package sagittarius.translation.v1

Get desktop application:
View/edit binary Protocol Buffers messages

Service that implements Sagittarius Translation API

• rpc DetectLanguage (DetectionRequest, DetectionResponse)

  translation.proto:41

  detect the language of text

  message DetectionRequest

  translation.proto:146

  • string text = 1

    the text to be detect

  message DetectionResponse

  translation.proto:151

  • repeated DetectionPrediction prediction = 1

    there might be more than one prediction

• rpc GetUserQuota (UserQuotaRequest, UserQuotaResponse)

  translation.proto:87

  Get User Quota

  message UserQuotaRequest

  translation.proto:374

  (message has no fields)

  message UserQuotaResponse

  translation.proto:379

  Remaining user quota

  • int64 quota = 1

    remaining user quota in number

  • int64 time_left = 2

    remaining quota in time(second)

  • optional google.rpc.Status error = 3

• rpc ProcessOrder (ProcessOrderRequest, ProcessOrderResponse)

  translation.proto:79

  Start an unpaid or failed order for internal use only

  message ProcessOrderRequest

  translation.proto:387

  • int64 order_id = 1

    id of the order

  • string audio_uri = 2

    uri to get the audio file

  • optional google.cloud.speech.v1.RecognitionConfig audio_config = 3

    information of the audio file

  message ProcessOrderResponse

  translation.proto:396

  • optional google.rpc.Status error = 1

  • int64 order_status = 2

• rpc StreamingTranslation (stream StreamingTranslationRequest, stream StreamingTranslationResponse)

  translation.proto:65

  Performs bidirectional streaming audio translation: receive results after or while sending audio. This method is only available via the gRPC API (not REST).

  message StreamingTranslationRequest

  translation.proto:199

  The top-level message sent by the client for the `StreamingTranslation` method. Multiple `StreamingTranslationRequest` messages are sent. The first message must contain a `streaming_config` message and must not contain `audio` data. All subsequent messages must contain `audio` data and must not contain a `streaming_config` message.

  • oneof streaming_request

    The streaming request, which is either a streaming config or audio content.

    • StreamingTranslationRequestConfig streaming_config = 1

    • bytes audio_content = 2

      The audio data to be recognized. Sequential chunks of audio data are sent in sequential `StreamingTranslationRequest` messages. The first `StreamingTranslationRequest` message must not contain `audio_content` data and all subsequent `StreamingTranslationRequest` messages must contain `audio_content` data. The audio bytes must be encoded as specified in `RecognitionConfig`. Note: as with all bytes fields, protobuffers use a pure binary representation (not base64). See [audio limits](https://cloud.google.com/speech/limits#content).

  message StreamingTranslationResponse

  translation.proto:241

  The top-level message sent by server for the `StreamingTranslation` method. Multiple `StreamingTranslationResponse` messages may be sent.

  • optional google.rpc.Status error = 1

    *Output-only* If set, returns a [google.rpc.Status][google.rpc.Status] message that specifies the error for the operation.

  • oneof streaming_response

    streaming_response must be one of following

    • StreamingTranslationResult streaming_result = 2

      *Output-only* If the request is suit for streaming result, This contains results that correspond to consecutive portions of the audio currently being processed.

    • StreamingTranslationTaskInfo taskinfo = 3

      *Output-only* If StreamingTranslationTask has been created for farther inquiry this is the task info include id and estimated finish time, etc.

    • TranscriptInfo transcript_result = 4

      *Output-only* If the StreamingTranslationTask has finished and the client still alive this is the translated transcript in whole

• rpc StreamingTranslationTask (StreamingTranslationTaskRequest, StreamingTranslationTaskResponse)

  translation.proto:70

  Check StreamingTranslationTask results or estimate finish time and maybe other informations related to the task

  message StreamingTranslationTaskRequest

  translation.proto:263

  the StreamingTranslationTask id that created by the `StreamingTranslation` method.

  • string task_id = 1

  message StreamingTranslationTaskResponse

  translation.proto:268

  the translated TranscriptInfo or `StreamingTranslationTaskInfo`

  • optional google.rpc.Status error = 1

    maybe be: StreamingTranslationTaskCode.CONTINUE StreamingTranslationTaskCode.SKIP_AUDIO

  • oneof streaming_request

    • StreamingTranslationTaskInfo taskinfo = 2

    • TranscriptInfo transcriptinfo = 3

      can return result

• rpc Transcript (TranscriptRequest, TranscriptResponse)

  translation.proto:48

  message TranscriptRequest

  translation.proto:166

  • string transcript_identity = 4

    oneof case 2 return translate result by transcript_identity

  • double start_time = 6

    position of the transcript relative to the begginning of the audio or video

  message TranscriptResponse

  translation.proto:175

  • optional google.rpc.Status error = 1

  • repeated TranscriptResponse.Cue transcripts = 2

    each line of the transcript

  • bool is_end_of_transcript = 3

    if transcripts ended in this result

• rpc TranslateMedia (MediaTranslationRequest, MediaTranslationResponse)

  translation.proto:33

  Translate media(audio or video) by media identity

  message MediaTranslationRequest

  translation.proto:92

  • string media_identity = 1

    Media Identity

  • string language_code = 2

    target language ISO-639-1 Code https://cloud.google.com/translate/docs/languages

  • string format = 3

    the format of the transcripts

  • double start_time = 6

    position of the transcript relative to the begginning of the audio or video

  • string hints = 7

    hints or keywords for more possible results

  message MediaTranslationResponse

  translation.proto:110

  • optional google.rpc.Status error = 1

    *Output-only* If set, returns a [google.rpc.Status][google.rpc.Status] message that specifies the error for the operation. return 404 if no result, in this case, client should use StreamingTranslationRequest

  • repeated TranscriptInfo results = 2

    best translation results

  • string stream_translation_task_id = 3

    if there is a stream translation task running, return task id

• rpc TranslateText (TextTranslationRequest, TextTranslationResponse)

  translation.proto:56

  Translate text by Google Translation Service

  message TextTranslationRequest

  translation.proto:342

  We use Google Translation Service for text translation. Translation API Reference: https://cloud.google.com/translate/docs/reference/translate

  • repeated string text = 1

    The text to translate

  • string target_language_code = 2

    The language to use for translation of the text ISO-639-1/bcp47 Code with tags https://cloud.google.com/translate/docs/languages

  • string source_language_code = 3

    The language of the source text ISO-639-1/bcp47 Code with tags https://cloud.google.com/translate/docs/languages

  message TextTranslationResponse

  translation.proto:357

  • optional google.rpc.Status error = 1

  • repeated TextTranslationResponse.Text results = 2

    translation results for the requested text

Used in: DetectionResponse

• string language_code = 1

  *Output-only* the language code of the detection result

• float confidence = 2

  *Output-only* The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the detection result are correct.

Used in: StreamingTranslationRequest

• optional google.cloud.speech.v1.RecognitionConfig streaming_config = 1

  Provides information to the recognizer that specifies how to process the request. The first `StreamingTranslationRequest` message must contain a `streaming_config` message.

• string media_identity = 2

  the media identity

• string audio_language_code = 3

  the language code of the audio ISO-639-1 Code https://cloud.google.com/translate/docs/languages

• string target_language_code = 4

  ISO-639-1 Code https://cloud.google.com/translate/docs/languages

• string audio_track = 5

  the track of audio

• string hints = 6

  maybe video or file name

Used in: StreamingTranslationResponse

• string transcript = 1

  *Output-only* Transcript text representing the words that the user spoke.

• float confidence = 2

  *Output-only* The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is typically provided only for the top hypothesis, and only for `is_final=true` results. Clients should not rely on the `confidence` field as it is not guaranteed to be accurate or consistent. The default of 0.0 is a sentinel value indicating `confidence` was not set.

• float stability = 3

  *Output-only* An estimate of the likelihood that the recognizer will not change its guess about this interim result. Values range from 0.0 (completely unstable) to 1.0 (completely stable). This field is only provided for interim results (`is_final=false`). The default of 0.0 is a sentinel value indicating `stability` was not set.

• double start_time = 4

  *Output-only* Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.

• double end_time = 5

  *Output-only* Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.

The canonical error codes for StreamingTranslationTaskResponse

• OK = 0

  The first enum value must be zero in proto3.

• CONTINUE = 9100

  instruct client to continue sending audio data

• SKIP_AUDIO = 9101

  instruct client to skip sending audio data

the StreamingTranslationTask that created by the `StreamingTranslation` method.

Used in: StreamingTranslationResponse, StreamingTranslationTaskResponse

• string task_id = 1

  this task id can be used for farther inquiry

• double estimate_time = 2

  this is the estimated finished time, the task is finished if the time is zero or less

Used in: TextTranslationResponse

• string source_language = 1

  The source language of the text detected ISO-639-1/bcp47 Code with tags https://cloud.google.com/translate/docs/languages

• string text = 2

  The translated Text

Used in: MediaTranslationResponse, StreamingTranslationResponse, StreamingTranslationTaskResponse

• string transcript_identity = 1

  the identity, can be used in TranslationRequest

• string language_code = 2

  ISO-639-1 Code https://cloud.google.com/translate/docs/languages

• float ranking = 3

  actually we should use as "confidence" use "ranking" for back ward competibility

• repeated string tags = 4

  maybe: "ai" - result from ai tranlation "edited" - result from user contribution

• int64 delay = 5

  in ms, can be +/-

• float confidence = 6

  the confidence of the quality of the translation

Used in: TranscriptResponse

• double start_time = 1

  the start and end of the transcripts

• double end_time = 2

• string text = 3