google-cloud-text_to_speech-v1 1.7.0 → 1.8.0
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 +4 -4
- data/lib/google/cloud/text_to_speech/v1/text_to_speech/client.rb +1 -1
- data/lib/google/cloud/text_to_speech/v1/version.rb +1 -1
- data/lib/google/cloud/texttospeech/v1/cloud_tts_pb.rb +1 -1
- data/lib/google/cloud/texttospeech/v1/cloud_tts_services_pb.rb +1 -1
- data/proto_docs/google/api/client.rb +14 -0
- data/proto_docs/google/cloud/texttospeech/v1/cloud_tts.rb +42 -27
- metadata +3 -3
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: b7e9240dceda6bf908d94f65b448935cc8c461f70a4e54bc738349f07ef084b4
|
|
4
|
+
data.tar.gz: 554a40bf73b61daa66adfc7c2aafa1eecb22a3645d9c5defa24248580c1d6b8d
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: a16ef899a14b5235338ca3251d5d7a15a44f1d0f2888cb8ce34669237b7ea2903125c7a6869ef330dee3126693599463a6110b8fd4499239a2d848425f235703
|
|
7
|
+
data.tar.gz: 9baec37bd4e40b201df870e56554df95922f8ec30bcede2dbea043cd705d432f8d2c04b756dc7c308f3c44e448c97da44ff7f59a5809d7be18f9d53fe54984c8
|
|
@@ -357,7 +357,7 @@ module Google
|
|
|
357
357
|
end
|
|
358
358
|
|
|
359
359
|
##
|
|
360
|
-
# Performs bidirectional streaming speech synthesis:
|
|
360
|
+
# Performs bidirectional streaming speech synthesis: receives audio while
|
|
361
361
|
# sending text.
|
|
362
362
|
#
|
|
363
363
|
# @param request [::Gapic::StreamInput, ::Enumerable<::Google::Cloud::TextToSpeech::V1::StreamingSynthesizeRequest, ::Hash>]
|
|
@@ -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\"\xda\x02\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\"o\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\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\"\xea\x01\n\x0eSynthesisInput\x12\x0e\n\x04text\x18\x01 \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\"\
|
|
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\"\xda\x02\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\"o\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\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\"\xea\x01\n\x0eSynthesisInput\x12\x0e\n\x04text\x18\x01 \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\"9\n\x17StreamingSynthesisInput\x12\x0e\n\x04text\x18\x01 \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
|
|
|
@@ -38,7 +38,7 @@ module Google
|
|
|
38
38
|
# Synthesizes speech synchronously: receive results after all text input
|
|
39
39
|
# has been processed.
|
|
40
40
|
rpc :SynthesizeSpeech, ::Google::Cloud::TextToSpeech::V1::SynthesizeSpeechRequest, ::Google::Cloud::TextToSpeech::V1::SynthesizeSpeechResponse
|
|
41
|
-
# Performs bidirectional streaming speech synthesis:
|
|
41
|
+
# Performs bidirectional streaming speech synthesis: receives audio while
|
|
42
42
|
# sending text.
|
|
43
43
|
rpc :StreamingSynthesize, stream(::Google::Cloud::TextToSpeech::V1::StreamingSynthesizeRequest), stream(::Google::Cloud::TextToSpeech::V1::StreamingSynthesizeResponse)
|
|
44
44
|
end
|
|
@@ -221,6 +221,12 @@ module Google
|
|
|
221
221
|
# Pythonic which are included in `protobuf>=5.29.x`. This feature will be
|
|
222
222
|
# enabled by default 1 month after launching the feature in preview
|
|
223
223
|
# packages.
|
|
224
|
+
# @!attribute [rw] unversioned_package_disabled
|
|
225
|
+
# @return [::Boolean]
|
|
226
|
+
# Disables generation of an unversioned Python package for this client
|
|
227
|
+
# library. This means that the module names will need to be versioned in
|
|
228
|
+
# import statements. For example `import google.cloud.library_v2` instead
|
|
229
|
+
# of `import google.cloud.library`.
|
|
224
230
|
class ExperimentalFeatures
|
|
225
231
|
include ::Google::Protobuf::MessageExts
|
|
226
232
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
|
@@ -409,6 +415,14 @@ module Google
|
|
|
409
415
|
# @return [::Array<::String>]
|
|
410
416
|
# An allowlist of the fully qualified names of RPCs that should be included
|
|
411
417
|
# on public client surfaces.
|
|
418
|
+
# @!attribute [rw] generate_omitted_as_internal
|
|
419
|
+
# @return [::Boolean]
|
|
420
|
+
# Setting this to true indicates to the client generators that methods
|
|
421
|
+
# that would be excluded from the generation should instead be generated
|
|
422
|
+
# in a way that indicates these methods should not be consumed by
|
|
423
|
+
# end users. How this is expressed is up to individual language
|
|
424
|
+
# implementations to decide. Some examples may be: added annotations,
|
|
425
|
+
# obfuscated identifiers, or other language idiomatic patterns.
|
|
412
426
|
class SelectiveGapicGeneration
|
|
413
427
|
include ::Google::Protobuf::MessageExts
|
|
414
428
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
|
@@ -69,8 +69,8 @@ module Google
|
|
|
69
69
|
# Used for advanced voice options.
|
|
70
70
|
# @!attribute [rw] low_latency_journey_synthesis
|
|
71
71
|
# @return [::Boolean]
|
|
72
|
-
# Only for Journey voices. If false, the synthesis
|
|
73
|
-
# and
|
|
72
|
+
# Only for Journey voices. If false, the synthesis is context aware
|
|
73
|
+
# and has a higher latency.
|
|
74
74
|
class AdvancedVoiceOptions
|
|
75
75
|
include ::Google::Protobuf::MessageExts
|
|
76
76
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
|
@@ -97,9 +97,9 @@ module Google
|
|
|
97
97
|
# Pronunciation customization for a phrase.
|
|
98
98
|
# @!attribute [rw] phrase
|
|
99
99
|
# @return [::String]
|
|
100
|
-
# The phrase to which the customization
|
|
101
|
-
# The phrase can be multiple words
|
|
102
|
-
#
|
|
100
|
+
# The phrase to which the customization is applied.
|
|
101
|
+
# The phrase can be multiple words, such as proper nouns, but shouldn't span
|
|
102
|
+
# the length of the sentence.
|
|
103
103
|
# @!attribute [rw] phonetic_encoding
|
|
104
104
|
# @return [::Google::Cloud::TextToSpeech::V1::CustomPronunciationParams::PhoneticEncoding]
|
|
105
105
|
# The phonetic encoding of the phrase.
|
|
@@ -116,11 +116,11 @@ module Google
|
|
|
116
116
|
# Not specified.
|
|
117
117
|
PHONETIC_ENCODING_UNSPECIFIED = 0
|
|
118
118
|
|
|
119
|
-
# IPA
|
|
119
|
+
# IPA, such as apple -> ˈæpəl.
|
|
120
120
|
# https://en.wikipedia.org/wiki/International_Phonetic_Alphabet
|
|
121
121
|
PHONETIC_ENCODING_IPA = 1
|
|
122
122
|
|
|
123
|
-
# X-SAMPA
|
|
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
126
|
end
|
|
@@ -129,7 +129,7 @@ module Google
|
|
|
129
129
|
# A collection of pronunciation customizations.
|
|
130
130
|
# @!attribute [rw] pronunciations
|
|
131
131
|
# @return [::Array<::Google::Cloud::TextToSpeech::V1::CustomPronunciationParams>]
|
|
132
|
-
# The pronunciation customizations
|
|
132
|
+
# The pronunciation customizations are applied.
|
|
133
133
|
class CustomPronunciations
|
|
134
134
|
include ::Google::Protobuf::MessageExts
|
|
135
135
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
|
@@ -143,7 +143,7 @@ module Google
|
|
|
143
143
|
include ::Google::Protobuf::MessageExts
|
|
144
144
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
|
145
145
|
|
|
146
|
-
# A
|
|
146
|
+
# A multi-speaker turn.
|
|
147
147
|
# @!attribute [rw] speaker
|
|
148
148
|
# @return [::String]
|
|
149
149
|
# Required. The speaker of the turn, for example, 'O' or 'Q'. Please refer
|
|
@@ -183,18 +183,16 @@ module Google
|
|
|
183
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.
|
|
184
184
|
# @!attribute [rw] custom_pronunciations
|
|
185
185
|
# @return [::Google::Cloud::TextToSpeech::V1::CustomPronunciations]
|
|
186
|
-
# Optional. The pronunciation customizations
|
|
187
|
-
# this is set, the input
|
|
186
|
+
# Optional. The pronunciation customizations are applied to the input. If
|
|
187
|
+
# this is set, the input is synthesized using the given pronunciation
|
|
188
188
|
# customizations.
|
|
189
189
|
#
|
|
190
|
-
# The initial support
|
|
191
|
-
#
|
|
192
|
-
# VoiceSelectionParams. Journey and Instant Clone voices are
|
|
193
|
-
# not supported yet.
|
|
190
|
+
# The initial support is for en-us, with plans to expand to other locales in
|
|
191
|
+
# the future. Instant Clone voices aren't supported.
|
|
194
192
|
#
|
|
195
193
|
# In order to customize the pronunciation of a phrase, there must be an exact
|
|
196
194
|
# match of the phrase in the input types. If using SSML, the phrase must not
|
|
197
|
-
# be inside a phoneme tag
|
|
195
|
+
# be inside a phoneme tag.
|
|
198
196
|
class SynthesisInput
|
|
199
197
|
include ::Google::Protobuf::MessageExts
|
|
200
198
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
|
@@ -234,8 +232,8 @@ module Google
|
|
|
234
232
|
# @!attribute [rw] voice_clone
|
|
235
233
|
# @return [::Google::Cloud::TextToSpeech::V1::VoiceCloneParams]
|
|
236
234
|
# Optional. The configuration for a voice clone. If
|
|
237
|
-
# [VoiceCloneParams.voice_clone_key] is set, the service
|
|
238
|
-
#
|
|
235
|
+
# [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
|
|
236
|
+
# clone matching the specified configuration.
|
|
239
237
|
class VoiceSelectionParams
|
|
240
238
|
include ::Google::Protobuf::MessageExts
|
|
241
239
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
|
@@ -247,10 +245,10 @@ module Google
|
|
|
247
245
|
# Required. The format of the audio byte stream.
|
|
248
246
|
# @!attribute [rw] speaking_rate
|
|
249
247
|
# @return [::Float]
|
|
250
|
-
# Optional. Input only. Speaking rate/speed, in the range [0.25,
|
|
248
|
+
# Optional. Input only. Speaking rate/speed, in the range [0.25, 2.0]. 1.0 is
|
|
251
249
|
# the normal native speed supported by the specific voice. 2.0 is twice as
|
|
252
250
|
# fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
|
|
253
|
-
# speed. Any other values < 0.25 or >
|
|
251
|
+
# speed. Any other values < 0.25 or > 2.0 will return an error.
|
|
254
252
|
# @!attribute [rw] pitch
|
|
255
253
|
# @return [::Float]
|
|
256
254
|
# Optional. Input only. Speaking pitch, in the range [-20.0, 20.0]. 20 means
|
|
@@ -343,11 +341,17 @@ module Google
|
|
|
343
341
|
# @!attribute [rw] audio_encoding
|
|
344
342
|
# @return [::Google::Cloud::TextToSpeech::V1::AudioEncoding]
|
|
345
343
|
# Required. The format of the audio byte stream.
|
|
346
|
-
#
|
|
347
|
-
#
|
|
344
|
+
# Streaming supports PCM, ALAW, MULAW and OGG_OPUS. All other encodings
|
|
345
|
+
# return an error.
|
|
348
346
|
# @!attribute [rw] sample_rate_hertz
|
|
349
347
|
# @return [::Integer]
|
|
350
348
|
# Optional. The synthesis sample rate (in hertz) for this audio.
|
|
349
|
+
# @!attribute [rw] speaking_rate
|
|
350
|
+
# @return [::Float]
|
|
351
|
+
# Optional. Input only. Speaking rate/speed, in the range [0.25, 2.0]. 1.0 is
|
|
352
|
+
# the normal native speed supported by the specific voice. 2.0 is twice as
|
|
353
|
+
# fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
|
|
354
|
+
# speed. Any other values < 0.25 or > 2.0 will return an error.
|
|
351
355
|
class StreamingAudioConfig
|
|
352
356
|
include ::Google::Protobuf::MessageExts
|
|
353
357
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
|
@@ -360,6 +364,18 @@ module Google
|
|
|
360
364
|
# @!attribute [rw] streaming_audio_config
|
|
361
365
|
# @return [::Google::Cloud::TextToSpeech::V1::StreamingAudioConfig]
|
|
362
366
|
# Optional. The configuration of the synthesized audio.
|
|
367
|
+
# @!attribute [rw] custom_pronunciations
|
|
368
|
+
# @return [::Google::Cloud::TextToSpeech::V1::CustomPronunciations]
|
|
369
|
+
# Optional. The pronunciation customizations are applied to the input. If
|
|
370
|
+
# this is set, the input is synthesized using the given pronunciation
|
|
371
|
+
# customizations.
|
|
372
|
+
#
|
|
373
|
+
# The initial support is for en-us, with plans to expand to other locales in
|
|
374
|
+
# the future. Instant Clone voices aren't supported.
|
|
375
|
+
#
|
|
376
|
+
# In order to customize the pronunciation of a phrase, there must be an exact
|
|
377
|
+
# match of the phrase in the input types. If using SSML, the phrase must not
|
|
378
|
+
# be inside a phoneme tag.
|
|
363
379
|
class StreamingSynthesizeConfig
|
|
364
380
|
include ::Google::Protobuf::MessageExts
|
|
365
381
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
|
@@ -369,9 +385,8 @@ module Google
|
|
|
369
385
|
# @!attribute [rw] text
|
|
370
386
|
# @return [::String]
|
|
371
387
|
# The raw text to be synthesized. It is recommended that each input
|
|
372
|
-
# contains complete, terminating sentences,
|
|
373
|
-
#
|
|
374
|
-
# input text however they please.
|
|
388
|
+
# contains complete, terminating sentences, which results in better prosody
|
|
389
|
+
# in the output audio.
|
|
375
390
|
class StreamingSynthesisInput
|
|
376
391
|
include ::Google::Protobuf::MessageExts
|
|
377
392
|
extend ::Google::Protobuf::MessageExts::ClassMethods
|
|
@@ -445,7 +460,7 @@ module Google
|
|
|
445
460
|
# MP3 audio at 32kbps.
|
|
446
461
|
MP3 = 2
|
|
447
462
|
|
|
448
|
-
# Opus encoded audio wrapped in an ogg container. The result
|
|
463
|
+
# Opus encoded audio wrapped in an ogg container. The result is a
|
|
449
464
|
# file which can be played natively on Android, and in browsers (at least
|
|
450
465
|
# Chrome and Firefox). The quality of the encoding is considerably higher
|
|
451
466
|
# than MP3 while using approximately the same bitrate.
|
|
@@ -460,7 +475,7 @@ module Google
|
|
|
460
475
|
ALAW = 6
|
|
461
476
|
|
|
462
477
|
# Uncompressed 16-bit signed little-endian samples (Linear PCM).
|
|
463
|
-
# Note that as opposed to LINEAR16, audio
|
|
478
|
+
# Note that as opposed to LINEAR16, audio won't be wrapped in a WAV (or
|
|
464
479
|
# any other) header.
|
|
465
480
|
PCM = 7
|
|
466
481
|
end
|
metadata
CHANGED
|
@@ -1,13 +1,13 @@
|
|
|
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: 1.8.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Google LLC
|
|
8
8
|
bindir: bin
|
|
9
9
|
cert_chain: []
|
|
10
|
-
date: 2025-
|
|
10
|
+
date: 2025-04-18 00:00:00.000000000 Z
|
|
11
11
|
dependencies:
|
|
12
12
|
- !ruby/object:Gem::Dependency
|
|
13
13
|
name: gapic-common
|
|
@@ -112,7 +112,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
112
112
|
- !ruby/object:Gem::Version
|
|
113
113
|
version: '0'
|
|
114
114
|
requirements: []
|
|
115
|
-
rubygems_version: 3.6.
|
|
115
|
+
rubygems_version: 3.6.5
|
|
116
116
|
specification_version: 4
|
|
117
117
|
summary: Synthesizes natural-sounding speech by applying powerful neural network models.
|
|
118
118
|
test_files: []
|