google-cloud-text_to_speech-v1beta1 0.2.3 → 0.3.0

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: 00366b876bfb6a9078deac6b3725db8e4b44c2baf45ce1a4cf6a562e5fdbb4dd
4
- data.tar.gz: 1b59de686c925420788284f07e4d025bb7451ca45c135a80d4cf49cda5df92ea
3
+ metadata.gz: de2de106cdd7284b300a3b37e46ca094e7eda1f041e1575e79aeea63380b7252
4
+ data.tar.gz: 8c72cd39142518547a5eeadc9c60364a8c71c24554be82e0d3747ea7970a9182
5
5
  SHA512:
6
- metadata.gz: b0d0c3981d85933c2e4ebd4ca799a65b5ee71f8f71765331a813eedcad92f22990baadf8542a0020fe85809b310206897d5a604ba5e75de2230a9af37ea11d7b
7
- data.tar.gz: 79f721b47f972cf1acde328c18d7e9272c5c711a6cc8a7988fe646a6e8e3c1d2240f11bbbff521469dd501f76fa9baf1fc6034ba29861d4fd7868064cc68eabd
6
+ metadata.gz: 0342e5eb764967a9af77ed71912931208ffcfe1e8f711e0728a5fa7b816cf2c85cb91b3923bf70f65e2ba6224e6a389a95fdad182523be4b80ea51d6f00f4b44
7
+ data.tar.gz: 3c106c4f18e0581e7222ebe96dc33911b66db72647ef9031c74a4a8bc68ecb42ac4aba92dfa0faacd727abbe6e41128f739e31478ce05f5f99662a0559f2aa12
@@ -63,20 +63,12 @@ module Google
63
63
  end
64
64
  default_config = Client::Configuration.new parent_config
65
65
 
66
- default_config.rpcs.list_voices.timeout = 600.0
67
- default_config.rpcs.list_voices.retry_policy = {
66
+ default_config.timeout = 300.0
67
+ default_config.retry_policy = {
68
68
  initial_delay: 0.1,
69
69
  max_delay: 60.0,
70
70
  multiplier: 1.3,
71
- retry_codes: ["UNAVAILABLE", "DEADLINE_EXCEEDED"]
72
- }
73
-
74
- default_config.rpcs.synthesize_speech.timeout = 600.0
75
- default_config.rpcs.synthesize_speech.retry_policy = {
76
- initial_delay: 0.1,
77
- max_delay: 60.0,
78
- multiplier: 1.3,
79
- retry_codes: ["UNAVAILABLE", "DEADLINE_EXCEEDED"]
71
+ retry_codes: [14, 4]
80
72
  }
81
73
 
82
74
  default_config
@@ -239,7 +231,7 @@ module Google
239
231
  # @param options [::Gapic::CallOptions, ::Hash]
240
232
  # Overrides the default settings for this call, e.g, timeout, retries, etc. Optional.
241
233
  #
242
- # @overload synthesize_speech(input: nil, voice: nil, audio_config: nil)
234
+ # @overload synthesize_speech(input: nil, voice: nil, audio_config: nil, enable_time_pointing: nil)
243
235
  # Pass arguments to `synthesize_speech` via keyword arguments. Note that at
244
236
  # least one keyword argument is required. To specify no parameters, or to keep all
245
237
  # the default parameter values, pass an empty Hash as a request object (see above).
@@ -250,6 +242,8 @@ module Google
250
242
  # Required. The desired voice of the synthesized audio.
251
243
  # @param audio_config [::Google::Cloud::TextToSpeech::V1beta1::AudioConfig, ::Hash]
252
244
  # Required. The configuration of the synthesized audio.
245
+ # @param enable_time_pointing [::Array<::Google::Cloud::TextToSpeech::V1beta1::SynthesizeSpeechRequest::TimepointType>]
246
+ # Whether and what timepoints should be returned in the response.
253
247
  #
254
248
  # @yield [response, operation] Access the result along with the RPC operation
255
249
  # @yieldparam response [::Google::Cloud::TextToSpeech::V1beta1::SynthesizeSpeechResponse]
@@ -21,7 +21,7 @@ module Google
21
21
  module Cloud
22
22
  module TextToSpeech
23
23
  module V1beta1
24
- VERSION = "0.2.3"
24
+ VERSION = "0.3.0"
25
25
  end
26
26
  end
27
27
  end
@@ -24,6 +24,11 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
24
24
  optional :input, :message, 1, "google.cloud.texttospeech.v1beta1.SynthesisInput"
25
25
  optional :voice, :message, 2, "google.cloud.texttospeech.v1beta1.VoiceSelectionParams"
26
26
  optional :audio_config, :message, 3, "google.cloud.texttospeech.v1beta1.AudioConfig"
27
+ repeated :enable_time_pointing, :enum, 4, "google.cloud.texttospeech.v1beta1.SynthesizeSpeechRequest.TimepointType"
28
+ end
29
+ add_enum "google.cloud.texttospeech.v1beta1.SynthesizeSpeechRequest.TimepointType" do
30
+ value :TIMEPOINT_TYPE_UNSPECIFIED, 0
31
+ value :SSML_MARK, 1
27
32
  end
28
33
  add_message "google.cloud.texttospeech.v1beta1.SynthesisInput" do
29
34
  oneof :input_source do
@@ -46,6 +51,12 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
46
51
  end
47
52
  add_message "google.cloud.texttospeech.v1beta1.SynthesizeSpeechResponse" do
48
53
  optional :audio_content, :bytes, 1
54
+ repeated :timepoints, :message, 2, "google.cloud.texttospeech.v1beta1.Timepoint"
55
+ optional :audio_config, :message, 4, "google.cloud.texttospeech.v1beta1.AudioConfig"
56
+ end
57
+ add_message "google.cloud.texttospeech.v1beta1.Timepoint" do
58
+ optional :mark_name, :string, 4
59
+ optional :time_seconds, :double, 3
49
60
  end
50
61
  add_enum "google.cloud.texttospeech.v1beta1.SsmlVoiceGender" do
51
62
  value :SSML_VOICE_GENDER_UNSPECIFIED, 0
@@ -57,7 +68,9 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
57
68
  value :AUDIO_ENCODING_UNSPECIFIED, 0
58
69
  value :LINEAR16, 1
59
70
  value :MP3, 2
71
+ value :MP3_64_KBPS, 4
60
72
  value :OGG_OPUS, 3
73
+ value :MULAW, 5
61
74
  end
62
75
  end
63
76
  end
@@ -70,10 +83,12 @@ module Google
70
83
  ListVoicesResponse = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.texttospeech.v1beta1.ListVoicesResponse").msgclass
71
84
  Voice = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.texttospeech.v1beta1.Voice").msgclass
72
85
  SynthesizeSpeechRequest = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.texttospeech.v1beta1.SynthesizeSpeechRequest").msgclass
86
+ SynthesizeSpeechRequest::TimepointType = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.texttospeech.v1beta1.SynthesizeSpeechRequest.TimepointType").enummodule
73
87
  SynthesisInput = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.texttospeech.v1beta1.SynthesisInput").msgclass
74
88
  VoiceSelectionParams = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.texttospeech.v1beta1.VoiceSelectionParams").msgclass
75
89
  AudioConfig = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.texttospeech.v1beta1.AudioConfig").msgclass
76
90
  SynthesizeSpeechResponse = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.texttospeech.v1beta1.SynthesizeSpeechResponse").msgclass
91
+ Timepoint = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.texttospeech.v1beta1.Timepoint").msgclass
77
92
  SsmlVoiceGender = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.texttospeech.v1beta1.SsmlVoiceGender").enummodule
78
93
  AudioEncoding = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.texttospeech.v1beta1.AudioEncoding").enummodule
79
94
  end
@@ -15,7 +15,6 @@
15
15
  # See the License for the specific language governing permissions and
16
16
  # limitations under the License.
17
17
  #
18
- #
19
18
 
20
19
  require 'grpc'
21
20
  require 'google/cloud/texttospeech/v1beta1/cloud_tts_pb'
@@ -76,9 +76,21 @@ module Google
76
76
  # @!attribute [rw] audio_config
77
77
  # @return [::Google::Cloud::TextToSpeech::V1beta1::AudioConfig]
78
78
  # Required. The configuration of the synthesized audio.
79
+ # @!attribute [rw] enable_time_pointing
80
+ # @return [::Array<::Google::Cloud::TextToSpeech::V1beta1::SynthesizeSpeechRequest::TimepointType>]
81
+ # Whether and what timepoints should be returned in the response.
79
82
  class SynthesizeSpeechRequest
80
83
  include ::Google::Protobuf::MessageExts
81
84
  extend ::Google::Protobuf::MessageExts::ClassMethods
85
+
86
+ # The type of timepoint information that is returned in the response.
87
+ module TimepointType
88
+ # Not specified. No timepoint information will be returned.
89
+ TIMEPOINT_TYPE_UNSPECIFIED = 0
90
+
91
+ # Timepoint information of `<mark>` tags in SSML input will be returned.
92
+ SSML_MARK = 1
93
+ end
82
94
  end
83
95
 
84
96
  # Contains text input to be synthesized. Either `text` or `ssml` must be
@@ -184,11 +196,31 @@ module Google
184
196
  # For LINEAR16 audio, we include the WAV header. Note: as
185
197
  # with all bytes fields, protobuffers use a pure binary representation,
186
198
  # whereas JSON representations use base64.
199
+ # @!attribute [rw] timepoints
200
+ # @return [::Array<::Google::Cloud::TextToSpeech::V1beta1::Timepoint>]
201
+ # A link between a position in the original request input and a corresponding
202
+ # time in the output audio. It's only supported via `<mark>` of SSML input.
203
+ # @!attribute [rw] audio_config
204
+ # @return [::Google::Cloud::TextToSpeech::V1beta1::AudioConfig]
205
+ # The audio metadata of `audio_content`.
187
206
  class SynthesizeSpeechResponse
188
207
  include ::Google::Protobuf::MessageExts
189
208
  extend ::Google::Protobuf::MessageExts::ClassMethods
190
209
  end
191
210
 
211
+ # This contains a mapping between a certain point in the input text and a
212
+ # corresponding time in the output audio.
213
+ # @!attribute [rw] mark_name
214
+ # @return [::String]
215
+ # Timepoint name as received from the client within `<mark>` tag.
216
+ # @!attribute [rw] time_seconds
217
+ # @return [::Float]
218
+ # Time offset in seconds from the start of the synthesized audio.
219
+ class Timepoint
220
+ include ::Google::Protobuf::MessageExts
221
+ extend ::Google::Protobuf::MessageExts::ClassMethods
222
+ end
223
+
192
224
  # Gender of the voice as described in
193
225
  # [SSML voice element](https://www.w3.org/TR/speech-synthesis11/#edef_voice).
194
226
  module SsmlVoiceGender
@@ -205,7 +237,7 @@ module Google
205
237
  # A female voice.
206
238
  FEMALE = 2
207
239
 
208
- # A gender-neutral voice.
240
+ # A gender-neutral voice. This voice is not yet supported.
209
241
  NEUTRAL = 3
210
242
  end
211
243
 
@@ -222,11 +254,18 @@ module Google
222
254
  # MP3 audio at 32kbps.
223
255
  MP3 = 2
224
256
 
257
+ # MP3 at 64kbps.
258
+ MP3_64_KBPS = 4
259
+
225
260
  # Opus encoded audio wrapped in an ogg container. The result will be a
226
261
  # file which can be played natively on Android, and in browsers (at least
227
262
  # Chrome and Firefox). The quality of the encoding is considerably higher
228
263
  # than MP3 while using approximately the same bitrate.
229
264
  OGG_OPUS = 3
265
+
266
+ # 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
267
+ # Audio content returned as MULAW also contains a WAV header.
268
+ MULAW = 5
230
269
  end
231
270
  end
232
271
  end
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: google-cloud-text_to_speech-v1beta1
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.2.3
4
+ version: 0.3.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - Google LLC
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2020-06-18 00:00:00.000000000 Z
11
+ date: 2020-08-06 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: gapic-common
@@ -16,14 +16,14 @@ dependencies:
16
16
  requirements:
17
17
  - - "~>"
18
18
  - !ruby/object:Gem::Version
19
- version: '0.2'
19
+ version: '0.3'
20
20
  type: :runtime
21
21
  prerelease: false
22
22
  version_requirements: !ruby/object:Gem::Requirement
23
23
  requirements:
24
24
  - - "~>"
25
25
  - !ruby/object:Gem::Version
26
- version: '0.2'
26
+ version: '0.3'
27
27
  - !ruby/object:Gem::Dependency
28
28
  name: google-cloud-errors
29
29
  requirement: !ruby/object:Gem::Requirement