mediatranslation

type SpeechTranslationServiceClient interface {
	// Performs bidirectional streaming speech translation: receive results while
	// sending audio. This method is only available via the gRPC API (not REST).
	StreamingTranslateSpeech(ctx context.Context, opts ...grpc.CallOption) (SpeechTranslationService_StreamingTranslateSpeechClient, error)
}

type SpeechTranslationServiceServer interface {
	// Performs bidirectional streaming speech translation: receive results while
	// sending audio. This method is only available via the gRPC API (not REST).
	StreamingTranslateSpeech(SpeechTranslationService_StreamingTranslateSpeechServer) error
}

type SpeechTranslationService_StreamingTranslateSpeechClient interface {
	Send(*StreamingTranslateSpeechRequest) error
	Recv() (*StreamingTranslateSpeechResponse, error)
	grpc.ClientStream
}

type SpeechTranslationService_StreamingTranslateSpeechServer interface {
	Send(*StreamingTranslateSpeechResponse) error
	Recv() (*StreamingTranslateSpeechRequest, error)
	grpc.ServerStream
}

type StreamingTranslateSpeechConfig struct {

	// Required. The common config for all the following audio contents.
	AudioConfig *TranslateSpeechConfig `protobuf:"bytes,1,opt,name=audio_config,json=audioConfig,proto3" json:"audio_config,omitempty"`
	// Optional. If `false` or omitted, the system performs
	// continuous translation (continuing to wait for and process audio even if
	// the user pauses speaking) until the client closes the input stream (gRPC
	// API) or until the maximum time limit has been reached. May return multiple
	// `StreamingTranslateSpeechResult`s with the `is_final` flag set to `true`.
	//
	// If `true`, the speech translator will detect a single spoken utterance.
	// When it detects that the user has paused or stopped speaking, it will
	// return an `END_OF_SINGLE_UTTERANCE` event and cease translation.
	// When the client receives `END_OF_SINGLE_UTTERANCE` event, the client should
	// stop sending the requests. However, clients should keep receiving remaining
	// responses until the stream is terminated. To construct the complete
	// sentence in a streaming way, one should override (if `is_final` of previous
	// response is false), or append (if 'is_final' of previous response is true).
	SingleUtterance bool `protobuf:"varint,2,opt,name=single_utterance,json=singleUtterance,proto3" json:"single_utterance,omitempty"`
	// Optional. Stability control for the media translation text. The value should be
	// "LOW", "MEDIUM", "HIGH". It applies to text/text_and_audio translation
	// only.
	// For audio translation mode, we only support HIGH stability mode,
	// low/medium stability mode will throw argument error.
	// Default empty string will be treated as "HIGH" in audio translation mode;
	// will be treated as "LOW" in other translation mode.
	// Note that stability and speed would be trade off.
	// 1. "LOW": In low mode, translation service will start to do translation
	// right after getting recognition response. The speed will be faster.
	// 2. "MEDIUM": In medium mode, translation service will
	// check if the recognition response is stable enough or not, and only
	// translate recognition response which is not likely to be changed later.
	// 3. "HIGH": In high mode, translation service will wait for more stable
	// recognition responses, and then start to do translation. Also, the
	// following recognition responses cannot modify previous recognition
	// responses. Thus it may impact quality in some situation. "HIGH" stability
	// will generate "final" responses more frequently.
	//
	Stability string `protobuf:"bytes,3,opt,name=stability,proto3" json:"stability,omitempty"`
	// Optional. Translation mode, the value should be "text", "audio", "text_and_audio".
	// Default empty string will be treated as "text".
	// 1. "text": The response will be text translation. Text translation has a
	// field "is_final". Detailed definition can be found in
	// `TextTranslationResult`.
	// 2. "audio": The response will be audio translation. Audio translation does
	// not have "is_final" field, which means each audio translation response is
	// stable and will not be changed by later response.
	// Translation mode "audio" can only be used with "high" stability mode,
	// 3. "text_and_audio": The response will have a text translation, when
	// "is_final" is true, we will also output its corresponding audio
	// translation. When "is_final" is false, audio_translation field will be
	// empty.
	TranslationMode string `protobuf:"bytes,4,opt,name=translation_mode,json=translationMode,proto3" json:"translation_mode,omitempty"`
	// Optional. If disable_interim_results is true, we will only return "final" responses.
	// Otherwise, we will return all the responses. Default value will be false.
	// User can only set disable_interim_results to be true with "high" stability
	// mode.
	DisableInterimResults bool `` /* 127-byte string literal not displayed */
	// contains filtered or unexported fields
}

type StreamingTranslateSpeechRequest struct {

	// The streaming request, which is either a streaming config or content.
	//
	// Types that are assignable to StreamingRequest:
	//	*StreamingTranslateSpeechRequest_StreamingConfig
	//	*StreamingTranslateSpeechRequest_AudioContent
	StreamingRequest isStreamingTranslateSpeechRequest_StreamingRequest `protobuf_oneof:"streaming_request"`
	// contains filtered or unexported fields
}

type StreamingTranslateSpeechRequest_AudioContent struct {
	// The audio data to be translated. Sequential chunks of audio data are sent
	// in sequential `StreamingTranslateSpeechRequest` messages. The first
	// `StreamingTranslateSpeechRequest` message must not contain
	// `audio_content` data and all subsequent `StreamingTranslateSpeechRequest`
	// messages must contain `audio_content` data. The audio bytes must be
	// encoded as specified in `StreamingTranslateSpeechConfig`. Note: as with
	// all bytes fields, protobuffers use a pure binary representation (not
	// base64).
	AudioContent []byte `protobuf:"bytes,2,opt,name=audio_content,json=audioContent,proto3,oneof"`
}

type StreamingTranslateSpeechRequest_StreamingConfig struct {
	// Provides information to the recognizer that specifies how to process the
	// request. The first `StreamingTranslateSpeechRequest` message must contain
	// a `streaming_config` message.
	StreamingConfig *StreamingTranslateSpeechConfig `protobuf:"bytes,1,opt,name=streaming_config,json=streamingConfig,proto3,oneof"`
}

type StreamingTranslateSpeechResponse struct {

	// Output only. If set, returns a [google.rpc.Status][google.rpc.Status] message that
	// specifies the error for the operation.
	Error *status.Status `protobuf:"bytes,1,opt,name=error,proto3" json:"error,omitempty"`
	// Output only. The translation result that is currently being processed (For text
	// translation, `is_final` could be `true` or `false`.
	// For audio translation, we do not have is_final field, which means each
	// audio response is stable and will not get changed later. For
	// text_and_audio, we still have `is_final` field in text translation, but we
	// only output corresponsding audio when `is_final` is true.).
	Result *StreamingTranslateSpeechResult `protobuf:"bytes,2,opt,name=result,proto3" json:"result,omitempty"`
	// Output only. Indicates the type of speech event.
	SpeechEventType StreamingTranslateSpeechResponse_SpeechEventType `` /* 202-byte string literal not displayed */
	// contains filtered or unexported fields
}

type StreamingTranslateSpeechResponse_SpeechEventType int32

type StreamingTranslateSpeechResult struct {

	// Text translation result.
	TextTranslationResult *StreamingTranslateSpeechResult_TextTranslationResult `` /* 126-byte string literal not displayed */
	// Audio translation result.
	AudioTranslationResult *StreamingTranslateSpeechResult_AudioTranslationResult `` /* 129-byte string literal not displayed */
	// Output only. The debug only recognition result in original language. This field is debug
	// only and will be set to empty string if not available.
	// This is implementation detail and will not be backward compatible.
	RecognitionResult string `protobuf:"bytes,3,opt,name=recognition_result,json=recognitionResult,proto3" json:"recognition_result,omitempty"`
	// Output only.
	DetectedSourceLanguageCode string `` /* 143-byte string literal not displayed */
	// contains filtered or unexported fields
}

type StreamingTranslateSpeechResult_AudioTranslationResult struct {

	// Output only. The translated audio.
	AudioTranslation []byte `protobuf:"bytes,1,opt,name=audio_translation,json=audioTranslation,proto3" json:"audio_translation,omitempty"`
	// contains filtered or unexported fields
}

type StreamingTranslateSpeechResult_TextTranslationResult struct {

	// Output only. The translated sentence.
	Translation string `protobuf:"bytes,1,opt,name=translation,proto3" json:"translation,omitempty"`
	// Output only. If `false`, this `StreamingTranslateSpeechResult` represents
	// an interim result that may change. If `true`, this is the final time the
	// translation service will return this particular
	// `StreamingTranslateSpeechResult`, the streaming translator will not
	// return any further hypotheses for this portion of the transcript and
	// corresponding audio.
	IsFinal bool `protobuf:"varint,2,opt,name=is_final,json=isFinal,proto3" json:"is_final,omitempty"`
	// contains filtered or unexported fields
}

type TranslateSpeechConfig struct {

	// Required. Encoding of audio data.
	// Supported formats:
	//
	// - `linear16`
	//
	//   Uncompressed 16-bit signed little-endian samples (Linear PCM).
	//
	// - `flac`
	//
	//   `flac` (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`.
	//
	// - `mulaw`
	//
	//   8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
	//
	// - `amr`
	//
	//   Adaptive Multi-Rate Narrowband codec. `sample_rate_hertz` must be 8000.
	//
	// - `amr-wb`
	//
	//   Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` must be 16000.
	//
	// - `ogg-opus`
	//
	//   Opus encoded audio frames in Ogg container
	//   ([OggOpus](https://wiki.xiph.org/OggOpus)).
	//   `sample_rate_hertz` must be one of 8000, 12000, 16000, 24000, or 48000.
	//
	// - `mp3`
	//
	//   MP3 audio. Support all standard MP3 bitrates (which range from 32-320
	//   kbps). When using this encoding, `sample_rate_hertz` has to match the
	//   sample rate of the file being used.
	//
	//
	AudioEncoding string `protobuf:"bytes,1,opt,name=audio_encoding,json=audioEncoding,proto3" json:"audio_encoding,omitempty"`
	// Required. Source language code (BCP-47) of the input audio.
	SourceLanguageCode string `protobuf:"bytes,2,opt,name=source_language_code,json=sourceLanguageCode,proto3" json:"source_language_code,omitempty"`
	// Required. Target language code (BCP-47) of the output.
	TargetLanguageCode string `protobuf:"bytes,3,opt,name=target_language_code,json=targetLanguageCode,proto3" json:"target_language_code,omitempty"`
	// Optional. A list of up to 3 additional language codes (BCP-47), listing possible
	// alternative languages of the supplied audio. If alternative source
	// languages are listed, speech translation result will translate in the most
	// likely language detected including the main source_language_code. The
	// translated result will include the language code of the language detected
	// in the audio.
	// Note:
	// 1. If the provided alternative_source_language_code is not supported
	// by current API version, we will skip that language code.
	// 2. If user only provided one eligible alternative_source_language_codes,
	// the translation will happen between source_language_code and
	// alternative_source_language_codes. The target_language_code will be
	// ignored. It will be useful in conversation mode.
	AlternativeSourceLanguageCodes []string `` /* 155-byte string literal not displayed */
	// Optional. Sample rate in Hertz of the audio data. Valid values are:
	// 8000-48000. 16000 is optimal. For best results, set the sampling rate of
	// the audio source to 16000 Hz. If that's not possible, use the native sample
	// rate of the audio source (instead of re-sampling).
	//
	SampleRateHertz int32 `protobuf:"varint,4,opt,name=sample_rate_hertz,json=sampleRateHertz,proto3" json:"sample_rate_hertz,omitempty"`
	// Optional.
	Model string `protobuf:"bytes,5,opt,name=model,proto3" json:"model,omitempty"`
	// contains filtered or unexported fields
}

type UnimplementedSpeechTranslationServiceServer struct {
}