Posted On: Dec 20, 2019

Amazon Transcribe is an automatic speech recognition (ASR) service that makes it easy for you to add speech-to-text capability to your applications. Starting today, when transcribing audio, you can instruct Amazon Transcribe to automatically mask or remove specific terms from the output transcripts based on a vocabulary that you specify. For example, you can use a vocabulary filter to automatically remove profane words from the transcription results for content moderation. You do not need to scrub inappropriate content from each transcript anymore. You can create a vocabulary filter once and apply it to all your transcription jobs. You can also create multiple vocabulary filters and choose which one should be used for a particular transcription job.

Amazon Transcribe enables organizations to increase the accessibility and discoverability of their audio and video content. The service is useful across a breadth of use cases. Customer contact centers can convert call recordings into text and analyze the data for actionable intelligence. Media content producers can automate subtitling workflows for greater engagement and accessibility. Enterprises that have archives of recorded meetings can make those archives accessible and searchable by transcribing them into useful text that’s demarcated by time stamps. Also, marketers and advertisers can enhance content discovery and display more targeted advertising based on the extracted metadata from video files.

Vocabulary filtering is available for batch transcription at no additional cost in all the AWS regions where Amazon Transcribe is available. To learn more, visit the Amazon Transcribe documentation page.