# frozen_string_literal: true

# Copyright 2020 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# 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.

# Auto-generated by gapic-generator-ruby. DO NOT EDIT!


module Google
  module Cloud
    module TextToSpeech
      module V1
        # The top-level message sent by the client for the `ListVoices` method.
        # @!attribute [rw] language_code
        #   @return [::String]
        #     Optional. Recommended.
        #     [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
        #     If not specified, the API will return all supported voices.
        #     If specified, the ListVoices call will only return voices that can be used
        #     to synthesize this language_code. For example, if you specify `"en-NZ"`,
        #     all `"en-NZ"` voices will be returned. If you specify `"no"`, both
        #     `"no-\*"` (Norwegian) and `"nb-\*"` (Norwegian Bokmal) voices will be
        #     returned.
        class ListVoicesRequest
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # The message returned to the client by the `ListVoices` method.
        # @!attribute [rw] voices
        #   @return [::Array<::Google::Cloud::TextToSpeech::V1::Voice>]
        #     The list of voices.
        class ListVoicesResponse
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # Description of a voice supported by the TTS service.
        # @!attribute [rw] language_codes
        #   @return [::Array<::String>]
        #     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").
        # @!attribute [rw] name
        #   @return [::String]
        #     The name of this voice.  Each distinct voice has a unique name.
        # @!attribute [rw] ssml_gender
        #   @return [::Google::Cloud::TextToSpeech::V1::SsmlVoiceGender]
        #     The gender of this voice.
        # @!attribute [rw] natural_sample_rate_hertz
        #   @return [::Integer]
        #     The natural sample rate (in hertz) for this voice.
        class Voice
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # Used for advanced voice options.
        # @!attribute [rw] low_latency_journey_synthesis
        #   @return [::Boolean]
        #     Only for Journey voices. If false, the synthesis will be context aware
        #     and have higher latency.
        class AdvancedVoiceOptions
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # The top-level message sent by the client for the `SynthesizeSpeech` method.
        # @!attribute [rw] input
        #   @return [::Google::Cloud::TextToSpeech::V1::SynthesisInput]
        #     Required. The Synthesizer requires either plain text or SSML as input.
        # @!attribute [rw] voice
        #   @return [::Google::Cloud::TextToSpeech::V1::VoiceSelectionParams]
        #     Required. The desired voice of the synthesized audio.
        # @!attribute [rw] audio_config
        #   @return [::Google::Cloud::TextToSpeech::V1::AudioConfig]
        #     Required. The configuration of the synthesized audio.
        # @!attribute [rw] advanced_voice_options
        #   @return [::Google::Cloud::TextToSpeech::V1::AdvancedVoiceOptions]
        #     Advanced voice options.
        class SynthesizeSpeechRequest
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # Pronunciation customization for a phrase.
        # @!attribute [rw] phrase
        #   @return [::String]
        #     The phrase to which the customization will be applied.
        #     The phrase can be multiple words (in the case of proper nouns etc), but
        #     should not span to a whole sentence.
        # @!attribute [rw] phonetic_encoding
        #   @return [::Google::Cloud::TextToSpeech::V1::CustomPronunciationParams::PhoneticEncoding]
        #     The phonetic encoding of the phrase.
        # @!attribute [rw] pronunciation
        #   @return [::String]
        #     The pronunciation of the phrase. This must be in the phonetic encoding
        #     specified above.
        class CustomPronunciationParams
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods

          # The phonetic encoding of the phrase.
          module PhoneticEncoding
            # Not specified.
            PHONETIC_ENCODING_UNSPECIFIED = 0

            # IPA. (e.g. apple -> ˈæpəl )
            # https://en.wikipedia.org/wiki/International_Phonetic_Alphabet
            PHONETIC_ENCODING_IPA = 1

            # X-SAMPA (e.g. apple -> "{p@l" )
            # https://en.wikipedia.org/wiki/X-SAMPA
            PHONETIC_ENCODING_X_SAMPA = 2
          end
        end

        # A collection of pronunciation customizations.
        # @!attribute [rw] pronunciations
        #   @return [::Array<::Google::Cloud::TextToSpeech::V1::CustomPronunciationParams>]
        #     The pronunciation customizations to be applied.
        class CustomPronunciations
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # A collection of turns for multi-speaker synthesis.
        # @!attribute [rw] turns
        #   @return [::Array<::Google::Cloud::TextToSpeech::V1::MultiSpeakerMarkup::Turn>]
        #     Required. Speaker turns.
        class MultiSpeakerMarkup
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods

          # A Multi-speaker turn.
          # @!attribute [rw] speaker
          #   @return [::String]
          #     Required. The speaker of the turn, for example, 'O' or 'Q'. Please refer
          #     to documentation for available speakers.
          # @!attribute [rw] text
          #   @return [::String]
          #     Required. The text to speak.
          class Turn
            include ::Google::Protobuf::MessageExts
            extend ::Google::Protobuf::MessageExts::ClassMethods
          end
        end

        # Contains text input to be synthesized. Either `text` or `ssml` must be
        # supplied. Supplying both or neither returns
        # [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]. The
        # input size is limited to 5000 bytes.
        # @!attribute [rw] text
        #   @return [::String]
        #     The raw text to be synthesized.
        # @!attribute [rw] ssml
        #   @return [::String]
        #     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][google.rpc.Code.INVALID_ARGUMENT]. For
        #     more information, see
        #     [SSML](https://cloud.google.com/text-to-speech/docs/ssml).
        # @!attribute [rw] multi_speaker_markup
        #   @return [::Google::Cloud::TextToSpeech::V1::MultiSpeakerMarkup]
        #     The multi-speaker input to be synthesized. Only applicable for
        #     multi-speaker synthesis.
        # @!attribute [rw] custom_pronunciations
        #   @return [::Google::Cloud::TextToSpeech::V1::CustomPronunciations]
        #     Optional. The pronunciation customizations to be applied to the input. If
        #     this is set, the input will be synthesized using the given pronunciation
        #     customizations.
        #
        #     The initial support will be for EFIGS (English, French,
        #     Italian, German, Spanish) languages, as provided in
        #     VoiceSelectionParams. Journey and Instant Clone voices are
        #     not supported yet.
        #
        #     In order to customize the pronunciation of a phrase, there must be an exact
        #     match of the phrase in the input types. If using SSML, the phrase must not
        #     be inside a phoneme tag (entirely or partially).
        class SynthesisInput
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # Description of which voice to use for a synthesis request.
        # @!attribute [rw] language_code
        #   @return [::String]
        #     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)".
        # @!attribute [rw] name
        #   @return [::String]
        #     The name of the voice. If both the name and the gender are not set,
        #     the service will choose a voice based on the other parameters such as
        #     language_code.
        # @!attribute [rw] ssml_gender
        #   @return [::Google::Cloud::TextToSpeech::V1::SsmlVoiceGender]
        #     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.
        # @!attribute [rw] custom_voice
        #   @return [::Google::Cloud::TextToSpeech::V1::CustomVoiceParams]
        #     The configuration for a custom voice. If [CustomVoiceParams.model] is set,
        #     the service will choose the custom voice matching the specified
        #     configuration.
        # @!attribute [rw] voice_clone
        #   @return [::Google::Cloud::TextToSpeech::V1::VoiceCloneParams]
        #     Optional. The configuration for a voice clone. If
        #     [VoiceCloneParams.voice_clone_key] is set, the service will choose the
        #     voice clone matching the specified configuration.
        class VoiceSelectionParams
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # Description of audio data to be synthesized.
        # @!attribute [rw] audio_encoding
        #   @return [::Google::Cloud::TextToSpeech::V1::AudioEncoding]
        #     Required. The format of the audio byte stream.
        # @!attribute [rw] speaking_rate
        #   @return [::Float]
        #     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.
        # @!attribute [rw] pitch
        #   @return [::Float]
        #     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.
        # @!attribute [rw] volume_gain_db
        #   @return [::Float]
        #     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.
        # @!attribute [rw] sample_rate_hertz
        #   @return [::Integer]
        #     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][google.rpc.Code.INVALID_ARGUMENT].
        # @!attribute [rw] effects_profile_id
        #   @return [::Array<::String>]
        #     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.
        class AudioConfig
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # Description of the custom voice to be synthesized.
        # @!attribute [rw] model
        #   @return [::String]
        #     Required. The name of the AutoML model that synthesizes the custom voice.
        # @!attribute [rw] reported_usage
        #   @deprecated This field is deprecated and may be removed in the next major version update.
        #   @return [::Google::Cloud::TextToSpeech::V1::CustomVoiceParams::ReportedUsage]
        #     Optional. Deprecated. The usage of the synthesized audio to be reported.
        class CustomVoiceParams
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods

          # Deprecated. The usage of the synthesized audio. Usage does not affect
          # billing.
          module ReportedUsage
            # Request with reported usage unspecified will be rejected.
            REPORTED_USAGE_UNSPECIFIED = 0

            # For scenarios where the synthesized audio is not downloadable and can
            # only be used once. For example, real-time request in IVR system.
            REALTIME = 1

            # For scenarios where the synthesized audio is downloadable and can be
            # reused. For example, the synthesized audio is downloaded, stored in
            # customer service system and played repeatedly.
            OFFLINE = 2
          end
        end

        # The configuration of Voice Clone feature.
        # @!attribute [rw] voice_cloning_key
        #   @return [::String]
        #     Required. Created by GenerateVoiceCloningKey.
        class VoiceCloneParams
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # The message returned to the client by the `SynthesizeSpeech` method.
        # @!attribute [rw] audio_content
        #   @return [::String]
        #     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.
        class SynthesizeSpeechResponse
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # Provides configuration information for the StreamingSynthesize request.
        # @!attribute [rw] voice
        #   @return [::Google::Cloud::TextToSpeech::V1::VoiceSelectionParams]
        #     Required. The desired voice of the synthesized audio.
        class StreamingSynthesizeConfig
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # Input to be synthesized.
        # @!attribute [rw] text
        #   @return [::String]
        #     The raw text to be synthesized. It is recommended that each input
        #     contains complete, terminating sentences, as this will likely result in
        #     better prosody in the output audio. That being said, users are free to
        #     input text however they please.
        class StreamingSynthesisInput
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # Request message for the `StreamingSynthesize` method. Multiple
        # `StreamingSynthesizeRequest` messages are sent in one call.
        # The first message must contain a `streaming_config` that
        # fully specifies the request configuration and must not contain `input`. All
        # subsequent messages must only have `input` set.
        # @!attribute [rw] streaming_config
        #   @return [::Google::Cloud::TextToSpeech::V1::StreamingSynthesizeConfig]
        #     StreamingSynthesizeConfig to be used in this streaming attempt. Only
        #     specified in the first message sent in a `StreamingSynthesize` call.
        # @!attribute [rw] input
        #   @return [::Google::Cloud::TextToSpeech::V1::StreamingSynthesisInput]
        #     Input to synthesize. Specified in all messages but the first in a
        #     `StreamingSynthesize` call.
        class StreamingSynthesizeRequest
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # `StreamingSynthesizeResponse` is the only message returned to the
        # client by `StreamingSynthesize` method. A series of zero or more
        # `StreamingSynthesizeResponse` messages are streamed back to the client.
        # @!attribute [rw] audio_content
        #   @return [::String]
        #     The audio data bytes encoded as specified in the request. This is
        #     headerless LINEAR16 audio with a sample rate of 24000.
        class StreamingSynthesizeResponse
          include ::Google::Protobuf::MessageExts
          extend ::Google::Protobuf::MessageExts::ClassMethods
        end

        # Gender of the voice as described in
        # [SSML voice element](https://www.w3.org/TR/speech-synthesis11/#edef_voice).
        module SsmlVoiceGender
          # An unspecified gender.
          # In VoiceSelectionParams, this means that the client doesn't care which
          # gender the selected voice will have. In the Voice field of
          # ListVoicesResponse, this may mean that the voice doesn't fit any of the
          # other categories in this enum, or that the gender of the voice isn't known.
          SSML_VOICE_GENDER_UNSPECIFIED = 0

          # A male voice.
          MALE = 1

          # A female voice.
          FEMALE = 2

          # A gender-neutral voice. This voice is not yet supported.
          NEUTRAL = 3
        end

        # Configuration to set up audio encoder. The encoding determines the output
        # audio format that we'd like.
        module AudioEncoding
          # Not specified. Will return result
          # [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
          AUDIO_ENCODING_UNSPECIFIED = 0

          # Uncompressed 16-bit signed little-endian samples (Linear PCM).
          # Audio content returned as LINEAR16 also contains a WAV header.
          LINEAR16 = 1

          # MP3 audio at 32kbps.
          MP3 = 2

          # Opus encoded audio wrapped in an ogg container. The result will be a
          # file which can be played natively on Android, and in browsers (at least
          # Chrome and Firefox). The quality of the encoding is considerably higher
          # than MP3 while using approximately the same bitrate.
          OGG_OPUS = 3

          # 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
          # Audio content returned as MULAW also contains a WAV header.
          MULAW = 5

          # 8-bit samples that compand 14-bit audio samples using G.711 PCMU/A-law.
          # Audio content returned as ALAW also contains a WAV header.
          ALAW = 6
        end
      end
    end
  end
end