murf/types/send_text_voice_config_pronunciation_dictionary_value_type.py +5 -0
  43. murf/types/set_advanced_settings.py +20 -0
  44. murf/types/set_voice_configuration_or_initialize_context.py +26 -0
  45. murf/types/set_voice_configuration_or_initialize_context_voice_config.py +57 -0
  46. murf/types/set_voice_configuration_or_initialize_context_voice_config_pronunciation_dictionary_value.py +30 -0
  47. murf/types/set_voice_configuration_or_initialize_context_voice_config_pronunciation_dictionary_value_type.py +7 -0
  48. murf/types/source_locale_response.py +2 -2
  49. murf/types/speech_to_speech_response.py +2 -2
  50. murf/types/style_details.py +2 -2
  51. murf/types/translation.py +2 -2
  52. murf/types/tts_request_both_payload.py +29 -0
  53. murf/types/tts_request_both_payload_voice_config.py +44 -0
  54. murf/types/tts_request_both_payload_voice_config_pronunciation_dictionary.py +22 -0
  55. murf/types/tts_request_both_payload_voice_config_pronunciation_dictionary_guess.py +20 -0
  56. murf/types/word_duration_response.py +2 -2
  57. murf/voice_changer/client.py +29 -23
  58. {murf-1.2.3.dist-info → murf-2.0.1.dist-info}/METADATA +1 -1
  59. murf-2.0.1.dist-info/RECORD +101 -0
  60. murf-1.2.3.dist-info/RECORD +0 -80
  61. {murf-1.2.3.dist-info → murf-2.0.1.dist-info}/LICENSE +0 -0
  62. {murf-1.2.3.dist-info → murf-2.0.1.dist-info}/WHEEL +0 -0
murf/text/client.py CHANGED
@@ -4,7 +4,7 @@ import typing
4
4
  from ..core.client_wrapper import SyncClientWrapper
5
5
  from ..core.request_options import RequestOptions
6
6
  from ..types.murf_api_translation_response import MurfApiTranslationResponse
7
- from ..core.pydantic_utilities import parse_obj_as
7
+ from ..core.unchecked_base_model import construct_type
8
8
  from ..errors.bad_request_error import BadRequestError
9
9
  from ..errors.payment_required_error import PaymentRequiredError
10
10
  from ..errors.forbidden_error import ForbiddenError
@@ -60,6 +60,7 @@ class TextClient:
60
60
  """
61
61
  _response = self._client_wrapper.httpx_client.request(
62
62
  "v1/text/translate",
63
+ base_url=self._client_wrapper.get_environment().base,
63
64
  method="POST",
64
65
  json={
65
66
  "targetLanguage": target_language,
@@ -75,7 +76,7 @@ class TextClient:
75
76
  if 200 <= _response.status_code < 300:
76
77
  return typing.cast(
77
78
  MurfApiTranslationResponse,
78
- parse_obj_as(
79
+ construct_type(
79
80
  type_=MurfApiTranslationResponse, # type: ignore
80
81
  object_=_response.json(),
81
82
  ),
@@ -84,7 +85,7 @@ class TextClient:
84
85
  raise BadRequestError(
85
86
  typing.cast(
86
87
  typing.Optional[typing.Any],
87
- parse_obj_as(
88
+ construct_type(
88
89
  type_=typing.Optional[typing.Any], # type: ignore
89
90
  object_=_response.json(),
90
91
  ),
@@ -94,7 +95,7 @@ class TextClient:
94
95
  raise PaymentRequiredError(
95
96
  typing.cast(
96
97
  typing.Optional[typing.Any],
97
- parse_obj_as(
98
+ construct_type(
98
99
  type_=typing.Optional[typing.Any], # type: ignore
99
100
  object_=_response.json(),
100
101
  ),
@@ -104,7 +105,7 @@ class TextClient:
104
105
  raise ForbiddenError(
105
106
  typing.cast(
106
107
  typing.Optional[typing.Any],
107
- parse_obj_as(
108
+ construct_type(
108
109
  type_=typing.Optional[typing.Any], # type: ignore
109
110
  object_=_response.json(),
110
111
  ),
@@ -114,7 +115,7 @@ class TextClient:
114
115
  raise InternalServerError(
115
116
  typing.cast(
116
117
  typing.Optional[typing.Any],
117
- parse_obj_as(
118
+ construct_type(
118
119
  type_=typing.Optional[typing.Any], # type: ignore
119
120
  object_=_response.json(),
120
121
  ),
@@ -124,7 +125,7 @@ class TextClient:
124
125
  raise ServiceUnavailableError(
125
126
  typing.cast(
126
127
  typing.Optional[typing.Any],
127
- parse_obj_as(
128
+ construct_type(
128
129
  type_=typing.Optional[typing.Any], # type: ignore
129
130
  object_=_response.json(),
130
131
  ),
@@ -186,6 +187,7 @@ class AsyncTextClient:
186
187
  """
187
188
  _response = await self._client_wrapper.httpx_client.request(
188
189
  "v1/text/translate",
190
+ base_url=self._client_wrapper.get_environment().base,
189
191
  method="POST",
190
192
  json={
191
193
  "targetLanguage": target_language,
@@ -201,7 +203,7 @@ class AsyncTextClient:
201
203
  if 200 <= _response.status_code < 300:
202
204
  return typing.cast(
203
205
  MurfApiTranslationResponse,
204
- parse_obj_as(
206
+ construct_type(
205
207
  type_=MurfApiTranslationResponse, # type: ignore
206
208
  object_=_response.json(),
207
209
  ),
@@ -210,7 +212,7 @@ class AsyncTextClient:
210
212
  raise BadRequestError(
211
213
  typing.cast(
212
214
  typing.Optional[typing.Any],
213
- parse_obj_as(
215
+ construct_type(
214
216
  type_=typing.Optional[typing.Any], # type: ignore
215
217
  object_=_response.json(),
216
218
  ),
@@ -220,7 +222,7 @@ class AsyncTextClient:
220
222
  raise PaymentRequiredError(
221
223
  typing.cast(
222
224
  typing.Optional[typing.Any],
223
- parse_obj_as(
225
+ construct_type(
224
226
  type_=typing.Optional[typing.Any], # type: ignore
225
227
  object_=_response.json(),
226
228
  ),
@@ -230,7 +232,7 @@ class AsyncTextClient:
230
232
  raise ForbiddenError(
231
233
  typing.cast(
232
234
  typing.Optional[typing.Any],
233
- parse_obj_as(
235
+ construct_type(
234
236
  type_=typing.Optional[typing.Any], # type: ignore
235
237
  object_=_response.json(),
236
238
  ),
@@ -240,7 +242,7 @@ class AsyncTextClient:
240
242
  raise InternalServerError(
241
243
  typing.cast(
242
244
  typing.Optional[typing.Any],
243
- parse_obj_as(
245
+ construct_type(
244
246
  type_=typing.Optional[typing.Any], # type: ignore
245
247
  object_=_response.json(),
246
248
  ),
@@ -250,7 +252,7 @@ class AsyncTextClient:
250
252
  raise ServiceUnavailableError(
251
253
  typing.cast(
252
254
  typing.Optional[typing.Any],
253
- parse_obj_as(
255
+ construct_type(
254
256
  type_=typing.Optional[typing.Any], # type: ignore
255
257
  object_=_response.json(),
256
258
  ),
murf/text_to_speech/client.py CHANGED
@@ -7,7 +7,7 @@ from ..types.pronunciation_detail import PronunciationDetail
7
7
  from ..core.request_options import RequestOptions
8
8
  from ..types.generate_speech_response import GenerateSpeechResponse
9
9
  from ..core.serialization import convert_and_respect_annotation_metadata
10
- from ..core.pydantic_utilities import parse_obj_as
10
+ from ..core.unchecked_base_model import construct_type
11
11
  from ..errors.bad_request_error import BadRequestError
12
12
  from ..errors.payment_required_error import PaymentRequiredError
13
13
  from ..errors.forbidden_error import ForbiddenError
@@ -43,6 +43,7 @@ class TextToSpeechClient:
43
43
  sample_rate: typing.Optional[float] = OMIT,
44
44
  style: typing.Optional[str] = OMIT,
45
45
  variation: typing.Optional[int] = OMIT,
46
+ word_durations_as_original_text: typing.Optional[bool] = OMIT,
46
47
  request_options: typing.Optional[RequestOptions] = None,
47
48
  ) -> GenerateSpeechResponse:
48
49
  """
@@ -66,7 +67,7 @@ class TextToSpeechClient:
66
67
  Set to true to receive audio in response as a Base64 encoded string instead of a url.
67
68
 
68
69
  format : typing.Optional[str]
69
- Format of the generated audio file. Valid values: MP3, WAV, FLAC, ALAW, ULAW
70
+ Format of the generated audio file. Valid values: MP3, WAV, FLAC, ALAW, ULAW, PCM, OGG
70
71
 
71
72
  model_version : typing.Optional[GenerateSpeechRequestModelVersion]
72
73
  Valid values: GEN1, GEN2. Use GEN2 to generate audio using new and advanced model. Outputs from Gen 2 will sound better, but different from the old model
@@ -97,6 +98,9 @@ class TextToSpeechClient:
97
98
  variation : typing.Optional[int]
98
99
  Higher values will add more variation in terms of Pause, Pitch, and Speed to the voice. Only available for Gen2 model.
99
100
 
101
+ word_durations_as_original_text : typing.Optional[bool]
102
+ If set to true, the word durations in response will return words as the original input text. (English only)
103
+
100
104
  request_options : typing.Optional[RequestOptions]
101
105
  Request-specific configuration.
102
106
 
@@ -119,6 +123,7 @@ class TextToSpeechClient:
119
123
  """
120
124
  _response = self._client_wrapper.httpx_client.request(
121
125
  "v1/speech/generate",
126
+ base_url=self._client_wrapper.get_environment().base,
122
127
  method="POST",
123
128
  json={
124
129
  "audioDuration": audio_duration,
@@ -139,6 +144,7 @@ class TextToSpeechClient:
139
144
  "text": text,
140
145
  "variation": variation,
141
146
  "voiceId": voice_id,
147
+ "wordDurationsAsOriginalText": word_durations_as_original_text,
142
148
  },
143
149
  headers={
144
150
  "content-type": "application/json",
@@ -150,7 +156,7 @@ class TextToSpeechClient:
150
156
  if 200 <= _response.status_code < 300:
151
157
  return typing.cast(
152
158
  GenerateSpeechResponse,
153
- parse_obj_as(
159
+ construct_type(
154
160
  type_=GenerateSpeechResponse, # type: ignore
155
161
  object_=_response.json(),
156
162
  ),
@@ -159,7 +165,7 @@ class TextToSpeechClient:
159
165
  raise BadRequestError(
160
166
  typing.cast(
161
167
  typing.Optional[typing.Any],
162
- parse_obj_as(
168
+ construct_type(
163
169
  type_=typing.Optional[typing.Any], # type: ignore
164
170
  object_=_response.json(),
165
171
  ),
@@ -169,7 +175,7 @@ class TextToSpeechClient:
169
175
  raise PaymentRequiredError(
170
176
  typing.cast(
171
177
  typing.Optional[typing.Any],
172
- parse_obj_as(
178
+ construct_type(
173
179
  type_=typing.Optional[typing.Any], # type: ignore
174
180
  object_=_response.json(),
175
181
  ),
@@ -179,7 +185,7 @@ class TextToSpeechClient:
179
185
  raise ForbiddenError(
180
186
  typing.cast(
181
187
  typing.Optional[typing.Any],
182
- parse_obj_as(
188
+ construct_type(
183
189
  type_=typing.Optional[typing.Any], # type: ignore
184
190
  object_=_response.json(),
185
191
  ),
@@ -189,7 +195,7 @@ class TextToSpeechClient:
189
195
  raise InternalServerError(
190
196
  typing.cast(
191
197
  typing.Optional[typing.Any],
192
- parse_obj_as(
198
+ construct_type(
193
199
  type_=typing.Optional[typing.Any], # type: ignore
194
200
  object_=_response.json(),
195
201
  ),
@@ -199,7 +205,7 @@ class TextToSpeechClient:
199
205
  raise ServiceUnavailableError(
200
206
  typing.cast(
201
207
  typing.Optional[typing.Any],
202
- parse_obj_as(
208
+ construct_type(
203
209
  type_=typing.Optional[typing.Any], # type: ignore
204
210
  object_=_response.json(),
205
211
  ),
@@ -219,6 +225,7 @@ class TextToSpeechClient:
219
225
  format: typing.Optional[str] = OMIT,
220
226
  multi_native_locale: typing.Optional[str] = OMIT,
221
227
  pitch: typing.Optional[int] = OMIT,
228
+ pronunciation_dictionary: typing.Optional[typing.Dict[str, PronunciationDetail]] = OMIT,
222
229
  rate: typing.Optional[int] = OMIT,
223
230
  sample_rate: typing.Optional[float] = OMIT,
224
231
  style: typing.Optional[str] = OMIT,
@@ -240,7 +247,7 @@ class TextToSpeechClient:
240
247
  Valid values: STEREO, MONO
241
248
 
242
249
  format : typing.Optional[str]
243
- Format of the generated audio file. Valid values: MP3, WAV
250
+ Format of the generated audio file. Valid values: MP3, WAV, PCM
244
251
 
245
252
  multi_native_locale : typing.Optional[str]
246
253
  Specifies the language for the generated audio, enabling a voice to speak in multiple languages natively. Only available in the Gen2 model.
@@ -249,6 +256,13 @@ class TextToSpeechClient:
249
256
  pitch : typing.Optional[int]
250
257
  Pitch of the voiceover
251
258
 
259
+ pronunciation_dictionary : typing.Optional[typing.Dict[str, PronunciationDetail]]
260
+ An object used to define custom pronunciations.
261
+
262
+ Example 1: {"live":{"type": "IPA", "pronunciation": "laɪv"}}.
263
+
264
+ Example 2: {"2022":{"type": "SAY_AS", "pronunciation": "twenty twenty two"}}
265
+
252
266
  rate : typing.Optional[int]
253
267
  Speed of the voiceover
254
268
 
@@ -280,12 +294,18 @@ class TextToSpeechClient:
280
294
  """
281
295
  with self._client_wrapper.httpx_client.stream(
282
296
  "v1/speech/stream",
297
+ base_url=self._client_wrapper.get_environment().base,
283
298
  method="POST",
284
299
  json={
285
300
  "channelType": channel_type,
286
301
  "format": format,
287
302
  "multiNativeLocale": multi_native_locale,
288
303
  "pitch": pitch,
304
+ "pronunciationDictionary": convert_and_respect_annotation_metadata(
305
+ object_=pronunciation_dictionary,
306
+ annotation=typing.Dict[str, PronunciationDetail],
307
+ direction="write",
308
+ ),
289
309
  "rate": rate,
290
310
  "sampleRate": sample_rate,
291
311
  "style": style,
@@ -310,7 +330,7 @@ class TextToSpeechClient:
310
330
  raise BadRequestError(
311
331
  typing.cast(
312
332
  typing.Optional[typing.Any],
313
- parse_obj_as(
333
+ construct_type(
314
334
  type_=typing.Optional[typing.Any], # type: ignore
315
335
  object_=_response.json(),
316
336
  ),
@@ -320,7 +340,7 @@ class TextToSpeechClient:
320
340
  raise PaymentRequiredError(
321
341
  typing.cast(
322
342
  typing.Optional[typing.Any],
323
- parse_obj_as(
343
+ construct_type(
324
344
  type_=typing.Optional[typing.Any], # type: ignore
325
345
  object_=_response.json(),
326
346
  ),
@@ -330,7 +350,7 @@ class TextToSpeechClient:
330
350
  raise ForbiddenError(
331
351
  typing.cast(
332
352
  typing.Optional[typing.Any],
333
- parse_obj_as(
353
+ construct_type(
334
354
  type_=typing.Optional[typing.Any], # type: ignore
335
355
  object_=_response.json(),
336
356
  ),
@@ -340,7 +360,7 @@ class TextToSpeechClient:
340
360
  raise InternalServerError(
341
361
  typing.cast(
342
362
  typing.Optional[typing.Any],
343
- parse_obj_as(
363
+ construct_type(
344
364
  type_=typing.Optional[typing.Any], # type: ignore
345
365
  object_=_response.json(),
346
366
  ),
@@ -350,7 +370,7 @@ class TextToSpeechClient:
350
370
  raise ServiceUnavailableError(
351
371
  typing.cast(
352
372
  typing.Optional[typing.Any],
353
- parse_obj_as(
373
+ construct_type(
354
374
  type_=typing.Optional[typing.Any], # type: ignore
355
375
  object_=_response.json(),
356
376
  ),
@@ -390,6 +410,7 @@ class TextToSpeechClient:
390
410
  """
391
411
  _response = self._client_wrapper.httpx_client.request(
392
412
  "v1/speech/voices",
413
+ base_url=self._client_wrapper.get_environment().base,
393
414
  method="GET",
394
415
  headers={
395
416
  "token": str(token) if token is not None else None,
@@ -400,7 +421,7 @@ class TextToSpeechClient:
400
421
  if 200 <= _response.status_code < 300:
401
422
  return typing.cast(
402
423
  typing.List[ApiVoice],
403
- parse_obj_as(
424
+ construct_type(
404
425
  type_=typing.List[ApiVoice], # type: ignore
405
426
  object_=_response.json(),
406
427
  ),
@@ -409,7 +430,7 @@ class TextToSpeechClient:
409
430
  raise BadRequestError(
410
431
  typing.cast(
411
432
  typing.Optional[typing.Any],
412
- parse_obj_as(
433
+ construct_type(
413
434
  type_=typing.Optional[typing.Any], # type: ignore
414
435
  object_=_response.json(),
415
436
  ),
@@ -419,7 +440,7 @@ class TextToSpeechClient:
419
440
  raise ForbiddenError(
420
441
  typing.cast(
421
442
  typing.Optional[typing.Any],
422
- parse_obj_as(
443
+ construct_type(
423
444
  type_=typing.Optional[typing.Any], # type: ignore
424
445
  object_=_response.json(),
425
446
  ),
@@ -429,7 +450,7 @@ class TextToSpeechClient:
429
450
  raise InternalServerError(
430
451
  typing.cast(
431
452
  typing.Optional[typing.Any],
432
- parse_obj_as(
453
+ construct_type(
433
454
  type_=typing.Optional[typing.Any], # type: ignore
434
455
  object_=_response.json(),
435
456
  ),
@@ -439,7 +460,7 @@ class TextToSpeechClient:
439
460
  raise ServiceUnavailableError(
440
461
  typing.cast(
441
462
  typing.Optional[typing.Any],
442
- parse_obj_as(
463
+ construct_type(
443
464
  type_=typing.Optional[typing.Any], # type: ignore
444
465
  object_=_response.json(),
445
466
  ),
@@ -472,6 +493,7 @@ class AsyncTextToSpeechClient:
472
493
  sample_rate: typing.Optional[float] = OMIT,
473
494
  style: typing.Optional[str] = OMIT,
474
495
  variation: typing.Optional[int] = OMIT,
496
+ word_durations_as_original_text: typing.Optional[bool] = OMIT,
475
497
  request_options: typing.Optional[RequestOptions] = None,
476
498
  ) -> GenerateSpeechResponse:
477
499
  """
@@ -495,7 +517,7 @@ class AsyncTextToSpeechClient:
495
517
  Set to true to receive audio in response as a Base64 encoded string instead of a url.
496
518
 
497
519
  format : typing.Optional[str]
498
- Format of the generated audio file. Valid values: MP3, WAV, FLAC, ALAW, ULAW
520
+ Format of the generated audio file. Valid values: MP3, WAV, FLAC, ALAW, ULAW, PCM, OGG
499
521
 
500
522
  model_version : typing.Optional[GenerateSpeechRequestModelVersion]
501
523
  Valid values: GEN1, GEN2. Use GEN2 to generate audio using new and advanced model. Outputs from Gen 2 will sound better, but different from the old model
@@ -526,6 +548,9 @@ class AsyncTextToSpeechClient:
526
548
  variation : typing.Optional[int]
527
549
  Higher values will add more variation in terms of Pause, Pitch, and Speed to the voice. Only available for Gen2 model.
528
550
 
551
+ word_durations_as_original_text : typing.Optional[bool]
552
+ If set to true, the word durations in response will return words as the original input text. (English only)
553
+
529
554
  request_options : typing.Optional[RequestOptions]
530
555
  Request-specific configuration.
531
556
 
@@ -556,6 +581,7 @@ class AsyncTextToSpeechClient:
556
581
  """
557
582
  _response = await self._client_wrapper.httpx_client.request(
558
583
  "v1/speech/generate",
584
+ base_url=self._client_wrapper.get_environment().base,
559
585
  method="POST",
560
586
  json={
561
587
  "audioDuration": audio_duration,
@@ -576,6 +602,7 @@ class AsyncTextToSpeechClient:
576
602
  "text": text,
577
603
  "variation": variation,
578
604
  "voiceId": voice_id,
605
+ "wordDurationsAsOriginalText": word_durations_as_original_text,
579
606
  },
580
607
  headers={
581
608
  "content-type": "application/json",
@@ -587,7 +614,7 @@ class AsyncTextToSpeechClient:
587
614
  if 200 <= _response.status_code < 300:
588
615
  return typing.cast(
589
616
  GenerateSpeechResponse,
590
- parse_obj_as(
617
+ construct_type(
591
618
  type_=GenerateSpeechResponse, # type: ignore
592
619
  object_=_response.json(),
593
620
  ),
@@ -596,7 +623,7 @@ class AsyncTextToSpeechClient:
596
623
  raise BadRequestError(
597
624
  typing.cast(
598
625
  typing.Optional[typing.Any],
599
- parse_obj_as(
626
+ construct_type(
600
627
  type_=typing.Optional[typing.Any], # type: ignore
601
628
  object_=_response.json(),
602
629
  ),
@@ -606,7 +633,7 @@ class AsyncTextToSpeechClient:
606
633
  raise PaymentRequiredError(
607
634
  typing.cast(
608
635
  typing.Optional[typing.Any],
609
- parse_obj_as(
636
+ construct_type(
610
637
  type_=typing.Optional[typing.Any], # type: ignore
611
638
  object_=_response.json(),
612
639
  ),
@@ -616,7 +643,7 @@ class AsyncTextToSpeechClient:
616
643
  raise ForbiddenError(
617
644
  typing.cast(
618
645
  typing.Optional[typing.Any],
619
- parse_obj_as(
646
+ construct_type(
620
647
  type_=typing.Optional[typing.Any], # type: ignore
621
648
  object_=_response.json(),
622
649
  ),
@@ -626,7 +653,7 @@ class AsyncTextToSpeechClient:
626
653
  raise InternalServerError(
627
654
  typing.cast(
628
655
  typing.Optional[typing.Any],
629
- parse_obj_as(
656
+ construct_type(
630
657
  type_=typing.Optional[typing.Any], # type: ignore
631
658
  object_=_response.json(),
632
659
  ),
@@ -636,7 +663,7 @@ class AsyncTextToSpeechClient:
636
663
  raise ServiceUnavailableError(
637
664
  typing.cast(
638
665
  typing.Optional[typing.Any],
639
- parse_obj_as(
666
+ construct_type(
640
667
  type_=typing.Optional[typing.Any], # type: ignore
641
668
  object_=_response.json(),
642
669
  ),
@@ -656,6 +683,7 @@ class AsyncTextToSpeechClient:
656
683
  format: typing.Optional[str] = OMIT,
657
684
  multi_native_locale: typing.Optional[str] = OMIT,
658
685
  pitch: typing.Optional[int] = OMIT,
686
+ pronunciation_dictionary: typing.Optional[typing.Dict[str, PronunciationDetail]] = OMIT,
659
687
  rate: typing.Optional[int] = OMIT,
660
688
  sample_rate: typing.Optional[float] = OMIT,
661
689
  style: typing.Optional[str] = OMIT,
@@ -677,7 +705,7 @@ class AsyncTextToSpeechClient:
677
705
  Valid values: STEREO, MONO
678
706
 
679
707
  format : typing.Optional[str]
680
- Format of the generated audio file. Valid values: MP3, WAV
708
+ Format of the generated audio file. Valid values: MP3, WAV, PCM
681
709
 
682
710
  multi_native_locale : typing.Optional[str]
683
711
  Specifies the language for the generated audio, enabling a voice to speak in multiple languages natively. Only available in the Gen2 model.
@@ -686,6 +714,13 @@ class AsyncTextToSpeechClient:
686
714
  pitch : typing.Optional[int]
687
715
  Pitch of the voiceover
688
716
 
717
+ pronunciation_dictionary : typing.Optional[typing.Dict[str, PronunciationDetail]]
718
+ An object used to define custom pronunciations.
719
+
720
+ Example 1: {"live":{"type": "IPA", "pronunciation": "laɪv"}}.
721
+
722
+ Example 2: {"2022":{"type": "SAY_AS", "pronunciation": "twenty twenty two"}}
723
+
689
724
  rate : typing.Optional[int]
690
725
  Speed of the voiceover
691
726
 
@@ -725,12 +760,18 @@ class AsyncTextToSpeechClient:
725
760
  """
726
761
  async with self._client_wrapper.httpx_client.stream(
727
762
  "v1/speech/stream",
763
+ base_url=self._client_wrapper.get_environment().base,
728
764
  method="POST",
729
765
  json={
730
766
  "channelType": channel_type,
731
767
  "format": format,
732
768
  "multiNativeLocale": multi_native_locale,
733
769
  "pitch": pitch,
770
+ "pronunciationDictionary": convert_and_respect_annotation_metadata(
771
+ object_=pronunciation_dictionary,
772
+ annotation=typing.Dict[str, PronunciationDetail],
773
+ direction="write",
774
+ ),
734
775
  "rate": rate,
735
776
  "sampleRate": sample_rate,
736
777
  "style": style,
@@ -755,7 +796,7 @@ class AsyncTextToSpeechClient:
755
796
  raise BadRequestError(
756
797
  typing.cast(
757
798
  typing.Optional[typing.Any],
758
- parse_obj_as(
799
+ construct_type(
759
800
  type_=typing.Optional[typing.Any], # type: ignore
760
801
  object_=_response.json(),
761
802
  ),
@@ -765,7 +806,7 @@ class AsyncTextToSpeechClient:
765
806
  raise PaymentRequiredError(
766
807
  typing.cast(
767
808
  typing.Optional[typing.Any],
768
- parse_obj_as(
809
+ construct_type(
769
810
  type_=typing.Optional[typing.Any], # type: ignore
770
811
  object_=_response.json(),
771
812
  ),
@@ -775,7 +816,7 @@ class AsyncTextToSpeechClient:
775
816
  raise ForbiddenError(
776
817
  typing.cast(
777
818
  typing.Optional[typing.Any],
778
- parse_obj_as(
819
+ construct_type(
779
820
  type_=typing.Optional[typing.Any], # type: ignore
780
821
  object_=_response.json(),
781
822
  ),
@@ -785,7 +826,7 @@ class AsyncTextToSpeechClient:
785
826
  raise InternalServerError(
786
827
  typing.cast(
787
828
  typing.Optional[typing.Any],
788
- parse_obj_as(
829
+ construct_type(
789
830
  type_=typing.Optional[typing.Any], # type: ignore
790
831
  object_=_response.json(),
791
832
  ),
@@ -795,7 +836,7 @@ class AsyncTextToSpeechClient:
795
836
  raise ServiceUnavailableError(
796
837
  typing.cast(
797
838
  typing.Optional[typing.Any],
798
- parse_obj_as(
839
+ construct_type(
799
840
  type_=typing.Optional[typing.Any], # type: ignore
800
841
  object_=_response.json(),
801
842
  ),
@@ -843,6 +884,7 @@ class AsyncTextToSpeechClient:
843
884
  """
844
885
  _response = await self._client_wrapper.httpx_client.request(
845
886
  "v1/speech/voices",
887
+ base_url=self._client_wrapper.get_environment().base,
846
888
  method="GET",
847
889
  headers={
848
890
  "token": str(token) if token is not None else None,
@@ -853,7 +895,7 @@ class AsyncTextToSpeechClient:
853
895
  if 200 <= _response.status_code < 300:
854
896
  return typing.cast(
855
897
  typing.List[ApiVoice],
856
- parse_obj_as(
898
+ construct_type(
857
899
  type_=typing.List[ApiVoice], # type: ignore
858
900
  object_=_response.json(),
859
901
  ),
@@ -862,7 +904,7 @@ class AsyncTextToSpeechClient:
862
904
  raise BadRequestError(
863
905
  typing.cast(
864
906
  typing.Optional[typing.Any],
865
- parse_obj_as(
907
+ construct_type(
866
908
  type_=typing.Optional[typing.Any], # type: ignore
867
909
  object_=_response.json(),
868
910
  ),
@@ -872,7 +914,7 @@ class AsyncTextToSpeechClient:
872
914
  raise ForbiddenError(
873
915
  typing.cast(
874
916
  typing.Optional[typing.Any],
875
- parse_obj_as(
917
+ construct_type(
876
918
  type_=typing.Optional[typing.Any], # type: ignore
877
919
  object_=_response.json(),
878
920
  ),
@@ -882,7 +924,7 @@ class AsyncTextToSpeechClient:
882
924
  raise InternalServerError(
883
925
  typing.cast(
884
926
  typing.Optional[typing.Any],
885
- parse_obj_as(
927
+ construct_type(
886
928
  type_=typing.Optional[typing.Any], # type: ignore
887
929
  object_=_response.json(),
888
930
  ),
@@ -892,7 +934,7 @@ class AsyncTextToSpeechClient:
892
934
  raise ServiceUnavailableError(
893
935
  typing.cast(
894
936
  typing.Optional[typing.Any],
895
- parse_obj_as(
937
+ construct_type(
896
938
  type_=typing.Optional[typing.Any], # type: ignore
897
939
  object_=_response.json(),
898
940
  ),