google-cloud-text_to_speech-v1 1.8.1 → 1.9.0
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.
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 97e4e0eebd64b8146111e2a32549706a02cf6b1fb19a91829f00a101d39ac520
|
|
4
|
+
data.tar.gz: 042b6a4eee4aa7235e8237e07a0d5fcd1dbebfbd8cc19ad9e7455ec67295ee91
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: c3a2549298b089ad9e2796a0a65190e4008aa8bc8aaf5f0174e5d4c02fd88009d2c535d0e04741fb7a80b9e064c45959576e9237bf691a3d32c3e60254f7bc03
|
|
7
|
+
data.tar.gz: 033fa02ee247d0a45e25fda3b1cac67a55bd3944cd5c8156974db61708677aca0f63f104ea785fddf8116feef085e00cc4975b4dbeac1b38fa374c141811ed9b
|
|
@@ -10,7 +10,7 @@ require 'google/api/field_behavior_pb'
|
|
|
10
10
|
require 'google/api/resource_pb'
|
|
11
11
|
|
|
12
12
|
|
|
13
|
-
descriptor_data = "\n,google/cloud/texttospeech/v1/cloud_tts.proto\x12\x1cgoogle.cloud.texttospeech.v1\x1a\x1cgoogle/api/annotations.proto\x1a\x17google/api/client.proto\x1a\x1fgoogle/api/field_behavior.proto\x1a\x19google/api/resource.proto\"/\n\x11ListVoicesRequest\x12\x1a\n\rlanguage_code\x18\x01 \x01(\tB\x03\xe0\x41\x01\"I\n\x12ListVoicesResponse\x12\x33\n\x06voices\x18\x01 \x03(\x0b\x32#.google.cloud.texttospeech.v1.Voice\"\x94\x01\n\x05Voice\x12\x16\n\x0elanguage_codes\x18\x01 \x03(\t\x12\x0c\n\x04name\x18\x02 \x01(\t\x12\x42\n\x0bssml_gender\x18\x03 \x01(\x0e\x32-.google.cloud.texttospeech.v1.SsmlVoiceGender\x12!\n\x19natural_sample_rate_hertz\x18\x04 \x01(\x05\"d\n\x14\x41\x64vancedVoiceOptions\x12*\n\x1dlow_latency_journey_synthesis\x18\x01 \x01(\x08H\x00\x88\x01\x01\x42 \n\x1e_low_latency_journey_synthesis\"\xdd\x02\n\x17SynthesizeSpeechRequest\x12@\n\x05input\x18\x01 \x01(\x0b\x32,.google.cloud.texttospeech.v1.SynthesisInputB\x03\xe0\x41\x02\x12\x46\n\x05voice\x18\x02 \x01(\x0b\x32\x32.google.cloud.texttospeech.v1.VoiceSelectionParamsB\x03\xe0\x41\x02\x12\x44\n\x0c\x61udio_config\x18\x03 \x01(\x0b\x32).google.cloud.texttospeech.v1.AudioConfigB\x03\xe0\x41\x02\x12W\n\x16\x61\x64vanced_voice_options\x18\x08 \x01(\x0b\x32\x32.google.cloud.texttospeech.v1.AdvancedVoiceOptionsH\x00\x88\x01\x01\x42\x19\n\x17_advanced_voice_options\"\
|
|
13
|
+
descriptor_data = "\n,google/cloud/texttospeech/v1/cloud_tts.proto\x12\x1cgoogle.cloud.texttospeech.v1\x1a\x1cgoogle/api/annotations.proto\x1a\x17google/api/client.proto\x1a\x1fgoogle/api/field_behavior.proto\x1a\x19google/api/resource.proto\"/\n\x11ListVoicesRequest\x12\x1a\n\rlanguage_code\x18\x01 \x01(\tB\x03\xe0\x41\x01\"I\n\x12ListVoicesResponse\x12\x33\n\x06voices\x18\x01 \x03(\x0b\x32#.google.cloud.texttospeech.v1.Voice\"\x94\x01\n\x05Voice\x12\x16\n\x0elanguage_codes\x18\x01 \x03(\t\x12\x0c\n\x04name\x18\x02 \x01(\t\x12\x42\n\x0bssml_gender\x18\x03 \x01(\x0e\x32-.google.cloud.texttospeech.v1.SsmlVoiceGender\x12!\n\x19natural_sample_rate_hertz\x18\x04 \x01(\x05\"d\n\x14\x41\x64vancedVoiceOptions\x12*\n\x1dlow_latency_journey_synthesis\x18\x01 \x01(\x08H\x00\x88\x01\x01\x42 \n\x1e_low_latency_journey_synthesis\"\xdd\x02\n\x17SynthesizeSpeechRequest\x12@\n\x05input\x18\x01 \x01(\x0b\x32,.google.cloud.texttospeech.v1.SynthesisInputB\x03\xe0\x41\x02\x12\x46\n\x05voice\x18\x02 \x01(\x0b\x32\x32.google.cloud.texttospeech.v1.VoiceSelectionParamsB\x03\xe0\x41\x02\x12\x44\n\x0c\x61udio_config\x18\x03 \x01(\x0b\x32).google.cloud.texttospeech.v1.AudioConfigB\x03\xe0\x41\x02\x12W\n\x16\x61\x64vanced_voice_options\x18\x08 \x01(\x0b\x32\x32.google.cloud.texttospeech.v1.AdvancedVoiceOptionsH\x00\x88\x01\x01\x42\x19\n\x17_advanced_voice_options\"\xa2\x03\n\x19\x43ustomPronunciationParams\x12\x13\n\x06phrase\x18\x01 \x01(\tH\x00\x88\x01\x01\x12h\n\x11phonetic_encoding\x18\x02 \x01(\x0e\x32H.google.cloud.texttospeech.v1.CustomPronunciationParams.PhoneticEncodingH\x01\x88\x01\x01\x12\x1a\n\rpronunciation\x18\x03 \x01(\tH\x02\x88\x01\x01\"\xb6\x01\n\x10PhoneticEncoding\x12!\n\x1dPHONETIC_ENCODING_UNSPECIFIED\x10\x00\x12\x19\n\x15PHONETIC_ENCODING_IPA\x10\x01\x12\x1d\n\x19PHONETIC_ENCODING_X_SAMPA\x10\x02\x12\'\n#PHONETIC_ENCODING_JAPANESE_YOMIGANA\x10\x03\x12\x1c\n\x18PHONETIC_ENCODING_PINYIN\x10\x04\x42\t\n\x07_phraseB\x14\n\x12_phonetic_encodingB\x10\n\x0e_pronunciation\"g\n\x14\x43ustomPronunciations\x12O\n\x0epronunciations\x18\x01 \x03(\x0b\x32\x37.google.cloud.texttospeech.v1.CustomPronunciationParams\"\x90\x01\n\x12MultiSpeakerMarkup\x12I\n\x05turns\x18\x01 \x03(\x0b\x32\x35.google.cloud.texttospeech.v1.MultiSpeakerMarkup.TurnB\x03\xe0\x41\x02\x1a/\n\x04Turn\x12\x14\n\x07speaker\x18\x01 \x01(\tB\x03\xe0\x41\x02\x12\x11\n\x04text\x18\x02 \x01(\tB\x03\xe0\x41\x02\"\xfc\x01\n\x0eSynthesisInput\x12\x0e\n\x04text\x18\x01 \x01(\tH\x00\x12\x10\n\x06markup\x18\x05 \x01(\tH\x00\x12\x0e\n\x04ssml\x18\x02 \x01(\tH\x00\x12P\n\x14multi_speaker_markup\x18\x04 \x01(\x0b\x32\x30.google.cloud.texttospeech.v1.MultiSpeakerMarkupH\x00\x12V\n\x15\x63ustom_pronunciations\x18\x03 \x01(\x0b\x32\x32.google.cloud.texttospeech.v1.CustomPronunciationsB\x03\xe0\x41\x01\x42\x0e\n\x0cinput_source\"\x95\x02\n\x14VoiceSelectionParams\x12\x1a\n\rlanguage_code\x18\x01 \x01(\tB\x03\xe0\x41\x02\x12\x0c\n\x04name\x18\x02 \x01(\t\x12\x42\n\x0bssml_gender\x18\x03 \x01(\x0e\x32-.google.cloud.texttospeech.v1.SsmlVoiceGender\x12\x45\n\x0c\x63ustom_voice\x18\x04 \x01(\x0b\x32/.google.cloud.texttospeech.v1.CustomVoiceParams\x12H\n\x0bvoice_clone\x18\x05 \x01(\x0b\x32..google.cloud.texttospeech.v1.VoiceCloneParamsB\x03\xe0\x41\x01\"\xf1\x01\n\x0b\x41udioConfig\x12H\n\x0e\x61udio_encoding\x18\x01 \x01(\x0e\x32+.google.cloud.texttospeech.v1.AudioEncodingB\x03\xe0\x41\x02\x12\x1d\n\rspeaking_rate\x18\x02 \x01(\x01\x42\x06\xe0\x41\x04\xe0\x41\x01\x12\x15\n\x05pitch\x18\x03 \x01(\x01\x42\x06\xe0\x41\x04\xe0\x41\x01\x12\x1e\n\x0evolume_gain_db\x18\x04 \x01(\x01\x42\x06\xe0\x41\x04\xe0\x41\x01\x12\x1e\n\x11sample_rate_hertz\x18\x05 \x01(\x05\x42\x03\xe0\x41\x01\x12\"\n\x12\x65\x66\x66\x65\x63ts_profile_id\x18\x06 \x03(\tB\x06\xe0\x41\x04\xe0\x41\x01\"\xf1\x01\n\x11\x43ustomVoiceParams\x12\x32\n\x05model\x18\x01 \x01(\tB#\xe0\x41\x02\xfa\x41\x1d\n\x1b\x61utoml.googleapis.com/Model\x12\\\n\x0ereported_usage\x18\x03 \x01(\x0e\x32=.google.cloud.texttospeech.v1.CustomVoiceParams.ReportedUsageB\x05\x18\x01\xe0\x41\x01\"J\n\rReportedUsage\x12\x1e\n\x1aREPORTED_USAGE_UNSPECIFIED\x10\x00\x12\x0c\n\x08REALTIME\x10\x01\x12\x0b\n\x07OFFLINE\x10\x02\"2\n\x10VoiceCloneParams\x12\x1e\n\x11voice_cloning_key\x18\x01 \x01(\tB\x03\xe0\x41\x02\"1\n\x18SynthesizeSpeechResponse\x12\x15\n\raudio_content\x18\x01 \x01(\x0c\"\x9f\x01\n\x14StreamingAudioConfig\x12H\n\x0e\x61udio_encoding\x18\x01 \x01(\x0e\x32+.google.cloud.texttospeech.v1.AudioEncodingB\x03\xe0\x41\x02\x12\x1e\n\x11sample_rate_hertz\x18\x02 \x01(\x05\x42\x03\xe0\x41\x01\x12\x1d\n\rspeaking_rate\x18\x03 \x01(\x01\x42\x06\xe0\x41\x04\xe0\x41\x01\"\x94\x02\n\x19StreamingSynthesizeConfig\x12\x46\n\x05voice\x18\x01 \x01(\x0b\x32\x32.google.cloud.texttospeech.v1.VoiceSelectionParamsB\x03\xe0\x41\x02\x12W\n\x16streaming_audio_config\x18\x04 \x01(\x0b\x32\x32.google.cloud.texttospeech.v1.StreamingAudioConfigB\x03\xe0\x41\x01\x12V\n\x15\x63ustom_pronunciations\x18\x05 \x01(\x0b\x32\x32.google.cloud.texttospeech.v1.CustomPronunciationsB\x03\xe0\x41\x01\"K\n\x17StreamingSynthesisInput\x12\x0e\n\x04text\x18\x01 \x01(\tH\x00\x12\x10\n\x06markup\x18\x05 \x01(\tH\x00\x42\x0e\n\x0cinput_source\"\xce\x01\n\x1aStreamingSynthesizeRequest\x12S\n\x10streaming_config\x18\x01 \x01(\x0b\x32\x37.google.cloud.texttospeech.v1.StreamingSynthesizeConfigH\x00\x12\x46\n\x05input\x18\x02 \x01(\x0b\x32\x35.google.cloud.texttospeech.v1.StreamingSynthesisInputH\x00\x42\x13\n\x11streaming_request\"4\n\x1bStreamingSynthesizeResponse\x12\x15\n\raudio_content\x18\x01 \x01(\x0c*W\n\x0fSsmlVoiceGender\x12!\n\x1dSSML_VOICE_GENDER_UNSPECIFIED\x10\x00\x12\x08\n\x04MALE\x10\x01\x12\n\n\x06\x46\x45MALE\x10\x02\x12\x0b\n\x07NEUTRAL\x10\x03*r\n\rAudioEncoding\x12\x1e\n\x1a\x41UDIO_ENCODING_UNSPECIFIED\x10\x00\x12\x0c\n\x08LINEAR16\x10\x01\x12\x07\n\x03MP3\x10\x02\x12\x0c\n\x08OGG_OPUS\x10\x03\x12\t\n\x05MULAW\x10\x05\x12\x08\n\x04\x41LAW\x10\x06\x12\x07\n\x03PCM\x10\x07\x32\xc7\x04\n\x0cTextToSpeech\x12\x93\x01\n\nListVoices\x12/.google.cloud.texttospeech.v1.ListVoicesRequest\x1a\x30.google.cloud.texttospeech.v1.ListVoicesResponse\"\"\xda\x41\rlanguage_code\x82\xd3\xe4\x93\x02\x0c\x12\n/v1/voices\x12\xbc\x01\n\x10SynthesizeSpeech\x12\x35.google.cloud.texttospeech.v1.SynthesizeSpeechRequest\x1a\x36.google.cloud.texttospeech.v1.SynthesizeSpeechResponse\"9\xda\x41\x18input,voice,audio_config\x82\xd3\xe4\x93\x02\x18\"\x13/v1/text:synthesize:\x01*\x12\x90\x01\n\x13StreamingSynthesize\x12\x38.google.cloud.texttospeech.v1.StreamingSynthesizeRequest\x1a\x39.google.cloud.texttospeech.v1.StreamingSynthesizeResponse\"\x00(\x01\x30\x01\x1aO\xca\x41\x1btexttospeech.googleapis.com\xd2\x41.https://www.googleapis.com/auth/cloud-platformB\xbc\x02\n com.google.cloud.texttospeech.v1B\x11TextToSpeechProtoP\x01ZDcloud.google.com/go/texttospeech/apiv1/texttospeechpb;texttospeechpb\xa2\x02\x04\x43TTS\xaa\x02\x1cGoogle.Cloud.TextToSpeech.V1\xca\x02\x1cGoogle\\Cloud\\TextToSpeech\\V1\xea\x02\x1fGoogle::Cloud::TextToSpeech::V1\xea\x41U\n\x1b\x61utoml.googleapis.com/Model\x12\x36projects/{project}/locations/{location}/models/{model}b\x06proto3"
|
|
14
14
|
|
|
15
15
|
pool = Google::Protobuf::DescriptorPool.generated_pool
|
|
16
16
|
|
|
@@ -123,6 +123,29 @@ module Google
|
|
|
123
123
|
# X-SAMPA, such as apple -> "{p@l".
|
|
124
124
|
# https://en.wikipedia.org/wiki/X-SAMPA
|
|
125
125
|
PHONETIC_ENCODING_X_SAMPA = 2
|
|
126
|
+
|
|
127
|
+
# For reading-to-pron conversion to work well, the `pronunciation` field
|
|
128
|
+
# should only contain Kanji, Hiragana, and Katakana.
|
|
129
|
+
#
|
|
130
|
+
# The pronunciation can also contain pitch accents.
|
|
131
|
+
# The start of a pitch phrase is specified with `^` and the down-pitch
|
|
132
|
+
# position is specified with `!`, for example:
|
|
133
|
+
#
|
|
134
|
+
# phrase:端 pronunciation:^はし
|
|
135
|
+
# phrase:箸 pronunciation:^は!し
|
|
136
|
+
# phrase:橋 pronunciation:^はし!
|
|
137
|
+
#
|
|
138
|
+
# We currently only support the Tokyo dialect, which allows at most one
|
|
139
|
+
# down-pitch per phrase (i.e. at most one `!` between `^`).
|
|
140
|
+
PHONETIC_ENCODING_JAPANESE_YOMIGANA = 3
|
|
141
|
+
|
|
142
|
+
# Used to specify pronunciations for Mandarin words. See
|
|
143
|
+
# https://en.wikipedia.org/wiki/Pinyin.
|
|
144
|
+
#
|
|
145
|
+
# For example: 朝阳, the pronunciation is "chao2 yang2". The number
|
|
146
|
+
# represents the tone, and there is a space between syllables. Neutral
|
|
147
|
+
# tones are represented by 5, for example 孩子 "hai2 zi5".
|
|
148
|
+
PHONETIC_ENCODING_PINYIN = 4
|
|
126
149
|
end
|
|
127
150
|
end
|
|
128
151
|
|
|
@@ -165,7 +188,13 @@ module Google
|
|
|
165
188
|
# @return [::String]
|
|
166
189
|
# The raw text to be synthesized.
|
|
167
190
|
#
|
|
168
|
-
# Note: The following fields are mutually exclusive: `text`, `ssml`, `multi_speaker_markup`. If a field in that set is populated, all other fields in the set will automatically be cleared.
|
|
191
|
+
# Note: The following fields are mutually exclusive: `text`, `markup`, `ssml`, `multi_speaker_markup`. If a field in that set is populated, all other fields in the set will automatically be cleared.
|
|
192
|
+
# @!attribute [rw] markup
|
|
193
|
+
# @return [::String]
|
|
194
|
+
# Markup for HD voices specifically. This field may not be used with any
|
|
195
|
+
# other voices.
|
|
196
|
+
#
|
|
197
|
+
# Note: The following fields are mutually exclusive: `markup`, `text`, `ssml`, `multi_speaker_markup`. If a field in that set is populated, all other fields in the set will automatically be cleared.
|
|
169
198
|
# @!attribute [rw] ssml
|
|
170
199
|
# @return [::String]
|
|
171
200
|
# The SSML document to be synthesized. The SSML document must be valid
|
|
@@ -174,13 +203,13 @@ module Google
|
|
|
174
203
|
# more information, see
|
|
175
204
|
# [SSML](https://cloud.google.com/text-to-speech/docs/ssml).
|
|
176
205
|
#
|
|
177
|
-
# Note: The following fields are mutually exclusive: `ssml`, `text`, `multi_speaker_markup`. If a field in that set is populated, all other fields in the set will automatically be cleared.
|
|
206
|
+
# Note: The following fields are mutually exclusive: `ssml`, `text`, `markup`, `multi_speaker_markup`. If a field in that set is populated, all other fields in the set will automatically be cleared.
|
|
178
207
|
# @!attribute [rw] multi_speaker_markup
|
|
179
208
|
# @return [::Google::Cloud::TextToSpeech::V1::MultiSpeakerMarkup]
|
|
180
209
|
# The multi-speaker input to be synthesized. Only applicable for
|
|
181
210
|
# multi-speaker synthesis.
|
|
182
211
|
#
|
|
183
|
-
# Note: The following fields are mutually exclusive: `multi_speaker_markup`, `text`, `ssml`. If a field in that set is populated, all other fields in the set will automatically be cleared.
|
|
212
|
+
# Note: The following fields are mutually exclusive: `multi_speaker_markup`, `text`, `markup`, `ssml`. If a field in that set is populated, all other fields in the set will automatically be cleared.
|
|
184
213
|
# @!attribute [rw] custom_pronunciations
|
|
185
214
|
# @return [::Google::Cloud::TextToSpeech::V1::CustomPronunciations]
|
|
186
215
|
# Optional. The pronunciation customizations are applied to the input. If
|
|
@@ -387,6 +416,14 @@ module Google
|
|
|
387
416
|
# The raw text to be synthesized. It is recommended that each input
|
|
388
417
|
# contains complete, terminating sentences, which results in better prosody
|
|
389
418
|
# in the output audio.
|
|
419
|
+
#
|
|
420
|
+
# Note: The following fields are mutually exclusive: `text`, `markup`. If a field in that set is populated, all other fields in the set will automatically be cleared.
|
|
421
|
+
# @!attribute [rw] markup
|
|
422
|
+
# @return [::String]
|
|
423
|
+
# Markup for HD voices specifically. This field may not be used with any
|
|
424
|
+
# other voices.
|
|
425
|
+
#
|
|
426
|
+
# Note: The following fields are mutually exclusive: `markup`, `text`. If a field in that set is populated, all other fields in the set will automatically be cleared.
|
|
390
427
|
class StreamingSynthesisInput
|
|
391
428
|
include ::Google::Protobuf::MessageExts
|
|
392
429
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: google-cloud-text_to_speech-v1
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 1.
|
|
4
|
+
version: 1.9.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Google LLC
|
|
@@ -13,22 +13,16 @@ dependencies:
|
|
|
13
13
|
name: gapic-common
|
|
14
14
|
requirement: !ruby/object:Gem::Requirement
|
|
15
15
|
requirements:
|
|
16
|
-
- - "
|
|
17
|
-
- !ruby/object:Gem::Version
|
|
18
|
-
version: 0.25.0
|
|
19
|
-
- - "<"
|
|
16
|
+
- - "~>"
|
|
20
17
|
- !ruby/object:Gem::Version
|
|
21
|
-
version:
|
|
18
|
+
version: '1.0'
|
|
22
19
|
type: :runtime
|
|
23
20
|
prerelease: false
|
|
24
21
|
version_requirements: !ruby/object:Gem::Requirement
|
|
25
22
|
requirements:
|
|
26
|
-
- - "
|
|
27
|
-
- !ruby/object:Gem::Version
|
|
28
|
-
version: 0.25.0
|
|
29
|
-
- - "<"
|
|
23
|
+
- - "~>"
|
|
30
24
|
- !ruby/object:Gem::Version
|
|
31
|
-
version:
|
|
25
|
+
version: '1.0'
|
|
32
26
|
- !ruby/object:Gem::Dependency
|
|
33
27
|
name: google-cloud-errors
|
|
34
28
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -105,7 +99,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
|
105
99
|
requirements:
|
|
106
100
|
- - ">="
|
|
107
101
|
- !ruby/object:Gem::Version
|
|
108
|
-
version: '3.
|
|
102
|
+
version: '3.1'
|
|
109
103
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
110
104
|
requirements:
|
|
111
105
|
- - ">="
|