Amazon Transcribe now supports vocabulary filtering for real-time transcription

Amazon Transcribe is an automatic speech recognition (ASR) service that makes it easy for you to add speech-to-text capabilities to your applications. Starting today, when transcribing audio streams, you can instruct Amazon Transcribe to automatically mask, remove, or tag specific terms in the transcription results 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 or generating family-friendly captions. You can create a vocabulary filter once and use it when processing multiple audio streams. You can also create multiple vocabulary filters and choose which one should be used for a particular audio stream. With this launch, vocabulary filtering is now available for both Amazon Transcribe’s batch and streaming transcription APIs.

Source:: Amazon AWS