Posted On: Aug 11, 2021

The Amazon Chime SDK lets developers add real-time audio, video, and screen share to their web and mobile applications. Starting today, developers can overlay subtitles, build a transcript, or perform real-time content analysis with live audio transcription powered by Amazon Transcribe or Amazon Transcribe Medical

To create real-time meeting transcriptions without audio leaving the AWS network, the Amazon Chime SDK now includes a service-side integration to your Amazon Transcribe account. For improved accuracy in double-talk scenarios, users’ audio is processed separately, before being mixed into the meeting. Amazon Chime uses its active talker algorithm to select the top two active talkers, and then sends their audio to Amazon Transcribe, in separate channels, via a single stream. For reduced latency, user-attributed transcriptions are sent directly to every meeting participant via data messages. When using a media pipeline to capture meeting audio, the meeting’s transcription information is also captured.

Developers can access all the streaming languages supported by Amazon Transcribe, as well as features such as custom vocabularies and vocabulary filters. When using Amazon Transcribe Medical, developers can choose the specialty, conversation type, and optionally provide any custom vocabulary. 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: