Transcribe Vocabulary Filter

Transcribe Vocabulary Filter in AWS is a custom word list used with Amazon Transcribe to filter or mask specific terms during speech-to-text transcription. It helps manage sensitive, profane, or unwanted words by replacing them with asterisks or removing them from the transcript. This allows greater control over transcription output for compliance, moderation, or content customization needs.

aws.transcribe_vocabulary_filter

Fields

TitleIDTypeData TypeDescription
_keycorestring
account_idcorestring
download_uricorestringThe Amazon S3 location where the custom vocabulary filter is stored; use this URI to view or download the custom vocabulary filter.
language_codecorestringThe language code you selected for your custom vocabulary filter.
last_modified_timecoretimestampThe date and time the specified custom vocabulary filter was last modified. 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.
tagscorehstore
vocabulary_filter_namecorestringThe name of the custom vocabulary filter you requested information about.