Skip to content

Commit 8e3099b

Browse files
feat(stt&tts): Add new model enum values
1 parent 4c40daf commit 8e3099b

File tree

2 files changed

+27
-11
lines changed

2 files changed

+27
-11
lines changed

ibm_watson/speech_to_text_v1.py

Lines changed: 5 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# coding: utf-8
22

3-
# (C) Copyright IBM Corp. 2015, 2024.
3+
# (C) Copyright IBM Corp. 2015, 2025.
44
#
55
# Licensed under the Apache License, Version 2.0 (the "License");
66
# you may not use this file except in compliance with the License.
@@ -14,7 +14,7 @@
1414
# See the License for the specific language governing permissions and
1515
# limitations under the License.
1616

17-
# IBM OpenAPI SDK Code Generator Version: 3.97.0-0e90eab1-20241120-170029
17+
# IBM OpenAPI SDK Code Generator Version: 3.105.0-3c13b041-20250605-193116
1818
"""
1919
The IBM Watson™ Speech to Text service provides APIs that use IBM's
2020
speech-recognition capabilities to produce transcripts of spoken audio. The service can
@@ -4309,6 +4309,7 @@ class ModelId(str, Enum):
43094309
AR_MS_BROADBANDMODEL = 'ar-MS_BroadbandModel'
43104310
AR_MS_TELEPHONY = 'ar-MS_Telephony'
43114311
CS_CZ_TELEPHONY = 'cs-CZ_Telephony'
4312+
DE_DE = 'de-DE'
43124313
DE_DE_BROADBANDMODEL = 'de-DE_BroadbandModel'
43134314
DE_DE_MULTIMEDIA = 'de-DE_Multimedia'
43144315
DE_DE_NARROWBANDMODEL = 'de-DE_NarrowbandModel'
@@ -4438,6 +4439,7 @@ class Model(str, Enum):
44384439
AR_MS_BROADBANDMODEL = 'ar-MS_BroadbandModel'
44394440
AR_MS_TELEPHONY = 'ar-MS_Telephony'
44404441
CS_CZ_TELEPHONY = 'cs-CZ_Telephony'
4442+
DE_DE = 'de-DE'
44414443
DE_DE_BROADBANDMODEL = 'de-DE_BroadbandModel'
44424444
DE_DE_MULTIMEDIA = 'de-DE_Multimedia'
44434445
DE_DE_NARROWBANDMODEL = 'de-DE_NarrowbandModel'
@@ -4567,6 +4569,7 @@ class Model(str, Enum):
45674569
AR_MS_BROADBANDMODEL = 'ar-MS_BroadbandModel'
45684570
AR_MS_TELEPHONY = 'ar-MS_Telephony'
45694571
CS_CZ_TELEPHONY = 'cs-CZ_Telephony'
4572+
DE_DE = 'de-DE'
45704573
DE_DE_BROADBANDMODEL = 'de-DE_BroadbandModel'
45714574
DE_DE_MULTIMEDIA = 'de-DE_Multimedia'
45724575
DE_DE_NARROWBANDMODEL = 'de-DE_NarrowbandModel'

ibm_watson/text_to_speech_v1.py

Lines changed: 22 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# coding: utf-8
22

3-
# (C) Copyright IBM Corp. 2015, 2024.
3+
# (C) Copyright IBM Corp. 2015, 2025.
44
#
55
# Licensed under the Apache License, Version 2.0 (the "License");
66
# you may not use this file except in compliance with the License.
@@ -14,7 +14,7 @@
1414
# See the License for the specific language governing permissions and
1515
# limitations under the License.
1616

17-
# IBM OpenAPI SDK Code Generator Version: 3.97.0-0e90eab1-20241120-170029
17+
# IBM OpenAPI SDK Code Generator Version: 3.105.0-3c13b041-20250605-193116
1818
"""
1919
The IBM Watson™ Text to Speech service provides APIs that use IBM's speech-synthesis
2020
capabilities to synthesize text into natural-sounding speech in a variety of languages,
@@ -232,31 +232,32 @@ def synthesize(
232232
* `audio/alaw` - You must specify the `rate` of the audio.
233233
* `audio/basic` - The service returns audio with a sampling rate of 8000 Hz.
234234
* `audio/flac` - You can optionally specify the `rate` of the audio. The default
235-
sampling rate is 22,050 Hz.
235+
sampling rate is 24,000 Hz for Natural voices and 22,050 Hz for all other voices.
236236
* `audio/l16` - You must specify the `rate` of the audio. You can optionally
237237
specify the `endianness` of the audio. The default endianness is `little-endian`.
238238
* `audio/mp3` - You can optionally specify the `rate` of the audio. The default
239-
sampling rate is 22,050 Hz.
239+
sampling rate is 24,000 Hz for Natural voices and 22,050 Hz for for all other
240+
voices.
240241
* `audio/mpeg` - You can optionally specify the `rate` of the audio. The default
241-
sampling rate is 22,050 Hz.
242+
sampling rate is 24,000 Hz for Natural voices and 22,050 Hz for all other voices.
242243
* `audio/mulaw` - You must specify the `rate` of the audio.
243244
* `audio/ogg` - The service returns the audio in the `vorbis` codec. You can
244-
optionally specify the `rate` of the audio. The default sampling rate is 22,050
245+
optionally specify the `rate` of the audio. The default sampling rate is 48,000
245246
Hz.
246247
* `audio/ogg;codecs=opus` - You can optionally specify the `rate` of the audio.
247248
Only the following values are valid sampling rates: `48000`, `24000`, `16000`,
248249
`12000`, or `8000`. If you specify a value other than one of these, the service
249250
returns an error. The default sampling rate is 48,000 Hz.
250251
* `audio/ogg;codecs=vorbis` - You can optionally specify the `rate` of the audio.
251-
The default sampling rate is 22,050 Hz.
252+
The default sampling rate is 48,000 Hz.
252253
* `audio/wav` - You can optionally specify the `rate` of the audio. The default
253-
sampling rate is 22,050 Hz.
254+
sampling rate is 24,000 Hz for Natural voices and 22,050 Hz for all other voices.
254255
* `audio/webm` - The service returns the audio in the `opus` codec. The service
255256
returns audio with a sampling rate of 48,000 Hz.
256257
* `audio/webm;codecs=opus` - The service returns audio with a sampling rate of
257258
48,000 Hz.
258259
* `audio/webm;codecs=vorbis` - You can optionally specify the `rate` of the audio.
259-
The default sampling rate is 22,050 Hz.
260+
The default sampling rate is 48,000 Hz.
260261
For more information about specifying an audio format, including additional
261262
details about some of the formats, see [Using audio
262263
formats](https://cloud.ibm.com/docs/text-to-speech?topic=text-to-speech-audio-formats).
@@ -1808,10 +1809,12 @@ class Voice(str, Enum):
18081809
EN_AU_HEIDIEXPRESSIVE = 'en-AU_HeidiExpressive'
18091810
EN_AU_JACKEXPRESSIVE = 'en-AU_JackExpressive'
18101811
EN_GB_CHARLOTTEV3VOICE = 'en-GB_CharlotteV3Voice'
1812+
EN_GB_GEORGEEXPRESSIVE = 'en-GB_GeorgeExpressive'
18111813
EN_GB_JAMESV3VOICE = 'en-GB_JamesV3Voice'
18121814
EN_GB_KATEV3VOICE = 'en-GB_KateV3Voice'
18131815
EN_US_ALLISONEXPRESSIVE = 'en-US_AllisonExpressive'
18141816
EN_US_ALLISONV3VOICE = 'en-US_AllisonV3Voice'
1817+
EN_US_ELLIENATURAL = 'en-US_EllieNatural'
18151818
EN_US_EMILYV3VOICE = 'en-US_EmilyV3Voice'
18161819
EN_US_EMMAEXPRESSIVE = 'en-US_EmmaExpressive'
18171820
EN_US_HENRYV3VOICE = 'en-US_HenryV3Voice'
@@ -1823,6 +1826,7 @@ class Voice(str, Enum):
18231826
EN_US_OLIVIAV3VOICE = 'en-US_OliviaV3Voice'
18241827
ES_ES_ENRIQUEV3VOICE = 'es-ES_EnriqueV3Voice'
18251828
ES_ES_LAURAV3VOICE = 'es-ES_LauraV3Voice'
1829+
ES_LA_DANIELAEXPRESSIVE = 'es-LA_DanielaExpressive'
18261830
ES_LA_SOFIAV3VOICE = 'es-LA_SofiaV3Voice'
18271831
ES_US_SOFIAV3VOICE = 'es-US_SofiaV3Voice'
18281832
FR_CA_LOUISEV3VOICE = 'fr-CA_LouiseV3Voice'
@@ -1833,6 +1837,7 @@ class Voice(str, Enum):
18331837
KO_KR_JINV3VOICE = 'ko-KR_JinV3Voice'
18341838
NL_NL_MERELV3VOICE = 'nl-NL_MerelV3Voice'
18351839
PT_BR_ISABELAV3VOICE = 'pt-BR_IsabelaV3Voice'
1840+
PT_BR_LUCASEXPRESSIVE = 'pt-BR_LucasExpressive'
18361841

18371842

18381843
class SynthesizeEnums:
@@ -1883,10 +1888,12 @@ class Voice(str, Enum):
18831888
EN_AU_HEIDIEXPRESSIVE = 'en-AU_HeidiExpressive'
18841889
EN_AU_JACKEXPRESSIVE = 'en-AU_JackExpressive'
18851890
EN_GB_CHARLOTTEV3VOICE = 'en-GB_CharlotteV3Voice'
1891+
EN_GB_GEORGEEXPRESSIVE = 'en-GB_GeorgeExpressive'
18861892
EN_GB_JAMESV3VOICE = 'en-GB_JamesV3Voice'
18871893
EN_GB_KATEV3VOICE = 'en-GB_KateV3Voice'
18881894
EN_US_ALLISONEXPRESSIVE = 'en-US_AllisonExpressive'
18891895
EN_US_ALLISONV3VOICE = 'en-US_AllisonV3Voice'
1896+
EN_US_ELLIENATURAL = 'en-US_EllieNatural'
18901897
EN_US_EMILYV3VOICE = 'en-US_EmilyV3Voice'
18911898
EN_US_EMMAEXPRESSIVE = 'en-US_EmmaExpressive'
18921899
EN_US_HENRYV3VOICE = 'en-US_HenryV3Voice'
@@ -1898,6 +1905,7 @@ class Voice(str, Enum):
18981905
EN_US_OLIVIAV3VOICE = 'en-US_OliviaV3Voice'
18991906
ES_ES_ENRIQUEV3VOICE = 'es-ES_EnriqueV3Voice'
19001907
ES_ES_LAURAV3VOICE = 'es-ES_LauraV3Voice'
1908+
ES_LA_DANIELAEXPRESSIVE = 'es-LA_DanielaExpressive'
19011909
ES_LA_SOFIAV3VOICE = 'es-LA_SofiaV3Voice'
19021910
ES_US_SOFIAV3VOICE = 'es-US_SofiaV3Voice'
19031911
FR_CA_LOUISEV3VOICE = 'fr-CA_LouiseV3Voice'
@@ -1908,6 +1916,7 @@ class Voice(str, Enum):
19081916
KO_KR_JINV3VOICE = 'ko-KR_JinV3Voice'
19091917
NL_NL_MERELV3VOICE = 'nl-NL_MerelV3Voice'
19101918
PT_BR_ISABELAV3VOICE = 'pt-BR_IsabelaV3Voice'
1919+
PT_BR_LUCASEXPRESSIVE = 'pt-BR_LucasExpressive'
19111920

19121921
class SpellOutMode(str, Enum):
19131922
"""
@@ -1957,10 +1966,12 @@ class Voice(str, Enum):
19571966
EN_AU_HEIDIEXPRESSIVE = 'en-AU_HeidiExpressive'
19581967
EN_AU_JACKEXPRESSIVE = 'en-AU_JackExpressive'
19591968
EN_GB_CHARLOTTEV3VOICE = 'en-GB_CharlotteV3Voice'
1969+
EN_GB_GEORGEEXPRESSIVE = 'en-GB_GeorgeExpressive'
19601970
EN_GB_JAMESV3VOICE = 'en-GB_JamesV3Voice'
19611971
EN_GB_KATEV3VOICE = 'en-GB_KateV3Voice'
19621972
EN_US_ALLISONEXPRESSIVE = 'en-US_AllisonExpressive'
19631973
EN_US_ALLISONV3VOICE = 'en-US_AllisonV3Voice'
1974+
EN_US_ELLIENATURAL = 'en-US_EllieNatural'
19641975
EN_US_EMILYV3VOICE = 'en-US_EmilyV3Voice'
19651976
EN_US_EMMAEXPRESSIVE = 'en-US_EmmaExpressive'
19661977
EN_US_HENRYV3VOICE = 'en-US_HenryV3Voice'
@@ -1972,6 +1983,7 @@ class Voice(str, Enum):
19721983
EN_US_OLIVIAV3VOICE = 'en-US_OliviaV3Voice'
19731984
ES_ES_ENRIQUEV3VOICE = 'es-ES_EnriqueV3Voice'
19741985
ES_ES_LAURAV3VOICE = 'es-ES_LauraV3Voice'
1986+
ES_LA_DANIELAEXPRESSIVE = 'es-LA_DanielaExpressive'
19751987
ES_LA_SOFIAV3VOICE = 'es-LA_SofiaV3Voice'
19761988
ES_US_SOFIAV3VOICE = 'es-US_SofiaV3Voice'
19771989
FR_CA_LOUISEV3VOICE = 'fr-CA_LouiseV3Voice'
@@ -1982,6 +1994,7 @@ class Voice(str, Enum):
19821994
KO_KR_JINV3VOICE = 'ko-KR_JinV3Voice'
19831995
NL_NL_MERELV3VOICE = 'nl-NL_MerelV3Voice'
19841996
PT_BR_ISABELAV3VOICE = 'pt-BR_IsabelaV3Voice'
1997+
PT_BR_LUCASEXPRESSIVE = 'pt-BR_LucasExpressive'
19851998

19861999
class Format(str, Enum):
19872000
"""

0 commit comments

Comments
 (0)