Amazon Chime SDK meetings live transcription now supports content identification and custom language models

Amazon Chime SDK lets developers add real-time audio, video, and screen share to their web and mobile applications. With live transcriptions, developers can include subtitles in meetings and create transcripts using Amazon Transcribe or Amazon Transcribe Medical. Using the service-side integration between Amazon Chime SDK and your Amazon Transcribe account, application builders can now help identify and redact personally identifiable information (PII) and personal health information (PHI) from transcripts. Builders can also utilize custom language models to help improve the transcription accuracy for their use cases.

The transcript content and meta data are shared in real-time with meeting participants for display during the meeting. They are also stored by media capture in the Amazon Simple Storage Service (Amazon S3) bucket of the developer’s choice for post-meeting processing. Developers can access all the streaming languages supported by Amazon Transcribe, as well as features such as custom vocabularies and vocabulary filters. Standard Amazon Transcribe and Amazon Transcribe Medical costs apply.

To learn more about the Amazon Chime SDK and live transcription with Amazon Transcribe or Amazon Transcribe Medical, review the following resources:

* Amazon Chime SDK
* Amazon Transcribe
* Using live transcription in the Amazon Chime SDK Developer Guide