14 DAY TRIAL // Microsoft Teams is the service whose adoption skyrocketed since early 2020 for obvious reasons, but at the same time, it’s also the one that received plenty of updates in the last 12 months or so.
And today, Microsoft has announced a new major update, adding live transcription with speaker attribution for the English version of the service.
“We’ve all been in situations where we’re double-booked or joined a meeting late. You don’t want to interrupt the flow but need to catch up quickly. Or, for accessibility reasons or ambient noise situations, you need help following the conversation and understanding who’s speaking. Wouldn’t it be great to have transcription with speaker attribution built into the meeting?” the company said in an announcement today.
Microsoft says Teams can accurately identify each speaker and create the transcript in near real time, with all the content to be then available not only during the meeting but also after it.
Available today for English (US)
The company claims it has invested massively in this feature, not only to develop it but also to make sure everything is working according to the plan.
Because let’s be honest, such a feature makes little sense if it comes with huge latency or it isn’t accurate, but the software giant promises it made huge investments in this regard in the last two years.
“Live transcription in Teams uses a meeting's invitation, participant names, attachments, etc. to improve the accuracy and recognize meeting-specific jargon for each transcript automatically, without any human involvement. This means no one at Microsoft ever sees the meeting’s content, and the models are automatically deleted immediately after each meeting. In addition, Microsoft doesn’t use or store this data for improving its own AI,” it explains.
Live transcripts are available for customers running Microsoft 365 E3, Microsoft 365 E5, Microsoft 365 Business Standard, and Microsoft 365 Business Premium SKUs.