google-cloud-text_to_speech-v1beta1 0.22.0 → 0.23.0
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: da36d2f04005aeb45395f1e1017cfa2936e3eb58baf6a422509c36c4b1ea329c
|
4
|
+
data.tar.gz: 8a8a9896e4c544b385ce075b10e0c34cd6d29e3f72ce87a462f6573e89bc3556
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8048983c7eb0224c43e5b1675c9f1a5f58f81d80689ac8bd4d91769dfb94a8da08f1a843583ac01334288dda63dc772e736667090358f1fc7fe227e9032a366d
|
7
|
+
data.tar.gz: 10967f02b7bdaaa17da061382e052a75936eaa717d5e56462d58e0c4fa1d7a75dea99dfd7d3372389522ff7b04439c5d800194006c9ccb2be281f8466944681f
|
@@ -10,7 +10,7 @@ require 'google/api/field_behavior_pb'
|
|
10
10
|
require 'google/api/resource_pb'
|
11
11
|
|
12
12
|
|
13
|
-
descriptor_data = "\n1google/cloud/texttospeech/v1beta1/cloud_tts.proto\x12!google.cloud.texttospeech.v1beta1\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\"N\n\x12ListVoicesResponse\x12\x38\n\x06voices\x18\x01 \x03(\x0b\x32(.google.cloud.texttospeech.v1beta1.Voice\"\x99\x01\n\x05Voice\x12\x16\n\x0elanguage_codes\x18\x01 \x03(\t\x12\x0c\n\x04name\x18\x02 \x01(\t\x12G\n\x0bssml_gender\x18\x03 \x01(\x0e\x32\x32.google.cloud.texttospeech.v1beta1.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\"\x99\x04\n\x17SynthesizeSpeechRequest\x12\x45\n\x05input\x18\x01 \x01(\x0b\x32\x31.google.cloud.texttospeech.v1beta1.SynthesisInputB\x03\xe0\x41\x02\x12K\n\x05voice\x18\x02 \x01(\x0b\x32\x37.google.cloud.texttospeech.v1beta1.VoiceSelectionParamsB\x03\xe0\x41\x02\x12I\n\x0c\x61udio_config\x18\x03 \x01(\x0b\x32..google.cloud.texttospeech.v1beta1.AudioConfigB\x03\xe0\x41\x02\x12\x66\n\x14\x65nable_time_pointing\x18\x04 \x03(\x0e\x32H.google.cloud.texttospeech.v1beta1.SynthesizeSpeechRequest.TimepointType\x12\\\n\x16\x61\x64vanced_voice_options\x18\x08 \x01(\x0b\x32\x37.google.cloud.texttospeech.v1beta1.AdvancedVoiceOptionsH\x00\x88\x01\x01\">\n\rTimepointType\x12\x1e\n\x1aTIMEPOINT_TYPE_UNSPECIFIED\x10\x00\x12\r\n\tSSML_MARK\x10\x01\x42\x19\n\x17_advanced_voice_options\"\xa7\x03\n\x19\x43ustomPronunciationParams\x12\x13\n\x06phrase\x18\x01 \x01(\tH\x00\x88\x01\x01\x12m\n\x11phonetic_encoding\x18\x02 \x01(\x0e\x32M.google.cloud.texttospeech.v1beta1.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\"l\n\x14\x43ustomPronunciations\x12T\n\x0epronunciations\x18\x01 \x03(\x0b\x32<.google.cloud.texttospeech.v1beta1.CustomPronunciationParams\"\x95\x01\n\x12MultiSpeakerMarkup\x12N\n\x05turns\x18\x01 \x03(\x0b\x32:.google.cloud.texttospeech.v1beta1.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 = "\n1google/cloud/texttospeech/v1beta1/cloud_tts.proto\x12!google.cloud.texttospeech.v1beta1\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\"N\n\x12ListVoicesResponse\x12\x38\n\x06voices\x18\x01 \x03(\x0b\x32(.google.cloud.texttospeech.v1beta1.Voice\"\x99\x01\n\x05Voice\x12\x16\n\x0elanguage_codes\x18\x01 \x03(\t\x12\x0c\n\x04name\x18\x02 \x01(\t\x12G\n\x0bssml_gender\x18\x03 \x01(\x0e\x32\x32.google.cloud.texttospeech.v1beta1.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\"\x99\x04\n\x17SynthesizeSpeechRequest\x12\x45\n\x05input\x18\x01 \x01(\x0b\x32\x31.google.cloud.texttospeech.v1beta1.SynthesisInputB\x03\xe0\x41\x02\x12K\n\x05voice\x18\x02 \x01(\x0b\x32\x37.google.cloud.texttospeech.v1beta1.VoiceSelectionParamsB\x03\xe0\x41\x02\x12I\n\x0c\x61udio_config\x18\x03 \x01(\x0b\x32..google.cloud.texttospeech.v1beta1.AudioConfigB\x03\xe0\x41\x02\x12\x66\n\x14\x65nable_time_pointing\x18\x04 \x03(\x0e\x32H.google.cloud.texttospeech.v1beta1.SynthesizeSpeechRequest.TimepointType\x12\\\n\x16\x61\x64vanced_voice_options\x18\x08 \x01(\x0b\x32\x37.google.cloud.texttospeech.v1beta1.AdvancedVoiceOptionsH\x00\x88\x01\x01\">\n\rTimepointType\x12\x1e\n\x1aTIMEPOINT_TYPE_UNSPECIFIED\x10\x00\x12\r\n\tSSML_MARK\x10\x01\x42\x19\n\x17_advanced_voice_options\"\xa7\x03\n\x19\x43ustomPronunciationParams\x12\x13\n\x06phrase\x18\x01 \x01(\tH\x00\x88\x01\x01\x12m\n\x11phonetic_encoding\x18\x02 \x01(\x0e\x32M.google.cloud.texttospeech.v1beta1.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\"l\n\x14\x43ustomPronunciations\x12T\n\x0epronunciations\x18\x01 \x03(\x0b\x32<.google.cloud.texttospeech.v1beta1.CustomPronunciationParams\"\x95\x01\n\x12MultiSpeakerMarkup\x12N\n\x05turns\x18\x01 \x03(\x0b\x32:.google.cloud.texttospeech.v1beta1.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\"\xa6\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\x12U\n\x14multi_speaker_markup\x18\x04 \x01(\x0b\x32\x35.google.cloud.texttospeech.v1beta1.MultiSpeakerMarkupH\x00\x12\x13\n\x06prompt\x18\x06 \x01(\tH\x01\x88\x01\x01\x12[\n\x15\x63ustom_pronunciations\x18\x03 \x01(\x0b\x32\x37.google.cloud.texttospeech.v1beta1.CustomPronunciationsB\x03\xe0\x41\x01\x42\x0e\n\x0cinput_sourceB\t\n\x07_prompt\"\xbd\x02\n\x14VoiceSelectionParams\x12\x1a\n\rlanguage_code\x18\x01 \x01(\tB\x03\xe0\x41\x02\x12\x0c\n\x04name\x18\x02 \x01(\t\x12G\n\x0bssml_gender\x18\x03 \x01(\x0e\x32\x32.google.cloud.texttospeech.v1beta1.SsmlVoiceGender\x12J\n\x0c\x63ustom_voice\x18\x04 \x01(\x0b\x32\x34.google.cloud.texttospeech.v1beta1.CustomVoiceParams\x12M\n\x0bvoice_clone\x18\x05 \x01(\x0b\x32\x33.google.cloud.texttospeech.v1beta1.VoiceCloneParamsB\x03\xe0\x41\x01\x12\x17\n\nmodel_name\x18\x06 \x01(\tB\x03\xe0\x41\x01\"\xf6\x01\n\x0b\x41udioConfig\x12M\n\x0e\x61udio_encoding\x18\x01 \x01(\x0e\x32\x30.google.cloud.texttospeech.v1beta1.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\"\xf6\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\x61\n\x0ereported_usage\x18\x03 \x01(\x0e\x32\x42.google.cloud.texttospeech.v1beta1.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\"\xb9\x01\n\x18SynthesizeSpeechResponse\x12\x15\n\raudio_content\x18\x01 \x01(\x0c\x12@\n\ntimepoints\x18\x02 \x03(\x0b\x32,.google.cloud.texttospeech.v1beta1.Timepoint\x12\x44\n\x0c\x61udio_config\x18\x04 \x01(\x0b\x32..google.cloud.texttospeech.v1beta1.AudioConfig\"4\n\tTimepoint\x12\x11\n\tmark_name\x18\x04 \x01(\t\x12\x14\n\x0ctime_seconds\x18\x03 \x01(\x01\"\xa4\x01\n\x14StreamingAudioConfig\x12M\n\x0e\x61udio_encoding\x18\x01 \x01(\x0e\x32\x30.google.cloud.texttospeech.v1beta1.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\"\xa3\x02\n\x19StreamingSynthesizeConfig\x12K\n\x05voice\x18\x01 \x01(\x0b\x32\x37.google.cloud.texttospeech.v1beta1.VoiceSelectionParamsB\x03\xe0\x41\x02\x12\\\n\x16streaming_audio_config\x18\x04 \x01(\x0b\x32\x37.google.cloud.texttospeech.v1beta1.StreamingAudioConfigB\x03\xe0\x41\x01\x12[\n\x15\x63ustom_pronunciations\x18\x05 \x01(\x0b\x32\x37.google.cloud.texttospeech.v1beta1.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\"\xd8\x01\n\x1aStreamingSynthesizeRequest\x12X\n\x10streaming_config\x18\x01 \x01(\x0b\x32<.google.cloud.texttospeech.v1beta1.StreamingSynthesizeConfigH\x00\x12K\n\x05input\x18\x02 \x01(\x0b\x32:.google.cloud.texttospeech.v1beta1.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*\x8c\x01\n\rAudioEncoding\x12\x1e\n\x1a\x41UDIO_ENCODING_UNSPECIFIED\x10\x00\x12\x0c\n\x08LINEAR16\x10\x01\x12\x07\n\x03MP3\x10\x02\x12\x0f\n\x0bMP3_64_KBPS\x10\x04\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\xef\x04\n\x0cTextToSpeech\x12\xa2\x01\n\nListVoices\x12\x34.google.cloud.texttospeech.v1beta1.ListVoicesRequest\x1a\x35.google.cloud.texttospeech.v1beta1.ListVoicesResponse\"\'\xda\x41\rlanguage_code\x82\xd3\xe4\x93\x02\x11\x12\x0f/v1beta1/voices\x12\xcb\x01\n\x10SynthesizeSpeech\x12:.google.cloud.texttospeech.v1beta1.SynthesizeSpeechRequest\x1a;.google.cloud.texttospeech.v1beta1.SynthesizeSpeechResponse\">\xda\x41\x18input,voice,audio_config\x82\xd3\xe4\x93\x02\x1d\"\x18/v1beta1/text:synthesize:\x01*\x12\x9a\x01\n\x13StreamingSynthesize\x12=.google.cloud.texttospeech.v1beta1.StreamingSynthesizeRequest\x1a>.google.cloud.texttospeech.v1beta1.StreamingSynthesizeResponse\"\x00(\x01\x30\x01\x1aO\xca\x41\x1btexttospeech.googleapis.com\xd2\x41.https://www.googleapis.com/auth/cloud-platformB\xd5\x02\n%com.google.cloud.texttospeech.v1beta1B\x11TextToSpeechProtoP\x01ZIcloud.google.com/go/texttospeech/apiv1beta1/texttospeechpb;texttospeechpb\xa2\x02\x04\x43TTS\xaa\x02!Google.Cloud.TextToSpeech.V1Beta1\xca\x02!Google\\Cloud\\TextToSpeech\\V1beta1\xea\x02$Google::Cloud::TextToSpeech::V1beta1\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
|
|
@@ -222,6 +222,12 @@ module Google
|
|
222
222
|
# multi-speaker synthesis.
|
223
223
|
#
|
224
224
|
# 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.
|
225
|
+
# @!attribute [rw] prompt
|
226
|
+
# @return [::String]
|
227
|
+
# This system instruction is supported only for controllable/promptable voice
|
228
|
+
# models. If this system instruction is used, we pass the unedited text to
|
229
|
+
# Gemini-TTS. Otherwise, a default system instruction is used. AI Studio
|
230
|
+
# calls this system instruction, Style Instructions.
|
225
231
|
# @!attribute [rw] custom_pronunciations
|
226
232
|
# @return [::Google::Cloud::TextToSpeech::V1beta1::CustomPronunciations]
|
227
233
|
# Optional. The pronunciation customizations are applied to the input. If
|