Synchronize new proto/yaml changes.

PiperOrigin-RevId: 268019602
This commit is contained in:
Google APIs 2019-09-09 10:02:45 -07:00 committed by Copybara-Service
parent e051f9dfa6
commit 53fe2e36f0
6 changed files with 352 additions and 254 deletions

View File

@ -8,6 +8,7 @@ common:
- v1beta1
service_yaml: tts_v1beta1.yaml
gapic_yaml: v1beta1/texttospeech_gapic.yaml
proto_package: google.cloud.texttospeech.v1beta1
artifacts:
- name: gapic_config
type: GAPIC_CONFIG

View File

@ -1,4 +1,4 @@
// Copyright 2018 Google Inc.
// Copyright 2019 Google LLC.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
@ -11,43 +11,51 @@
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
syntax = "proto3";
package google.cloud.texttospeech.v1beta1;
import "google/api/annotations.proto";
import "google/api/client.proto";
import "google/api/field_behavior.proto";
option cc_enable_arenas = true;
option csharp_namespace = "Google.Cloud.TextToSpeech.V1beta1";
option go_package = "google.golang.org/genproto/googleapis/cloud/texttospeech/v1beta1;texttospeech";
option java_multiple_files = true;
option java_outer_classname = "TextToSpeechProto";
option java_package = "com.google.cloud.texttospeech.v1beta1";
option php_namespace = "Google\\Cloud\\TextToSpeech\\V1beta1";
// Service that implements Google Cloud Text-to-Speech API.
service TextToSpeech {
// Returns a list of [Voice][google.cloud.texttospeech.v1beta1.Voice]
// supported for synthesis.
option (google.api.default_host) = "texttospeech.googleapis.com";
option (google.api.oauth_scopes) = "https://www.googleapis.com/auth/cloud-platform";
// Returns a list of Voice supported for synthesis.
rpc ListVoices(ListVoicesRequest) returns (ListVoicesResponse) {
option (google.api.http) = {
get: "/v1beta1/voices"
};
option (google.api.method_signature) = "language_code";
}
// Synthesizes speech synchronously: receive results after all text input
// has been processed.
rpc SynthesizeSpeech(SynthesizeSpeechRequest)
returns (SynthesizeSpeechResponse) {
rpc SynthesizeSpeech(SynthesizeSpeechRequest) returns (SynthesizeSpeechResponse) {
option (google.api.http) = {
post: "/v1beta1/text:synthesize"
body: "*"
};
option (google.api.method_signature) = "input,voice,audio_config";
}
}
// The top-level message sent by the client for the `ListVoices` method.
message ListVoicesRequest {
// Optional (but recommended)
// Optional. Recommended.
// [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. If
// specified, the ListVoices call will only return voices that can be used to
// synthesize this language_code. E.g. when specifying "en-NZ", you will get
@ -55,136 +63,7 @@ message ListVoicesRequest {
// "no-*" (Norwegian) and "nb-*" (Norwegian Bokmal) voices; specifying "zh"
// will also get supported "cmn-*" voices; specifying "zh-hk" will also get
// supported "yue-*" voices.
string language_code = 1;
}
// The message returned to the client by the `ListVoices` method.
message ListVoicesResponse {
// The list of voices.
repeated Voice voices = 1;
}
// Description of a voice supported by the TTS service.
message Voice {
// The languages that this voice supports, expressed as
// [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags (e.g.
// "en-US", "es-419", "cmn-tw").
repeated string language_codes = 1;
// The name of this voice. Each distinct voice has a unique name.
string name = 2;
// The gender of this voice.
SsmlVoiceGender ssml_gender = 3;
// The natural sample rate (in hertz) for this voice.
int32 natural_sample_rate_hertz = 4;
}
// The top-level message sent by the client for the `SynthesizeSpeech` method.
message SynthesizeSpeechRequest {
// Required. The Synthesizer requires either plain text or SSML as input.
SynthesisInput input = 1;
// Required. The desired voice of the synthesized audio.
VoiceSelectionParams voice = 2;
// Required. The configuration of the synthesized audio.
AudioConfig audio_config = 3;
}
// Contains text input to be synthesized. Either `text` or `ssml` must be
// supplied. Supplying both or neither returns
// [google.rpc.Code.INVALID_ARGUMENT][]. The input size is limited to 5000
// characters.
message SynthesisInput {
// The input source, which is either plain text or SSML.
oneof input_source {
// The raw text to be synthesized.
string text = 1;
// The SSML document to be synthesized. The SSML document must be valid
// and well-formed. Otherwise the RPC will fail and return
// [google.rpc.Code.INVALID_ARGUMENT][]. For more information, see
// [SSML](/speech/text-to-speech/docs/ssml).
string ssml = 2;
}
}
// Description of which voice to use for a synthesis request.
message VoiceSelectionParams {
// The language (and optionally also the region) of the voice expressed as a
// [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag, e.g.
// "en-US". Required. This should not include a script tag (e.g. use
// "cmn-cn" rather than "cmn-Hant-cn"), because the script will be inferred
// from the input provided in the SynthesisInput. The TTS service
// will use this parameter to help choose an appropriate voice. Note that
// the TTS service may choose a voice with a slightly different language code
// than the one selected; it may substitute a different region
// (e.g. using en-US rather than en-CA if there isn't a Canadian voice
// available), or even a different language, e.g. using "nb" (Norwegian
// Bokmal) instead of "no" (Norwegian)".
string language_code = 1;
// The name of the voice. Optional; if not set, the service will choose a
// voice based on the other parameters such as language_code and gender.
string name = 2;
// The preferred gender of the voice. Optional; if not set, the service will
// choose a voice based on the other parameters such as language_code and
// name. Note that this is only a preference, not requirement; if a
// voice of the appropriate gender is not available, the synthesizer should
// substitute a voice with a different gender rather than failing the request.
SsmlVoiceGender ssml_gender = 3;
}
// Description of audio data to be synthesized.
message AudioConfig {
// Required. The format of the requested audio byte stream.
AudioEncoding audio_encoding = 1;
// Optional speaking rate/speed, in the range [0.25, 4.0]. 1.0 is the normal
// native speed supported by the specific voice. 2.0 is twice as fast, and
// 0.5 is half as fast. If unset(0.0), defaults to the native 1.0 speed. Any
// other values < 0.25 or > 4.0 will return an error.
double speaking_rate = 2;
// Optional speaking pitch, in the range [-20.0, 20.0]. 20 means increase 20
// semitones from the original pitch. -20 means decrease 20 semitones from the
// original pitch.
double pitch = 3;
// Optional volume gain (in dB) of the normal native volume supported by the
// specific voice, in the range [-96.0, 16.0]. If unset, or set to a value of
// 0.0 (dB), will play at normal native signal amplitude. A value of -6.0 (dB)
// will play at approximately half the amplitude of the normal native signal
// amplitude. A value of +6.0 (dB) will play at approximately twice the
// amplitude of the normal native signal amplitude. Strongly recommend not to
// exceed +10 (dB) as there's usually no effective increase in loudness for
// any value greater than that.
double volume_gain_db = 4;
// The synthesis sample rate (in hertz) for this audio. Optional. If this is
// different from the voice's natural sample rate, then the synthesizer will
// honor this request by converting to the desired sample rate (which might
// result in worse audio quality), unless the specified sample rate is not
// supported for the encoding chosen, in which case it will fail the request
// and return [google.rpc.Code.INVALID_ARGUMENT][].
int32 sample_rate_hertz = 5;
// An identifier which selects 'audio effects' profiles that are applied on
// (post synthesized) text to speech.
// Effects are applied on top of each other in the order they are given.
repeated string effects_profile_id = 6;
}
// The message returned to the client by the `SynthesizeSpeech` method.
message SynthesizeSpeechResponse {
// The audio data bytes encoded as specified in the request, including the
// header (For LINEAR16 audio, we include the WAV header). Note: as
// with all bytes fields, protobuffers use a pure binary representation,
// whereas JSON representations use base64.
bytes audio_content = 1;
string language_code = 1 [(google.api.field_behavior) = OPTIONAL];
}
// Gender of the voice as described in
@ -217,7 +96,7 @@ enum AudioEncoding {
// Audio content returned as LINEAR16 also contains a WAV header.
LINEAR16 = 1;
// MP3 audio.
// MP3 audio at 32kbps.
MP3 = 2;
// Opus encoded audio wrapped in an ogg container. The result will be a
@ -226,3 +105,149 @@ enum AudioEncoding {
// than MP3 while using approximately the same bitrate.
OGG_OPUS = 3;
}
// The message returned to the client by the `ListVoices` method.
message ListVoicesResponse {
// The list of voices.
repeated Voice voices = 1;
}
// Description of a voice supported by the TTS service.
message Voice {
// The languages that this voice supports, expressed as
// [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags (e.g.
// "en-US", "es-419", "cmn-tw").
repeated string language_codes = 1;
// The name of this voice. Each distinct voice has a unique name.
string name = 2;
// The gender of this voice.
SsmlVoiceGender ssml_gender = 3;
// The natural sample rate (in hertz) for this voice.
int32 natural_sample_rate_hertz = 4;
}
// The top-level message sent by the client for the `SynthesizeSpeech` method.
message SynthesizeSpeechRequest {
// Required. The Synthesizer requires either plain text or SSML as input.
SynthesisInput input = 1 [(google.api.field_behavior) = REQUIRED];
// Required. The desired voice of the synthesized audio.
VoiceSelectionParams voice = 2 [(google.api.field_behavior) = REQUIRED];
// Required. The configuration of the synthesized audio.
AudioConfig audio_config = 3 [(google.api.field_behavior) = REQUIRED];
}
// Contains text input to be synthesized. Either `text` or `ssml` must be
// supplied. Supplying both or neither returns
// [google.rpc.Code.INVALID_ARGUMENT][]. The input size is limited to 5000
// characters.
message SynthesisInput {
// The input source, which is either plain text or SSML.
oneof input_source {
// The raw text to be synthesized.
string text = 1;
// The SSML document to be synthesized. The SSML document must be valid
// and well-formed. Otherwise the RPC will fail and return
// [google.rpc.Code.INVALID_ARGUMENT][]. For more information, see
// [SSML](/speech/text-to-speech/docs/ssml).
string ssml = 2;
}
}
// Description of which voice to use for a synthesis request.
message VoiceSelectionParams {
// Required. The language (and potentially also the region) of the voice expressed as a
// [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag, e.g.
// "en-US". This should not include a script tag (e.g. use
// "cmn-cn" rather than "cmn-Hant-cn"), because the script will be inferred
// from the input provided in the SynthesisInput. The TTS service
// will use this parameter to help choose an appropriate voice. Note that
// the TTS service may choose a voice with a slightly different language code
// than the one selected; it may substitute a different region
// (e.g. using en-US rather than en-CA if there isn't a Canadian voice
// available), or even a different language, e.g. using "nb" (Norwegian
// Bokmal) instead of "no" (Norwegian)".
string language_code = 1 [(google.api.field_behavior) = REQUIRED];
// The name of the voice. If not set, the service will choose a
// voice based on the other parameters such as language_code and gender.
string name = 2;
// The preferred gender of the voice. If not set, the service will
// choose a voice based on the other parameters such as language_code and
// name. Note that this is only a preference, not requirement; if a
// voice of the appropriate gender is not available, the synthesizer should
// substitute a voice with a different gender rather than failing the request.
SsmlVoiceGender ssml_gender = 3;
}
// Description of audio data to be synthesized.
message AudioConfig {
// Required. The format of the audio byte stream.
AudioEncoding audio_encoding = 1 [(google.api.field_behavior) = REQUIRED];
// Optional. Input only. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is
// the normal native speed supported by the specific voice. 2.0 is twice as
// fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
// speed. Any other values < 0.25 or > 4.0 will return an error.
double speaking_rate = 2 [
(google.api.field_behavior) = INPUT_ONLY,
(google.api.field_behavior) = OPTIONAL
];
// Optional. Input only. Speaking pitch, in the range [-20.0, 20.0]. 20 means
// increase 20 semitones from the original pitch. -20 means decrease 20
// semitones from the original pitch.
double pitch = 3 [
(google.api.field_behavior) = INPUT_ONLY,
(google.api.field_behavior) = OPTIONAL
];
// Optional. Input only. Volume gain (in dB) of the normal native volume
// supported by the specific voice, in the range [-96.0, 16.0]. If unset, or
// set to a value of 0.0 (dB), will play at normal native signal amplitude. A
// value of -6.0 (dB) will play at approximately half the amplitude of the
// normal native signal amplitude. A value of +6.0 (dB) will play at
// approximately twice the amplitude of the normal native signal amplitude.
// Strongly recommend not to exceed +10 (dB) as there's usually no effective
// increase in loudness for any value greater than that.
double volume_gain_db = 4 [
(google.api.field_behavior) = INPUT_ONLY,
(google.api.field_behavior) = OPTIONAL
];
// Optional. The synthesis sample rate (in hertz) for this audio. When this is
// specified in SynthesizeSpeechRequest, if this is different from the voice's
// natural sample rate, then the synthesizer will honor this request by
// converting to the desired sample rate (which might result in worse audio
// quality), unless the specified sample rate is not supported for the
// encoding chosen, in which case it will fail the request and return
// [google.rpc.Code.INVALID_ARGUMENT][].
int32 sample_rate_hertz = 5 [(google.api.field_behavior) = OPTIONAL];
// Optional. Input only. An identifier which selects 'audio effects' profiles
// that are applied on (post synthesized) text to speech. Effects are applied
// on top of each other in the order they are given. See
// [audio
// profiles](https://cloud.google.com/text-to-speech/docs/audio-profiles) for
// current supported profile ids.
repeated string effects_profile_id = 6 [
(google.api.field_behavior) = INPUT_ONLY,
(google.api.field_behavior) = OPTIONAL
];
}
// The message returned to the client by the `SynthesizeSpeech` method.
message SynthesizeSpeechResponse {
// The audio data bytes encoded as specified in the request, including the
// header for encodings that are wrapped in containers (e.g. MP3, OGG_OPUS).
// For LINEAR16 audio, we include the WAV header. Note: as
// with all bytes fields, protobuffers use a pure binary representation,
// whereas JSON representations use base64.
bytes audio_content = 1;
}

View File

@ -0,0 +1,135 @@
type: com.google.api.codegen.ConfigProto
config_schema_version: 1.0.0
# The settings of generated code in a specific language.
language_settings:
java:
package_name: com.google.cloud.texttospeech.v1beta1
python:
package_name: google.cloud.texttospeech_v1beta1.gapic
go:
package_name: cloud.google.com/go/texttospeech/apiv1beta1
csharp:
package_name: Google.Cloud.TextToSpeech.V1Beta1
ruby:
package_name: Google::Cloud::TextToSpeech::V1beta1
php:
package_name: Google\Cloud\TextToSpeech\V1beta1
nodejs:
package_name: text-to-speech.v1beta1
domain_layer_location: google-cloud
# A list of API interface configurations.
interfaces:
# The fully qualified name of the API interface.
- name: google.cloud.texttospeech.v1beta1.TextToSpeech
smoke_test:
method: SynthesizeSpeech
init_fields:
- input.text="test"
- voice.language_code="en-US"
- audio_config.audio_encoding=MP3
# A list of resource collection configurations.
# Consists of a name_pattern and an entity_name.
# The name_pattern is a pattern to describe the names of the resources of this
# collection, using the platform's conventions for URI patterns. A generator
# may use this to generate methods to compose and decompose such names. The
# pattern should use named placeholders as in `shelves/{shelf}/books/{book}`;
# those will be taken as hints for the parameter names of the generated
# methods. If empty, no name methods are generated.
# The entity_name is the name to be used as a basis for generated methods and
# classes.
collections: []
# Definition for retryable codes.
retry_codes_def:
- name: idempotent
retry_codes:
- UNAVAILABLE
- DEADLINE_EXCEEDED
- name: non_idempotent
retry_codes: []
# Definition for retry/backoff parameters.
retry_params_def:
- name: default
initial_retry_delay_millis: 100
retry_delay_multiplier: 1.3
max_retry_delay_millis: 60000
initial_rpc_timeout_millis: 20000
rpc_timeout_multiplier: 1
max_rpc_timeout_millis: 20000
total_timeout_millis: 600000
# A list of method configurations.
# Common properties:
#
# name - The simple name of the method.
#
# flattening - Specifies the configuration for parameter flattening.
# Describes the parameter groups for which a generator should produce method
# overloads which allow a client to directly pass request message fields as
# method parameters. This information may or may not be used, depending on
# the target language.
# Consists of groups, which each represent a list of parameters to be
# flattened. Each parameter listed must be a field of the request message.
#
# required_fields - Fields that are always required for a request to be
# valid.
#
# resource_name_treatment - An enum that specifies how to treat the resource
# name formats defined in the field_name_patterns and
# response_field_name_patterns fields.
# UNSET: default value
# NONE: the collection configs will not be used by the generated code.
# VALIDATE: string fields will be validated by the client against the
# specified resource name formats.
# STATIC_TYPES: the client will use generated types for resource names.
#
# page_streaming - Specifies the configuration for paging.
# Describes information for generating a method which transforms a paging
# list RPC into a stream of resources.
# Consists of a request and a response.
# The request specifies request information of the list method. It defines
# which fields match the paging pattern in the request. The request consists
# of a page_size_field and a token_field. The page_size_field is the name of
# the optional field specifying the maximum number of elements to be
# returned in the response. The token_field is the name of the field in the
# request containing the page token.
# The response specifies response information of the list method. It defines
# which fields match the paging pattern in the response. The response
# consists of a token_field and a resources_field. The token_field is the
# name of the field in the response containing the next page token. The
# resources_field is the name of the field in the response containing the
# list of resources belonging to the page.
#
# retry_codes_name - Specifies the configuration for retryable codes. The
# name must be defined in interfaces.retry_codes_def.
#
# retry_params_name - Specifies the configuration for retry/backoff
# parameters. The name must be defined in interfaces.retry_params_def.
#
# field_name_patterns - Maps the field name of the request type to
# entity_name of interfaces.collections.
# Specifies the string pattern that the field must follow.
#
# timeout_millis - Specifies the default timeout for a non-retrying call. If
# the call is retrying, refer to retry_params_name instead.
methods:
- name: ListVoices
flattening:
groups:
- parameters:
- language_code
retry_codes_name: idempotent
retry_params_name: default
timeout_millis: 30000
- name: SynthesizeSpeech
flattening:
groups:
- parameters:
- input
- voice
- audio_config
required_fields:
- input
- voice
- audio_config
retry_codes_name: idempotent
retry_params_name: default
timeout_millis: 60000

View File

@ -1,5 +1,5 @@
type: com.google.api.codegen.ConfigProto
config_schema_version: 1.0.0
config_schema_version: 2.0.0
# The settings of generated code in a specific language.
language_settings:
java:
@ -17,119 +17,3 @@ language_settings:
nodejs:
package_name: text-to-speech.v1beta1
domain_layer_location: google-cloud
# A list of API interface configurations.
interfaces:
# The fully qualified name of the API interface.
- name: google.cloud.texttospeech.v1beta1.TextToSpeech
smoke_test:
method: SynthesizeSpeech
init_fields:
- input.text="test"
- voice.language_code="en-US"
- audio_config.audio_encoding=MP3
# A list of resource collection configurations.
# Consists of a name_pattern and an entity_name.
# The name_pattern is a pattern to describe the names of the resources of this
# collection, using the platform's conventions for URI patterns. A generator
# may use this to generate methods to compose and decompose such names. The
# pattern should use named placeholders as in `shelves/{shelf}/books/{book}`;
# those will be taken as hints for the parameter names of the generated
# methods. If empty, no name methods are generated.
# The entity_name is the name to be used as a basis for generated methods and
# classes.
collections: []
# Definition for retryable codes.
retry_codes_def:
- name: idempotent
retry_codes:
- UNAVAILABLE
- DEADLINE_EXCEEDED
- name: non_idempotent
retry_codes: []
# Definition for retry/backoff parameters.
retry_params_def:
- name: default
initial_retry_delay_millis: 100
retry_delay_multiplier: 1.3
max_retry_delay_millis: 60000
initial_rpc_timeout_millis: 20000
rpc_timeout_multiplier: 1
max_rpc_timeout_millis: 20000
total_timeout_millis: 600000
# A list of method configurations.
# Common properties:
#
# name - The simple name of the method.
#
# flattening - Specifies the configuration for parameter flattening.
# Describes the parameter groups for which a generator should produce method
# overloads which allow a client to directly pass request message fields as
# method parameters. This information may or may not be used, depending on
# the target language.
# Consists of groups, which each represent a list of parameters to be
# flattened. Each parameter listed must be a field of the request message.
#
# required_fields - Fields that are always required for a request to be
# valid.
#
# resource_name_treatment - An enum that specifies how to treat the resource
# name formats defined in the field_name_patterns and
# response_field_name_patterns fields.
# UNSET: default value
# NONE: the collection configs will not be used by the generated code.
# VALIDATE: string fields will be validated by the client against the
# specified resource name formats.
# STATIC_TYPES: the client will use generated types for resource names.
#
# page_streaming - Specifies the configuration for paging.
# Describes information for generating a method which transforms a paging
# list RPC into a stream of resources.
# Consists of a request and a response.
# The request specifies request information of the list method. It defines
# which fields match the paging pattern in the request. The request consists
# of a page_size_field and a token_field. The page_size_field is the name of
# the optional field specifying the maximum number of elements to be
# returned in the response. The token_field is the name of the field in the
# request containing the page token.
# The response specifies response information of the list method. It defines
# which fields match the paging pattern in the response. The response
# consists of a token_field and a resources_field. The token_field is the
# name of the field in the response containing the next page token. The
# resources_field is the name of the field in the response containing the
# list of resources belonging to the page.
#
# retry_codes_name - Specifies the configuration for retryable codes. The
# name must be defined in interfaces.retry_codes_def.
#
# retry_params_name - Specifies the configuration for retry/backoff
# parameters. The name must be defined in interfaces.retry_params_def.
#
# field_name_patterns - Maps the field name of the request type to
# entity_name of interfaces.collections.
# Specifies the string pattern that the field must follow.
#
# timeout_millis - Specifies the default timeout for a non-retrying call. If
# the call is retrying, refer to retry_params_name instead.
methods:
- name: ListVoices
flattening:
groups:
- parameters:
- language_code
retry_codes_name: idempotent
retry_params_name: default
timeout_millis: 30000
- name: SynthesizeSpeech
flattening:
groups:
- parameters:
- input
- voice
- audio_config
required_fields:
- input
- voice
- audio_config
retry_codes_name: idempotent
retry_params_name: default
timeout_millis: 60000

View File

@ -0,0 +1,26 @@
{
"methodConfig": [
{
"name": [
{
"service": "google.cloud.texttospeech.v1beta1.TextToSpeech",
"method": "ListVoices"
},
{
"service": "google.cloud.texttospeech.v1beta1.TextToSpeech",
"method": "SynthesizeSpeech"
}
],
"timeout": "600s",
"retryPolicy": {
"initialBackoff": "0.100s",
"maxBackoff": "60s",
"backoffMultiplier": 1.3,
"retryableStatusCodes": [
"UNAVAILABLE",
"DEADLINE_EXCEEDED"
]
}
}
]
}

View File

@ -0,0 +1,27 @@
type: google.api.Service
config_version: 3
name: texttospeech.googleapis.com
title: Cloud Text-to-Speech API
apis:
- name: google.cloud.texttospeech.v1beta1.TextToSpeech
documentation:
summary: |-
Synthesizes natural-sounding speech by applying powerful neural network
models.
overview: |-
# Introduction
Google Cloud Text-to-Speech API provides speech synthesis as a service.
authentication:
rules:
- selector: google.cloud.texttospeech.v1beta1.TextToSpeech.ListVoices
oauth:
canonical_scopes: |-
https://www.googleapis.com/auth/cloud-platform
- selector: google.cloud.texttospeech.v1beta1.TextToSpeech.SynthesizeSpeech
oauth:
canonical_scopes: |-
https://www.googleapis.com/auth/cloud-platform