v3beta1

v3beta1

Source:

Type Definitions

BatchTranslateMetadata

State metadata for the batch translation operation.

Properties:
Name Type Description
state number

The state of the operation.

The number should be among the values of State
translatedCharacters number

Number of successfully translated characters so far (Unicode codepoints).
failedCharacters number

Number of characters that have failed to process so far (Unicode codepoints).
totalCharacters number

Total number of characters (Unicode codepoints). This is the total number of codepoints from input files times the number of target languages and appears here shortly after the call is submitted.
submitTime Object

Time when the operation was submitted.

This object should have the same structure as Timestamp
Source:
See:

BatchTranslateResponse

Stored in the google.longrunning.Operation.response field returned by BatchTranslateText if at least one sentence is translated successfully.

Properties:
Name Type Description
totalCharacters number

Total number of characters (Unicode codepoints).
translatedCharacters number

Number of successfully translated characters (Unicode codepoints).
failedCharacters number

Number of characters that have failed to process (Unicode codepoints).
submitTime Object

Time when the operation was submitted.

This object should have the same structure as Timestamp
endTime Object

The time when the operation is finished and google.longrunning.Operation.done is set to true.

This object should have the same structure as Timestamp
Source:
See:

BatchTranslateTextRequest

The batch translation request.

Properties:
Name Type Description
parent string

Required. Location to make a call. Must refer to a caller's project.

Format: projects/{project-id}/locations/{location-id}.

The global location is not supported for batch translation.

Only AutoML Translation models or glossaries within the same region (have the same location-id) can be used, otherwise an INVALID_ARGUMENT (400) error is returned.
sourceLanguageCode string

Required. Source language code.
targetLanguageCodes Array.<string>

Required. Specify up to 10 language codes here.
models Object.<string, string>

Optional. The models to use for translation. Map's key is target language code. Map's value is model name. Value can be a built-in general model, or an AutoML Translation model.

The value format depends on model type:

  • AutoML Translation models: projects/{project-id}/locations/{location-id}/models/{model-id}

  • General (built-in) models: projects/{project-id}/locations/{location-id}/models/general/nmt, projects/{project-id}/locations/{location-id}/models/general/base

If the map is empty or a specific model is not requested for a language pair, then default google model (nmt) is used.
inputConfigs Array.<Object>

Required. Input configurations. The total number of files matched should be <= 1000. The total content size should be <= 100M Unicode codepoints. The files must use UTF-8 encoding.

This object should have the same structure as InputConfig
outputConfig Object

Required. Output configuration. If 2 input configs match to the same file (that is, same input path), we don't generate output for duplicate inputs.

This object should have the same structure as OutputConfig
glossaries Object.<string, Object>

Optional. Glossaries to be applied for translation. It's keyed by target language code.
labels Object.<string, string>

Optional. The labels with user-defined metadata for the request.

Label keys and values can be no longer than 63 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. Label values are optional. Label keys must start with a letter.

See https://cloud.google.com/translate/docs/labels for more information.
Source:
See:

CreateGlossaryMetadata

Stored in the google.longrunning.Operation.metadata field returned by CreateGlossary.

Properties:
Name Type Description
name string

The name of the glossary that is being created.
state number

The current state of the glossary creation operation.

The number should be among the values of State
submitTime Object

The time when the operation was submitted to the server.

This object should have the same structure as Timestamp
Source:
See:

CreateGlossaryRequest

Request message for CreateGlossary.

Properties:
Name Type Description
parent string

Required. The project name.
glossary Object

Required. The glossary to create.

This object should have the same structure as Glossary
Source:
See:

DeleteGlossaryMetadata

Stored in the google.longrunning.Operation.metadata field returned by DeleteGlossary.

Properties:
Name Type Description
name string

The name of the glossary that is being deleted.
state number

The current state of the glossary deletion operation.

The number should be among the values of State
submitTime Object

The time when the operation was submitted to the server.

This object should have the same structure as Timestamp
Source:
See:

DeleteGlossaryRequest

Request message for DeleteGlossary.

Properties:
Name Type Description
name string

Required. The name of the glossary to delete.
Source:
See:

DeleteGlossaryResponse

Stored in the google.longrunning.Operation.response field returned by DeleteGlossary.

Properties:
Name Type Description
name string

The name of the deleted glossary.
submitTime Object

The time when the operation was submitted to the server.

This object should have the same structure as Timestamp
endTime Object

The time when the glossary deletion is finished and google.longrunning.Operation.done is set to true.

This object should have the same structure as Timestamp
Source:
See:

DetectedLanguage

The response message for language detection.

Properties:
Name Type Description
languageCode string

The BCP-47 language code of source content in the request, detected automatically.
confidence number

The confidence of the detection result for this language.
Source:
See:

DetectLanguageRequest

The request message for language detection.

Properties:
Name Type Description
parent string

Required. Project or location to make a call. Must refer to a caller's project.

Format: projects/{project-id}/locations/{location-id} or projects/{project-id}.

For global calls, use projects/{project-id}/locations/global or projects/{project-id}.

Only models within the same region (has same location-id) can be used. Otherwise an INVALID_ARGUMENT (400) error is returned.
model string

Optional. The language detection model to be used.

Format: projects/{project-id}/locations/{location-id}/models/language-detection/{model-id}

Only one language detection model is currently supported: projects/{project-id}/locations/{location-id}/models/language-detection/default.

If not specified, the default model is used.
content string

The content of the input stored as a string.
mimeType string

Optional. The format of the source text, for example, "text/html", "text/plain". If left blank, the MIME type defaults to "text/html".
labels Object.<string, string>

Optional. The labels with user-defined metadata for the request.

Label keys and values can be no longer than 63 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. Label values are optional. Label keys must start with a letter.

See https://cloud.google.com/translate/docs/labels for more information.
Source:
See:

DetectLanguageResponse

The response message for language detection.

Properties:
Name Type Description
languages Array.<Object>

A list of detected languages sorted by detection confidence in descending order. The most probable language first.

This object should have the same structure as DetectedLanguage
Source:
See:

GcsDestination

The Google Cloud Storage location for the output content.

Properties:
Name Type Description
outputUriPrefix string

Required. There must be no files under 'output_uri_prefix'. 'output_uri_prefix' must end with "/" and start with "gs://", otherwise an INVALID_ARGUMENT (400) error is returned.
Source:
See:

GcsSource

The Google Cloud Storage location for the input content.

Properties:
Name Type Description
inputUri string

Required. Source data URI. For example, gs://my_bucket/my_object.
Source:
See:

GetGlossaryRequest

Request message for GetGlossary.

Properties:
Name Type Description
name string

Required. The name of the glossary to retrieve.
Source:
See:

GetSupportedLanguagesRequest

The request message for discovering supported languages.

Properties:
Name Type Description
parent string

Required. Project or location to make a call. Must refer to a caller's project.

Format: projects/{project-id} or projects/{project-id}/locations/{location-id}.

For global calls, use projects/{project-id}/locations/global or projects/{project-id}.

Non-global location is required for AutoML models.

Only models within the same region (have same location-id) can be used, otherwise an INVALID_ARGUMENT (400) error is returned.
displayLanguageCode string

Optional. The language to use to return localized, human readable names of supported languages. If missing, then display names are not returned in a response.
model string

Optional. Get supported languages of this model.

The format depends on model type:

  • AutoML Translation models: projects/{project-id}/locations/{location-id}/models/{model-id}

  • General (built-in) models: projects/{project-id}/locations/{location-id}/models/general/nmt, projects/{project-id}/locations/{location-id}/models/general/base

Returns languages supported by the specified model. If missing, we get supported languages of Google general base (PBMT) model.
Source:
See:

Glossary

Represents a glossary built from user provided data.

Properties:
Name Type Description
name string

Required. The resource name of the glossary. Glossary names have the form projects/{project-id}/locations/{location-id}/glossaries/{glossary-id}.
languagePair Object

Used with unidirectional glossaries.

This object should have the same structure as LanguageCodePair
languageCodesSet Object

Used with equivalent term set glossaries.

This object should have the same structure as LanguageCodesSet
inputConfig Object

Required. Provides examples to build the glossary from. Total glossary must not exceed 10M Unicode codepoints.

This object should have the same structure as GlossaryInputConfig
entryCount number

Output only. The number of entries defined in the glossary.
submitTime Object

Output only. When CreateGlossary was called.

This object should have the same structure as Timestamp
endTime Object

Output only. When the glossary creation was finished.

This object should have the same structure as Timestamp
Source:
See:

GlossaryInputConfig

Input configuration for glossaries.

Properties:
Name Type Description
gcsSource Object

Required. Google Cloud Storage location of glossary data. File format is determined based on the filename extension. API returns [google.rpc.Code.INVALID_ARGUMENT] for unsupported URI-s and file formats. Wildcards are not allowed. This must be a single file in one of the following formats:

For unidirectional glossaries:

  • TSV/CSV (.tsv/.csv): 2 column file, tab- or comma-separated. The first column is source text. The second column is target text. The file must not contain headers. That is, the first row is data, not column names.

  • TMX (.tmx): TMX file with parallel data defining source/target term pairs.

For equivalent term sets glossaries:

  • CSV (.csv): Multi-column CSV file defining equivalent glossary terms in multiple languages. The format is defined for Google Translation Toolkit and documented in Use a glossary.

This object should have the same structure as GcsSource
Source:
See:

InputConfig

Input configuration for BatchTranslateText request.

Properties:
Name Type Description
mimeType string

Optional. Can be "text/plain" or "text/html". For .tsv, "text/html" is used if mime_type is missing. For .html, this field must be "text/html" or empty. For .txt, this field must be "text/plain" or empty.
gcsSource Object

Required. Google Cloud Storage location for the source input. This can be a single file (for example, gs://translation-test/input.tsv) or a wildcard (for example, gs://translation-test/*). If a file extension is .tsv, it can contain either one or two columns. The first column (optional) is the id of the text request. If the first column is missing, we use the row number (0-based) from the input file as the ID in the output file. The second column is the actual text to be translated. We recommend each row be <= 10K Unicode codepoints, otherwise an error might be returned. Note that the input tsv must be RFC 4180 compliant.

You could use https://github.com/Clever/csvlint to check potential formatting errors in your tsv file. csvlint --delimiter='\t' your_input_file.tsv

The other supported file extensions are .txt or .html, which is treated as a single large chunk of text.

This object should have the same structure as GcsSource
Source:
See:

LanguageCodePair

Used with unidirectional glossaries.

Properties:
Name Type Description
sourceLanguageCode string

Required. The BCP-47 language code of the input text, for example, "en-US". Expected to be an exact match for GlossaryTerm.language_code.
targetLanguageCode string

Required. The BCP-47 language code for translation output, for example, "zh-CN". Expected to be an exact match for GlossaryTerm.language_code.
Source:
See:

LanguageCodesSet

Used with equivalent term set glossaries.

Properties:
Name Type Description
languageCodes Array.<string>

The BCP-47 language code(s) for terms defined in the glossary. All entries are unique. The list contains at least two entries. Expected to be an exact match for GlossaryTerm.language_code.
Source:
See:

ListGlossariesRequest

Request message for ListGlossaries.

Properties:
Name Type Description
parent string

Required. The name of the project from which to list all of the glossaries.
pageSize number

Optional. Requested page size. The server may return fewer glossaries than requested. If unspecified, the server picks an appropriate default.
pageToken string

Optional. A token identifying a page of results the server should return. Typically, this is the value of [ListGlossariesResponse.next_page_token] returned from the previous call to ListGlossaries method. The first page is returned if page_tokenis empty or missing.
filter string

Optional. Filter specifying constraints of a list operation. Filtering is not supported yet, and the parameter currently has no effect. If missing, no filtering is performed.
Source:
See:

ListGlossariesResponse

Response message for ListGlossaries.

Properties:
Name Type Description
glossaries Array.<Object>

The list of glossaries for a project.

This object should have the same structure as Glossary
nextPageToken string

A token to retrieve a page of results. Pass this value in the [ListGlossariesRequest.page_token] field in the subsequent call to ListGlossaries method to retrieve the next page of results.
Source:
See:

OutputConfig

Output configuration for BatchTranslateText request.

Properties:
Name Type Description
gcsDestination Object

Google Cloud Storage destination for output content. For every single input file (for example, gs://a/b/c.[extension]), we generate at most 2 * n output files. (n is the # of target_language_codes in the BatchTranslateTextRequest).

Output files (tsv) generated are compliant with RFC 4180 except that record delimiters are '\n' instead of '\r\n'. We don't provide any way to change record delimiters.

While the input files are being processed, we write/update an index file 'index.csv' under 'output_uri_prefix' (for example, gs://translation-test/index.csv) The index file is generated/updated as new files are being translated. The format is:

input_file,target_language_code,translations_file,errors_file, glossary_translations_file,glossary_errors_file

input_file is one file we matched using gcs_source.input_uri. target_language_code is provided in the request. translations_file contains the translations. (details provided below) errors_file contains the errors during processing of the file. (details below). Both translations_file and errors_file could be empty strings if we have no content to output. glossary_translations_file and glossary_errors_file are always empty strings if the input_file is tsv. They could also be empty if we have no content to output.

Once a row is present in index.csv, the input/output matching never changes. Callers should also expect all the content in input_file are processed and ready to be consumed (that is, no partial output file is written).

The format of translations_file (for target language code 'trg') is: gs://translation_test/a_b_c_'trg'_translations.[extension]

If the input file extension is tsv, the output has the following columns: Column 1: ID of the request provided in the input, if it's not provided in the input, then the input row number is used (0-based). Column 2: source sentence. Column 3: translation without applying a glossary. Empty string if there is an error. Column 4 (only present if a glossary is provided in the request): translation after applying the glossary. Empty string if there is an error applying the glossary. Could be same string as column 3 if there is no glossary applied.

If input file extension is a txt or html, the translation is directly written to the output file. If glossary is requested, a separate glossary_translations_file has format of gs://translation_test/a_b_c_'trg'_glossary_translations.[extension]

The format of errors file (for target language code 'trg') is: gs://translation_test/a_b_c_'trg'_errors.[extension]

If the input file extension is tsv, errors_file contains the following: Column 1: ID of the request provided in the input, if it's not provided in the input, then the input row number is used (0-based). Column 2: source sentence. Column 3: Error detail for the translation. Could be empty. Column 4 (only present if a glossary is provided in the request): Error when applying the glossary.

If the input file extension is txt or html, glossary_error_file will be generated that contains error details. glossary_error_file has format of gs://translation_test/a_b_c_'trg'_glossary_errors.[extension]

This object should have the same structure as GcsDestination
Source:
See:

SupportedLanguage

A single supported language response corresponds to information related to one supported language.

Properties:
Name Type Description
languageCode string

Supported language code, generally consisting of its ISO 639-1 identifier, for example, 'en', 'ja'. In certain cases, BCP-47 codes including language and region identifiers are returned (for example, 'zh-TW' and 'zh-CN')
displayName string

Human readable name of the language localized in the display language specified in the request.
supportSource boolean

Can be used as source language.
supportTarget boolean

Can be used as target language.
Source:
See:

SupportedLanguages

The response message for discovering supported languages.

Properties:
Name Type Description
languages Array.<Object>

A list of supported language responses. This list contains an entry for each language the Translation API supports.

This object should have the same structure as SupportedLanguage
Source:
See:

TranslateTextGlossaryConfig

Configures which glossary should be used for a specific target language, and defines options for applying that glossary.

Properties:
Name Type Description
glossary string

Required. Specifies the glossary used for this translation. Use this format: projects/* /locations/* /glossaries/*
ignoreCase boolean

Optional. Indicates match is case-insensitive. Default value is false if missing.
Source:
See:

TranslateTextRequest

The request message for synchronous translation.

Properties:
Name Type Description
contents Array.<string>

Required. The content of the input in string format. We recommend the total content be less than 30k codepoints. Use BatchTranslateText for larger text.
mimeType string

Optional. The format of the source text, for example, "text/html", "text/plain". If left blank, the MIME type defaults to "text/html".
sourceLanguageCode string

Optional. The BCP-47 language code of the input text if known, for example, "en-US" or "sr-Latn". Supported language codes are listed in Language Support. If the source language isn't specified, the API attempts to identify the source language automatically and returns the source language within the response.
targetLanguageCode string

Required. The BCP-47 language code to use for translation of the input text, set to one of the language codes listed in Language Support.
parent string

Required. Project or location to make a call. Must refer to a caller's project.

Format: projects/{project-id} or projects/{project-id}/locations/{location-id}.

For global calls, use projects/{project-id}/locations/global or projects/{project-id}.

Non-global location is required for requests using AutoML models or custom glossaries.

Models and glossaries must be within the same region (have same location-id), otherwise an INVALID_ARGUMENT (400) error is returned.
model string

Optional. The model type requested for this translation.

The format depends on model type:

  • AutoML Translation models: projects/{project-id}/locations/{location-id}/models/{model-id}

  • General (built-in) models: projects/{project-id}/locations/{location-id}/models/general/nmt, projects/{project-id}/locations/{location-id}/models/general/base

For global (non-regionalized) requests, use location-id global. For example, projects/{project-id}/locations/global/models/general/nmt.

If missing, the system decides which google base model to use.
glossaryConfig Object

Optional. Glossary to be applied. The glossary must be within the same region (have the same location-id) as the model, otherwise an INVALID_ARGUMENT (400) error is returned.

This object should have the same structure as TranslateTextGlossaryConfig
labels Object.<string, string>

Optional. The labels with user-defined metadata for the request.

Label keys and values can be no longer than 63 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. Label values are optional. Label keys must start with a letter.

See https://cloud.google.com/translate/docs/labels for more information.
Source:
See:

TranslateTextResponse

Properties:
Name Type Description
translations Array.<Object>

Text translation responses with no glossary applied. This field has the same length as contents.

This object should have the same structure as Translation
glossaryTranslations Array.<Object>

Text translation responses if a glossary is provided in the request. This can be the same as translations if no terms apply. This field has the same length as contents.

This object should have the same structure as Translation
Source:
See:

Translation

A single translation response.

Properties:
Name Type Description
translatedText string

Text translated into the target language.
model string

Only present when model is present in the request. This is same as model provided in the request.
detectedLanguageCode string

The BCP-47 language code of source text in the initial request, detected automatically, if no source language was passed within the initial request. If the source language was passed, auto-detection of the language does not occur and this field is empty.
glossaryConfig Object

The glossary_config used for this translation.

This object should have the same structure as TranslateTextGlossaryConfig
Source:
See: