google-cloud-text_to_speech-v1 1.9.0 → 1.11.0
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: 45f60fc6e395753db57e42bdc60759f3f14ed1c17d5fe7ed611fb0588ce60a43
|
|
4
|
+
data.tar.gz: b9c630c4a629ce3a1f9c5cb9953020747a2055db0362358666b716d107151a1d
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 5807d0d998036d5f26f6bb141aaa3b56d34bb4c0a51294c5c3fff8ae6b193222400f177d88132f40849a03a75c77cb076a010271a0244823ac279756000f1f12
|
|
7
|
+
data.tar.gz: 7a6ca1fddcc187af35785c0d048c5c597c2ee1802751174f036166e9d0335d233195c78294164609841ebf8fdd19a2dd3c09e3b8f2b00a9c0e5cc5685fd1eeb5
|
|
@@ -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\"\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\"\
|
|
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\"\x9c\x02\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\x12\x13\n\x06prompt\x18\x06 \x01(\tH\x01\x88\x01\x01\x12V\n\x15\x63ustom_pronunciations\x18\x03 \x01(\x0b\x32\x32.google.cloud.texttospeech.v1.CustomPronunciationsB\x03\xe0\x41\x01\x42\x0e\n\x0cinput_sourceB\t\n\x07_prompt\"\xae\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\x12\x17\n\nmodel_name\x18\x06 \x01(\tB\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\x12\x13\n\x06prompt\x18\x06 \x01(\tH\x01\x88\x01\x01\x42\x0e\n\x0cinput_sourceB\t\n\x07_prompt\"\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*{\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\x12\x07\n\x03M4A\x10\x08\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
|
|
|
@@ -210,6 +210,12 @@ module Google
|
|
|
210
210
|
# multi-speaker synthesis.
|
|
211
211
|
#
|
|
212
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.
|
|
213
|
+
# @!attribute [rw] prompt
|
|
214
|
+
# @return [::String]
|
|
215
|
+
# This system instruction is supported only for controllable/promptable voice
|
|
216
|
+
# models. If this system instruction is used, we pass the unedited text to
|
|
217
|
+
# Gemini-TTS. Otherwise, a default system instruction is used. AI Studio
|
|
218
|
+
# calls this system instruction, Style Instructions.
|
|
213
219
|
# @!attribute [rw] custom_pronunciations
|
|
214
220
|
# @return [::Google::Cloud::TextToSpeech::V1::CustomPronunciations]
|
|
215
221
|
# Optional. The pronunciation customizations are applied to the input. If
|
|
@@ -263,6 +269,10 @@ module Google
|
|
|
263
269
|
# Optional. The configuration for a voice clone. If
|
|
264
270
|
# [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
|
|
265
271
|
# clone matching the specified configuration.
|
|
272
|
+
# @!attribute [rw] model_name
|
|
273
|
+
# @return [::String]
|
|
274
|
+
# Optional. The name of the model. If set, the service will choose the model
|
|
275
|
+
# matching the specified configuration.
|
|
266
276
|
class VoiceSelectionParams
|
|
267
277
|
include ::Google::Protobuf::MessageExts
|
|
268
278
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
|
@@ -424,6 +434,9 @@ module Google
|
|
|
424
434
|
# other voices.
|
|
425
435
|
#
|
|
426
436
|
# 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.
|
|
437
|
+
# @!attribute [rw] prompt
|
|
438
|
+
# @return [::String]
|
|
439
|
+
# This is system instruction supported only for controllable voice models.
|
|
427
440
|
class StreamingSynthesisInput
|
|
428
441
|
include ::Google::Protobuf::MessageExts
|
|
429
442
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
|
@@ -486,7 +499,8 @@ module Google
|
|
|
486
499
|
# Configuration to set up audio encoder. The encoding determines the output
|
|
487
500
|
# audio format that we'd like.
|
|
488
501
|
module AudioEncoding
|
|
489
|
-
# Not specified.
|
|
502
|
+
# Not specified. Only used by GenerateVoiceCloningKey. Otherwise, will return
|
|
503
|
+
# result
|
|
490
504
|
# [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
|
|
491
505
|
AUDIO_ENCODING_UNSPECIFIED = 0
|
|
492
506
|
|
|
@@ -515,6 +529,9 @@ module Google
|
|
|
515
529
|
# Note that as opposed to LINEAR16, audio won't be wrapped in a WAV (or
|
|
516
530
|
# any other) header.
|
|
517
531
|
PCM = 7
|
|
532
|
+
|
|
533
|
+
# M4A audio.
|
|
534
|
+
M4A = 8
|
|
518
535
|
end
|
|
519
536
|
end
|
|
520
537
|
end
|
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: 1.11.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Google LLC
|
|
@@ -15,14 +15,14 @@ dependencies:
|
|
|
15
15
|
requirements:
|
|
16
16
|
- - "~>"
|
|
17
17
|
- !ruby/object:Gem::Version
|
|
18
|
-
version: '1.
|
|
18
|
+
version: '1.1'
|
|
19
19
|
type: :runtime
|
|
20
20
|
prerelease: false
|
|
21
21
|
version_requirements: !ruby/object:Gem::Requirement
|
|
22
22
|
requirements:
|
|
23
23
|
- - "~>"
|
|
24
24
|
- !ruby/object:Gem::Version
|
|
25
|
-
version: '1.
|
|
25
|
+
version: '1.1'
|
|
26
26
|
- !ruby/object:Gem::Dependency
|
|
27
27
|
name: google-cloud-errors
|
|
28
28
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -106,7 +106,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
106
106
|
- !ruby/object:Gem::Version
|
|
107
107
|
version: '0'
|
|
108
108
|
requirements: []
|
|
109
|
-
rubygems_version: 3.6.
|
|
109
|
+
rubygems_version: 3.6.9
|
|
110
110
|
specification_version: 4
|
|
111
111
|
summary: Synthesizes natural-sounding speech by applying powerful neural network models.
|
|
112
112
|
test_files: []
|