# frozen_string_literal: true

# Copyright 2021 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 Dialogflow
      module CX
        module V3
          # Information for a word recognized by the speech recognizer.
          # @!attribute [rw] word
          #   @return [::String]
          #     The word this info is for.
          # @!attribute [rw] start_offset
          #   @return [::Google::Protobuf::Duration]
          #     Time offset relative to the beginning of the audio that corresponds to the
          #     start of the spoken word. This is an experimental feature and the accuracy
          #     of the time offset can vary.
          # @!attribute [rw] end_offset
          #   @return [::Google::Protobuf::Duration]
          #     Time offset relative to the beginning of the audio that corresponds to the
          #     end of the spoken word. This is an experimental feature and the accuracy of
          #     the time offset can vary.
          # @!attribute [rw] confidence
          #   @return [::Float]
          #     The Speech confidence between 0.0 and 1.0 for this word. A higher number
          #     indicates an estimated greater likelihood that the recognized word is
          #     correct. The default of 0.0 is a sentinel value indicating that confidence
          #     was not set.
          #
          #     This field is not guaranteed to be fully stable over time for the same
          #     audio input. Users should also not rely on it to always be provided.
          class SpeechWordInfo
            include ::Google::Protobuf::MessageExts
            extend ::Google::Protobuf::MessageExts::ClassMethods
          end

          # Configuration of the barge-in behavior. Barge-in instructs the API to return
          # a detected utterance at a proper time while the client is playing back the
          # response audio from a previous request. When the client sees the
          # utterance, it should stop the playback and immediately get ready for
          # receiving the responses for the current request.
          #
          # The barge-in handling requires the client to start streaming audio input
          # as soon as it starts playing back the audio from the previous response. The
          # playback is modeled into two phases:
          #
          # * No barge-in phase: which goes first and during which speech detection
          #   should not be carried out.
          #
          # * Barge-in phase: which follows the no barge-in phase and during which
          #   the API starts speech detection and may inform the client that an utterance
          #   has been detected. Note that no-speech event is not expected in this
          #   phase.
          #
          # The client provides this configuration in terms of the durations of those
          # two phases. The durations are measured in terms of the audio length from the
          # the start of the input audio.
          #
          # No-speech event is a response with END_OF_UTTERANCE without any transcript
          # following up.
          # @!attribute [rw] no_barge_in_duration
          #   @return [::Google::Protobuf::Duration]
          #     Duration that is not eligible for barge-in at the beginning of the input
          #     audio.
          # @!attribute [rw] total_duration
          #   @return [::Google::Protobuf::Duration]
          #     Total duration for the playback at the beginning of the input audio.
          class BargeInConfig
            include ::Google::Protobuf::MessageExts
            extend ::Google::Protobuf::MessageExts::ClassMethods
          end

          # Instructs the speech recognizer on how to process the audio content.
          # @!attribute [rw] audio_encoding
          #   @return [::Google::Cloud::Dialogflow::CX::V3::AudioEncoding]
          #     Required. Audio encoding of the audio content to process.
          # @!attribute [rw] sample_rate_hertz
          #   @return [::Integer]
          #     Sample rate (in Hertz) of the audio content sent in the query.
          #     Refer to
          #     [Cloud Speech API
          #     documentation](https://cloud.google.com/speech-to-text/docs/basics) for
          #     more details.
          # @!attribute [rw] enable_word_info
          #   @return [::Boolean]
          #     Optional. If `true`, Dialogflow returns
          #     {::Google::Cloud::Dialogflow::CX::V3::SpeechWordInfo SpeechWordInfo} in
          #     {::Google::Cloud::Dialogflow::CX::V3::StreamingRecognitionResult StreamingRecognitionResult}
          #     with information about the recognized speech words, e.g. start and end time
          #     offsets. If false or unspecified, Speech doesn't return any word-level
          #     information.
          # @!attribute [rw] phrase_hints
          #   @return [::Array<::String>]
          #     Optional. A list of strings containing words and phrases that the speech
          #     recognizer should recognize with higher likelihood.
          #
          #     See [the Cloud Speech
          #     documentation](https://cloud.google.com/speech-to-text/docs/basics#phrase-hints)
          #     for more details.
          # @!attribute [rw] model
          #   @return [::String]
          #     Optional. Which Speech model to select for the given request.
          #     For more information, see
          #     [Speech
          #     models](https://cloud.google.com/dialogflow/cx/docs/concept/speech-models).
          # @!attribute [rw] model_variant
          #   @return [::Google::Cloud::Dialogflow::CX::V3::SpeechModelVariant]
          #     Optional. Which variant of the [Speech
          #     model][google.cloud.dialogflow.cx.v3.InputAudioConfig.model] to use.
          # @!attribute [rw] single_utterance
          #   @return [::Boolean]
          #     Optional. If `false` (default), recognition does not cease until the
          #     client closes the stream.
          #     If `true`, the recognizer will detect a single spoken utterance in input
          #     audio. Recognition ceases when it detects the audio's voice has
          #     stopped or paused. In this case, once a detected intent is received, the
          #     client should close the stream and start a new request with a new stream as
          #     needed.
          #     Note: This setting is relevant only for streaming methods.
          # @!attribute [rw] barge_in_config
          #   @return [::Google::Cloud::Dialogflow::CX::V3::BargeInConfig]
          #     Configuration of barge-in behavior during the streaming of input audio.
          # @!attribute [rw] opt_out_conformer_model_migration
          #   @return [::Boolean]
          #     If `true`, the request will opt out for STT conformer model migration.
          #     This field will be deprecated once force migration takes place in June
          #     2024. Please refer to [Dialogflow CX Speech model
          #     migration](https://cloud.google.com/dialogflow/cx/docs/concept/speech-model-migration).
          class InputAudioConfig
            include ::Google::Protobuf::MessageExts
            extend ::Google::Protobuf::MessageExts::ClassMethods
          end

          # Description of which voice to use for speech synthesis.
          # @!attribute [rw] name
          #   @return [::String]
          #     Optional. The name of the voice. If not set, the service will choose a
          #     voice based on the other parameters such as language_code and
          #     {::Google::Cloud::Dialogflow::CX::V3::VoiceSelectionParams#ssml_gender ssml_gender}.
          #
          #     For the list of available voices, please refer to [Supported voices and
          #     languages](https://cloud.google.com/text-to-speech/docs/voices).
          # @!attribute [rw] ssml_gender
          #   @return [::Google::Cloud::Dialogflow::CX::V3::SsmlVoiceGender]
          #     Optional. 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
          #     {::Google::Cloud::Dialogflow::CX::V3::VoiceSelectionParams#name name}. Note that
          #     this is only a preference, not requirement. If a voice of the appropriate
          #     gender is not available, the synthesizer substitutes a voice with a
          #     different gender rather than failing the request.
          class VoiceSelectionParams
            include ::Google::Protobuf::MessageExts
            extend ::Google::Protobuf::MessageExts::ClassMethods
          end

          # Configuration of how speech should be synthesized.
          # @!attribute [rw] speaking_rate
          #   @return [::Float]
          #     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.
          # @!attribute [rw] pitch
          #   @return [::Float]
          #     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.
          # @!attribute [rw] volume_gain_db
          #   @return [::Float]
          #     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. We strongly recommend not
          #     to exceed +10 (dB) as there's usually no effective increase in loudness for
          #     any value greater than that.
          # @!attribute [rw] effects_profile_id
          #   @return [::Array<::String>]
          #     Optional. 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.
          # @!attribute [rw] voice
          #   @return [::Google::Cloud::Dialogflow::CX::V3::VoiceSelectionParams]
          #     Optional. The desired voice of the synthesized audio.
          class SynthesizeSpeechConfig
            include ::Google::Protobuf::MessageExts
            extend ::Google::Protobuf::MessageExts::ClassMethods
          end

          # Instructs the speech synthesizer how to generate the output audio content.
          # @!attribute [rw] audio_encoding
          #   @return [::Google::Cloud::Dialogflow::CX::V3::OutputAudioEncoding]
          #     Required. Audio encoding of the synthesized audio content.
          # @!attribute [rw] sample_rate_hertz
          #   @return [::Integer]
          #     Optional. The synthesis sample rate (in hertz) for this audio. If not
          #     provided, then the synthesizer will use the default sample rate based on
          #     the audio encoding. 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).
          # @!attribute [rw] synthesize_speech_config
          #   @return [::Google::Cloud::Dialogflow::CX::V3::SynthesizeSpeechConfig]
          #     Optional. Configuration of how speech should be synthesized.
          #     If not specified,
          #     {::Google::Cloud::Dialogflow::CX::V3::Agent#text_to_speech_settings Agent.text_to_speech_settings}
          #     is applied.
          class OutputAudioConfig
            include ::Google::Protobuf::MessageExts
            extend ::Google::Protobuf::MessageExts::ClassMethods
          end

          # Settings related to speech synthesizing.
          # @!attribute [rw] synthesize_speech_configs
          #   @return [::Google::Protobuf::Map{::String => ::Google::Cloud::Dialogflow::CX::V3::SynthesizeSpeechConfig}]
          #     Configuration of how speech should be synthesized, mapping from language
          #     (https://cloud.google.com/dialogflow/cx/docs/reference/language) to
          #     SynthesizeSpeechConfig.
          #
          #     These settings affect:
          #
          #      - The [phone
          #      gateway](https://cloud.google.com/dialogflow/cx/docs/concept/integration/phone-gateway)
          #        synthesize configuration set via
          #        {::Google::Cloud::Dialogflow::CX::V3::Agent#text_to_speech_settings Agent.text_to_speech_settings}.
          #
          #      - How speech is synthesized when invoking
          #      {::Google::Cloud::Dialogflow::CX::V3::Sessions::Client session} APIs.
          #        {::Google::Cloud::Dialogflow::CX::V3::Agent#text_to_speech_settings Agent.text_to_speech_settings}
          #        only applies if
          #        {::Google::Cloud::Dialogflow::CX::V3::OutputAudioConfig#synthesize_speech_config OutputAudioConfig.synthesize_speech_config}
          #        is not specified.
          class TextToSpeechSettings
            include ::Google::Protobuf::MessageExts
            extend ::Google::Protobuf::MessageExts::ClassMethods

            # @!attribute [rw] key
            #   @return [::String]
            # @!attribute [rw] value
            #   @return [::Google::Cloud::Dialogflow::CX::V3::SynthesizeSpeechConfig]
            class SynthesizeSpeechConfigsEntry
              include ::Google::Protobuf::MessageExts
              extend ::Google::Protobuf::MessageExts::ClassMethods
            end
          end

          # Audio encoding of the audio content sent in the conversational query request.
          # Refer to the
          # [Cloud Speech API
          # documentation](https://cloud.google.com/speech-to-text/docs/basics) for more
          # details.
          module AudioEncoding
            # Not specified.
            AUDIO_ENCODING_UNSPECIFIED = 0

            # Uncompressed 16-bit signed little-endian samples (Linear PCM).
            AUDIO_ENCODING_LINEAR_16 = 1

            # [`FLAC`](https://xiph.org/flac/documentation.html) (Free Lossless Audio
            # Codec) is the recommended encoding because it is lossless (therefore
            # recognition is not compromised) and requires only about half the
            # bandwidth of `LINEAR16`. `FLAC` stream encoding supports 16-bit and
            # 24-bit samples, however, not all fields in `STREAMINFO` are supported.
            AUDIO_ENCODING_FLAC = 2

            # 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
            AUDIO_ENCODING_MULAW = 3

            # Adaptive Multi-Rate Narrowband codec. `sample_rate_hertz` must be 8000.
            AUDIO_ENCODING_AMR = 4

            # Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` must be 16000.
            AUDIO_ENCODING_AMR_WB = 5

            # Opus encoded audio frames in Ogg container
            # ([OggOpus](https://wiki.xiph.org/OggOpus)).
            # `sample_rate_hertz` must be 16000.
            AUDIO_ENCODING_OGG_OPUS = 6

            # Although the use of lossy encodings is not recommended, if a very low
            # bitrate encoding is required, `OGG_OPUS` is highly preferred over
            # Speex encoding. The [Speex](https://speex.org/) encoding supported by
            # Dialogflow API has a header byte in each block, as in MIME type
            # `audio/x-speex-with-header-byte`.
            # It is a variant of the RTP Speex encoding defined in
            # [RFC 5574](https://tools.ietf.org/html/rfc5574).
            # The stream is a sequence of blocks, one block per RTP packet. Each block
            # starts with a byte containing the length of the block, in bytes, followed
            # by one or more frames of Speex data, padded to an integral number of
            # bytes (octets) as specified in RFC 5574. In other words, each RTP header
            # is replaced with a single byte containing the block length. Only Speex
            # wideband is supported. `sample_rate_hertz` must be 16000.
            AUDIO_ENCODING_SPEEX_WITH_HEADER_BYTE = 7

            # 8-bit samples that compand 13-bit audio samples using G.711 PCMU/a-law.
            AUDIO_ENCODING_ALAW = 8
          end

          # Variant of the specified [Speech
          # model][google.cloud.dialogflow.cx.v3.InputAudioConfig.model] to use.
          #
          # See the [Cloud Speech
          # documentation](https://cloud.google.com/speech-to-text/docs/enhanced-models)
          # for which models have different variants. For example, the "phone_call" model
          # has both a standard and an enhanced variant. When you use an enhanced model,
          # you will generally receive higher quality results than for a standard model.
          module SpeechModelVariant
            # No model variant specified. In this case Dialogflow defaults to
            # USE_BEST_AVAILABLE.
            SPEECH_MODEL_VARIANT_UNSPECIFIED = 0

            # Use the best available variant of the [Speech
            # model][InputAudioConfig.model] that the caller is eligible for.
            USE_BEST_AVAILABLE = 1

            # Use standard model variant even if an enhanced model is available.  See the
            # [Cloud Speech
            # documentation](https://cloud.google.com/speech-to-text/docs/enhanced-models)
            # for details about enhanced models.
            USE_STANDARD = 2

            # Use an enhanced model variant:
            #
            # * If an enhanced variant does not exist for the given
            #   {::Google::Cloud::Dialogflow::CX::V3::InputAudioConfig#model model} and request
            #   language, Dialogflow falls back to the standard variant.
            #
            #   The [Cloud Speech
            #   documentation](https://cloud.google.com/speech-to-text/docs/enhanced-models)
            #   describes which models have enhanced variants.
            USE_ENHANCED = 3
          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, which means that the client doesn't care which
            # gender the selected voice will have.
            SSML_VOICE_GENDER_UNSPECIFIED = 0

            # A male voice.
            SSML_VOICE_GENDER_MALE = 1

            # A female voice.
            SSML_VOICE_GENDER_FEMALE = 2

            # A gender-neutral voice.
            SSML_VOICE_GENDER_NEUTRAL = 3
          end

          # Audio encoding of the output audio format in Text-To-Speech.
          module OutputAudioEncoding
            # Not specified.
            OUTPUT_AUDIO_ENCODING_UNSPECIFIED = 0

            # Uncompressed 16-bit signed little-endian samples (Linear PCM).
            # Audio content returned as LINEAR16 also contains a WAV header.
            OUTPUT_AUDIO_ENCODING_LINEAR_16 = 1

            # MP3 audio at 32kbps.
            OUTPUT_AUDIO_ENCODING_MP3 = 2

            # MP3 audio at 64kbps.
            OUTPUT_AUDIO_ENCODING_MP3_64_KBPS = 4

            # 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.
            OUTPUT_AUDIO_ENCODING_OGG_OPUS = 3

            # 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
            OUTPUT_AUDIO_ENCODING_MULAW = 5

            # 8-bit samples that compand 13-bit audio samples using G.711 PCMU/a-law.
            OUTPUT_AUDIO_ENCODING_ALAW = 6
          end
        end
      end
    end
  end
end