CreateVocabularyFilter - Amazon Transcribe

CreateVocabularyFilter

Creates a new custom vocabulary filter.

You can use custom vocabulary filters to mask, delete, or flag specific words from your transcript. Custom vocabulary filters are commonly used to mask profanity in transcripts.

Each language has a character set that contains all allowed characters for that specific language. If you use unsupported characters, your custom vocabulary filter request fails. Refer to Character Sets for Custom Vocabularies to get the character set for your language.

For more information, see Vocabulary filtering.

Request Syntax

{ "DataAccessRoleArn": "string", "LanguageCode": "string", "Tags": [ { "Key": "string", "Value": "string" } ], "VocabularyFilterFileUri": "string", "VocabularyFilterName": "string", "Words": [ "string" ] }

Request Parameters

For information about the parameters that are common to all actions, see Common Parameters.

The request accepts the following data in JSON format.

DataAccessRoleArn

The Amazon Resource Name (ARN) of an IAM role that has permissions to access the Amazon S3 bucket that contains your input files (in this case, your custom vocabulary filter). If the role that you specify doesn’t have the appropriate permissions to access the specified Amazon S3 location, your request fails.

IAM role ARNs have the format arn:partition:iam::account:role/role-name-with-path. For example: arn:aws:iam::111122223333:role/Admin.

For more information, see IAM ARNs.

Type: String

Length Constraints: Minimum length of 20. Maximum length of 2048.

Pattern: ^arn:(aws|aws-cn|aws-us-gov|aws-iso-{0,1}[a-z]{0,1}):iam::[0-9]{0,63}:role/[A-Za-z0-9:_/+=,@.-]{0,1024}$

Required: No

LanguageCode

The language code that represents the language of the entries in your vocabulary filter. Each custom vocabulary filter must contain terms in only one language.

A custom vocabulary filter can only be used to transcribe files in the same language as the filter. For example, if you create a custom vocabulary filter using US English (en-US), you can only apply this filter to files that contain English audio.

For a list of supported languages and their associated language codes, refer to the Supported languages table.

Type: String

Valid Values: af-ZA | ar-AE | ar-SA | da-DK | de-CH | de-DE | en-AB | en-AU | en-GB | en-IE | en-IN | en-US | en-WL | es-ES | es-US | fa-IR | fr-CA | fr-FR | he-IL | hi-IN | id-ID | it-IT | ja-JP | ko-KR | ms-MY | nl-NL | pt-BR | pt-PT | ru-RU | ta-IN | te-IN | tr-TR | zh-CN | zh-TW | th-TH | en-ZA | en-NZ | vi-VN | sv-SE

Required: Yes

Tags

Adds one or more custom tags, each in the form of a key:value pair, to a new custom vocabulary filter at the time you create this new vocabulary filter.

To learn more about using tags with Amazon Transcribe, refer to Tagging resources.

Type: Array of Tag objects

Array Members: Minimum number of 1 item. Maximum number of 200 items.

Required: No

VocabularyFilterFileUri

The Amazon S3 location of the text file that contains your custom vocabulary filter terms. The URI must be located in the same AWS Region as the resource you're calling.

Here's an example URI path: s3://DOC-EXAMPLE-BUCKET/my-vocab-filter-file.txt

Note that if you include VocabularyFilterFileUri in your request, you cannot use Words; you must choose one or the other.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 2000.

Pattern: (s3://|http(s*)://).+

Required: No

VocabularyFilterName

A unique name, chosen by you, for your new custom vocabulary filter.

This name is case sensitive, cannot contain spaces, and must be unique within an AWS account. If you try to create a new custom vocabulary filter with the same name as an existing custom vocabulary filter, you get a ConflictException error.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 200.

Pattern: ^[0-9a-zA-Z._-]+

Required: Yes

Words

Use this parameter if you want to create your custom vocabulary filter by including all desired terms, as comma-separated values, within your request. The other option for creating your vocabulary filter is to save your entries in a text file and upload them to an Amazon S3 bucket, then specify the location of your file using the VocabularyFilterFileUri parameter.

Note that if you include Words in your request, you cannot use VocabularyFilterFileUri; you must choose one or the other.

Each language has a character set that contains all allowed characters for that specific language. If you use unsupported characters, your custom vocabulary filter request fails. Refer to Character Sets for Custom Vocabularies to get the character set for your language.

Type: Array of strings

Array Members: Minimum number of 1 item.

Length Constraints: Minimum length of 1. Maximum length of 256.

Required: No

Response Syntax

{ "LanguageCode": "string", "LastModifiedTime": number, "VocabularyFilterName": "string" }

Response Elements

If the action is successful, the service sends back an HTTP 200 response.

The following data is returned in JSON format by the service.

LanguageCode

The language code you selected for your custom vocabulary filter.

Type: String

Valid Values: af-ZA | ar-AE | ar-SA | da-DK | de-CH | de-DE | en-AB | en-AU | en-GB | en-IE | en-IN | en-US | en-WL | es-ES | es-US | fa-IR | fr-CA | fr-FR | he-IL | hi-IN | id-ID | it-IT | ja-JP | ko-KR | ms-MY | nl-NL | pt-BR | pt-PT | ru-RU | ta-IN | te-IN | tr-TR | zh-CN | zh-TW | th-TH | en-ZA | en-NZ | vi-VN | sv-SE

LastModifiedTime

The date and time you created your custom vocabulary filter.

Timestamps are in the format YYYY-MM-DD'T'HH:MM:SS.SSSSSS-UTC. For example, 2022-05-04T12:32:58.761000-07:00 represents 12:32 PM UTC-7 on May 4, 2022.

Type: Timestamp

VocabularyFilterName

The name you chose for your custom vocabulary filter.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 200.

Pattern: ^[0-9a-zA-Z._-]+

Errors

For information about the errors that are common to all actions, see Common Errors.

BadRequestException

Your request didn't pass one or more validation tests. This can occur when the entity you're trying to delete doesn't exist or if it's in a non-terminal state (such as IN PROGRESS). See the exception message field for more information.

HTTP Status Code: 400

ConflictException

A resource already exists with this name. Resource names must be unique within an AWS account.

HTTP Status Code: 400

InternalFailureException

There was an internal error. Check the error message, correct the issue, and try your request again.

HTTP Status Code: 500

LimitExceededException

You've either sent too many requests or your input file is too long. Wait before retrying your request, or use a smaller file and try your request again.

HTTP Status Code: 400

See Also

For more information about using this API in one of the language-specific AWS SDKs, see the following: