Microsoft is preparing to add two AI-driven features to Microsoft Teams aimed at improving multilingual communication and making meeting recaps easier to review. The updates recently appeared on the Microsoft 365 roadmap, indicating the company’s intention to introduce automatic spoken language detection along with a new video recap tool for meetings. Both additions are expected to roll out to desktop and Mac versions of Microsoft Teams in April.
The automatic spoken language detection feature focuses on multilingual meetings, which have become increasingly common for globally distributed teams. Currently, Teams requires participants or organizers to manually switch language settings when a speaker changes languages or dialects. This manual step can easily be overlooked, particularly during fast-moving discussions. When that happens, captions and transcripts often become inaccurate or unreadable.
The planned update removes the need for manual language selection. Microsoft Teams will instead use AI-based speech recognition to identify the language spoken by each participant in real time. Once detected, the system will automatically adjust captions and meeting transcripts to match the speaker’s language. In practice, this means participants should see captions that more accurately reflect what is being said, even when conversations switch between multiple languages.
To enable the feature, meeting organizers will still need to activate either the Interpreter tool or multilingual speech recognition within the meeting settings. Once enabled, Teams will dynamically detect and adjust to different languages without requiring user intervention.
Alongside this change, Microsoft is also working on an updated meeting recap system that generates video highlights from recorded meetings. Instead of only offering written summaries or transcripts, Teams will automatically produce a short video recap that narrates key moments from the meeting.
While Microsoft has not provided detailed information about how the video recap system will select highlights, the feature appears similar to automated highlight reels used in consumer photo applications. Tools such as Google Photos and iCloud Photos already generate short videos from media collections. In the case of Microsoft Teams, however, the recap will focus on meeting content rather than personal media, summarizing discussions and important moments from the recorded session.
At this stage, Microsoft has not clarified whether users will be able to disable the video recap feature or control how the summaries are generated. Those details may become clearer as the rollout approaches.
These additions come alongside other updates Microsoft has been preparing for Teams. Recent roadmap entries mention tools such as a bot management system for meeting administrators and a network strength indicator designed to help users monitor connection stability during calls.
Microsoft Teams continues to evolve as organizations rely more heavily on video meetings and collaboration software. Features like automatic language detection and AI-generated meeting summaries reflect a broader shift across workplace tools toward automation designed to reduce manual setup and make information easier to review after meetings.
If Microsoft follows its current roadmap timeline, both the automatic spoken language detection system and the video recap feature should begin appearing in Microsoft Teams desktop and Mac clients in April.
