texttospeech

type AudioConfig struct {

	// Required. The format of the audio byte stream.
	AudioEncoding AudioEncoding `` /* 154-byte string literal not displayed */
	// 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.
	SpeakingRate float64 `protobuf:"fixed64,2,opt,name=speaking_rate,json=speakingRate,proto3" json:"speaking_rate,omitempty"`
	// 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.
	Pitch float64 `protobuf:"fixed64,3,opt,name=pitch,proto3" json:"pitch,omitempty"`
	// 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.
	VolumeGainDb float64 `protobuf:"fixed64,4,opt,name=volume_gain_db,json=volumeGainDb,proto3" json:"volume_gain_db,omitempty"`
	// 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].
	SampleRateHertz int32 `protobuf:"varint,5,opt,name=sample_rate_hertz,json=sampleRateHertz,proto3" json:"sample_rate_hertz,omitempty"`
	// 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.
	EffectsProfileId []string `protobuf:"bytes,6,rep,name=effects_profile_id,json=effectsProfileId,proto3" json:"effects_profile_id,omitempty"`
	// contains filtered or unexported fields
}

type AudioEncoding int32

type CustomVoiceParams struct {

	// Required. The name of the AutoML model that synthesizes the custom voice.
	Model string `protobuf:"bytes,1,opt,name=model,proto3" json:"model,omitempty"`
	// Optional. The usage of the synthesized audio to be reported.
	ReportedUsage CustomVoiceParams_ReportedUsage `` /* 172-byte string literal not displayed */
	// contains filtered or unexported fields
}

type CustomVoiceParams_ReportedUsage int32

type ListVoicesRequest struct {

	// 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.
	LanguageCode string `protobuf:"bytes,1,opt,name=language_code,json=languageCode,proto3" json:"language_code,omitempty"`
	// contains filtered or unexported fields
}

type ListVoicesResponse struct {

	// The list of voices.
	Voices []*Voice `protobuf:"bytes,1,rep,name=voices,proto3" json:"voices,omitempty"`
	// contains filtered or unexported fields
}

type SsmlVoiceGender int32

type SynthesisInput struct {

	// The input source, which is either plain text or SSML.
	//
	// Types that are assignable to InputSource:
	//
	//	*SynthesisInput_Text
	//	*SynthesisInput_Ssml
	InputSource isSynthesisInput_InputSource `protobuf_oneof:"input_source"`
	// contains filtered or unexported fields
}

type SynthesisInput_Ssml struct {
	// 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).
	Ssml string `protobuf:"bytes,2,opt,name=ssml,proto3,oneof"`
}

type SynthesisInput_Text struct {
	// The raw text to be synthesized.
	Text string `protobuf:"bytes,1,opt,name=text,proto3,oneof"`
}

type SynthesizeLongAudioMetadata struct {

	// Time when the request was received.
	StartTime *timestamppb.Timestamp `protobuf:"bytes,1,opt,name=start_time,json=startTime,proto3" json:"start_time,omitempty"`
	// Time of the most recent processing update.
	LastUpdateTime *timestamppb.Timestamp `protobuf:"bytes,2,opt,name=last_update_time,json=lastUpdateTime,proto3" json:"last_update_time,omitempty"`
	// The progress of the most recent processing update in percentage, ie. 70.0%.
	ProgressPercentage float64 `protobuf:"fixed64,3,opt,name=progress_percentage,json=progressPercentage,proto3" json:"progress_percentage,omitempty"`
	// contains filtered or unexported fields
}

type SynthesizeLongAudioRequest struct {

	// The resource states of the request in the form of
	// `projects/*/locations/*/voices/*`.
	Parent string `protobuf:"bytes,1,opt,name=parent,proto3" json:"parent,omitempty"`
	// Required. The Synthesizer requires either plain text or SSML as input.
	Input *SynthesisInput `protobuf:"bytes,2,opt,name=input,proto3" json:"input,omitempty"`
	// Required. The configuration of the synthesized audio.
	AudioConfig *AudioConfig `protobuf:"bytes,3,opt,name=audio_config,json=audioConfig,proto3" json:"audio_config,omitempty"`
	// Specifies a Cloud Storage URI for the synthesis results. Must be
	// specified in the format: `gs://bucket_name/object_name`, and the bucket
	// must already exist.
	OutputGcsUri string `protobuf:"bytes,4,opt,name=output_gcs_uri,json=outputGcsUri,proto3" json:"output_gcs_uri,omitempty"`
	// The desired voice of the synthesized audio.
	Voice *VoiceSelectionParams `protobuf:"bytes,5,opt,name=voice,proto3" json:"voice,omitempty"`
	// contains filtered or unexported fields
}

type SynthesizeLongAudioResponse struct {
	// contains filtered or unexported fields
}

type SynthesizeSpeechRequest struct {

	// Required. The Synthesizer requires either plain text or SSML as input.
	Input *SynthesisInput `protobuf:"bytes,1,opt,name=input,proto3" json:"input,omitempty"`
	// Required. The desired voice of the synthesized audio.
	Voice *VoiceSelectionParams `protobuf:"bytes,2,opt,name=voice,proto3" json:"voice,omitempty"`
	// Required. The configuration of the synthesized audio.
	AudioConfig *AudioConfig `protobuf:"bytes,3,opt,name=audio_config,json=audioConfig,proto3" json:"audio_config,omitempty"`
	// Whether and what timepoints are returned in the response.
	EnableTimePointing []SynthesizeSpeechRequest_TimepointType `` /* 202-byte string literal not displayed */
	// contains filtered or unexported fields
}

type SynthesizeSpeechRequest_TimepointType int32

type SynthesizeSpeechResponse struct {

	// 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.
	AudioContent []byte `protobuf:"bytes,1,opt,name=audio_content,json=audioContent,proto3" json:"audio_content,omitempty"`
	// A link between a position in the original request input and a corresponding
	// time in the output audio. It's only supported via `<mark>` of SSML input.
	Timepoints []*Timepoint `protobuf:"bytes,2,rep,name=timepoints,proto3" json:"timepoints,omitempty"`
	// The audio metadata of `audio_content`.
	AudioConfig *AudioConfig `protobuf:"bytes,4,opt,name=audio_config,json=audioConfig,proto3" json:"audio_config,omitempty"`
	// contains filtered or unexported fields
}

type TextToSpeechClient interface {
	// Returns a list of Voice supported for synthesis.
	ListVoices(ctx context.Context, in *ListVoicesRequest, opts ...grpc.CallOption) (*ListVoicesResponse, error)
	// Synthesizes speech synchronously: receive results after all text input
	// has been processed.
	SynthesizeSpeech(ctx context.Context, in *SynthesizeSpeechRequest, opts ...grpc.CallOption) (*SynthesizeSpeechResponse, error)
}

type TextToSpeechLongAudioSynthesizeClient interface {
	// Synthesizes long form text asynchronously.
	SynthesizeLongAudio(ctx context.Context, in *SynthesizeLongAudioRequest, opts ...grpc.CallOption) (*longrunning.Operation, error)
}

type TextToSpeechLongAudioSynthesizeServer interface {
	// Synthesizes long form text asynchronously.
	SynthesizeLongAudio(context.Context, *SynthesizeLongAudioRequest) (*longrunning.Operation, error)
}

type TextToSpeechServer interface {
	// Returns a list of Voice supported for synthesis.
	ListVoices(context.Context, *ListVoicesRequest) (*ListVoicesResponse, error)
	// Synthesizes speech synchronously: receive results after all text input
	// has been processed.
	SynthesizeSpeech(context.Context, *SynthesizeSpeechRequest) (*SynthesizeSpeechResponse, error)
}

type Timepoint struct {

	// Timepoint name as received from the client within `<mark>` tag.
	MarkName string `protobuf:"bytes,4,opt,name=mark_name,json=markName,proto3" json:"mark_name,omitempty"`
	// Time offset in seconds from the start of the synthesized audio.
	TimeSeconds float64 `protobuf:"fixed64,3,opt,name=time_seconds,json=timeSeconds,proto3" json:"time_seconds,omitempty"`
	// contains filtered or unexported fields
}

type UnimplementedTextToSpeechLongAudioSynthesizeServer struct {
}

type UnimplementedTextToSpeechServer struct {
}

type Voice struct {

	// 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").
	LanguageCodes []string `protobuf:"bytes,1,rep,name=language_codes,json=languageCodes,proto3" json:"language_codes,omitempty"`
	// The name of this voice.  Each distinct voice has a unique name.
	Name string `protobuf:"bytes,2,opt,name=name,proto3" json:"name,omitempty"`
	// The gender of this voice.
	SsmlGender SsmlVoiceGender `` /* 147-byte string literal not displayed */
	// The natural sample rate (in hertz) for this voice.
	NaturalSampleRateHertz int32 `` /* 132-byte string literal not displayed */
	// contains filtered or unexported fields
}

type VoiceSelectionParams struct {

	// 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)".
	LanguageCode string `protobuf:"bytes,1,opt,name=language_code,json=languageCode,proto3" json:"language_code,omitempty"`
	// 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.
	Name string `protobuf:"bytes,2,opt,name=name,proto3" json:"name,omitempty"`
	// 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.
	SsmlGender SsmlVoiceGender `` /* 147-byte string literal not displayed */
	// The configuration for a custom voice. If [CustomVoiceParams.model] is set,
	// the service will choose the custom voice matching the specified
	// configuration.
	CustomVoice *CustomVoiceParams `protobuf:"bytes,4,opt,name=custom_voice,json=customVoice,proto3" json:"custom_voice,omitempty"`
	// contains filtered or unexported fields
}