Short answer: Microsoft Teams has captions and some translation on certain licences, but they aren't built for a room where four people each need to read along in a different language at once. To get real-time per-person translated captions on a Teams call, you add a translation bot to the meeting — everyone then reads the conversation in the language they choose.
Here's the setup, what you get afterward, and the one detail worth being precise about before you rely on it.
The setup
There's nothing for attendees to install and no add-in for them to approve. You bring the bot into the meeting the same way you'd bring in a guest:
- Add the Sageio bot to your Teams meeting. From your Sageio dashboard, point it at the Teams meeting link — or add the bot to the invite. If your organisation gates the meeting lobby, admit it once, like any external guest.
- Everyone reads their own language. Each participant picks the language their captions appear in. Translated captions show up in about two seconds, so nobody has to slow the call down.
- Get the record afterward. When the meeting ends, a searchable translated transcript and an AI summary arrive within about five minutes. The host controls who they go to.
That's the whole flow. The hard part — translating live speech across languages without breaking the meeting's pace — runs in the background.
Why "per-person" is the part that matters
Most built-in captioning treats the meeting as having one caption setting. Real multilingual meetings don't work that way. The person in Ho Chi Minh City needs Vietnamese; the person in Seoul needs Korean; the person in Munich needs German — from the same conversation, at the same time.
Per-person captions make the language a personal setting for each listener, not a single choice imposed on the meeting. That's the difference between "there are captions" and "everyone can actually follow."
A single Teams meeting can run several caption languages at once — up to 7 on the Teams plan — so a genuinely mixed room reads along together.
Languages — and why Asian languages specifically
Sageio translates into 20+ languages and treats Asian languages as first-class, not as an afterthought bolted onto a European-first engine. In practice that means Traditional Chinese isn't quietly served as Simplified, Cantonese isn't routed through a Mandarin model, and Thai and Vietnamese keep their diacritics intact.
If anyone on your team has one of these as a first language, the difference is obvious the first time they read the captions — a wrong word choice in Taiwanese Chinese reads the way a comma splice reads in English.
One thing to be precise about: who said what
It's worth being straight about this, because it's easy to assume. Speaker labels — the "who said what" tags on each line — are a Google Meet feature today; Teams captions aren't speaker-labelled the same way. On Teams you get the live per-person translated captions and the translated transcript and summary; the per-line speaker attribution is the piece that's Google-Meet-only for now. If that distinction matters for your use case, it's worth flagging on the contact form.
Is it private?
For meeting content, this is the first question a sensible buyer asks. Two things to know:
- Your meetings aren't used to train AI models — and the underlying AI vendors are contractually restricted from doing so either.
- Audio is processed in memory and discarded. Only the encrypted text transcript and summary are kept, in the region you choose (US, EU, or APAC). Enterprise customers can self-host the whole stack, so nothing leaves their own servers.
Which platforms does this work on?
Sageio joins Microsoft Teams and Google Meet today. Zoom support is coming soon. If Zoom is critical for your rollout, say so on the contact form — it helps us prioritise.
Frequently asked questions
Can I add real-time translation to a Microsoft Teams meeting? Yes. Teams is supported today. You add the Sageio bot to the meeting, and each participant reads translated captions in the language they choose — no add-in or install for attendees.
Does every attendee get their own language? Yes — captions are a per-person setting. One Teams meeting can run several caption languages at once (up to 7 on the Teams plan) across 20+ languages.
How fast are the captions? About two seconds — fast enough to keep a live conversation flowing.
Does Teams show who said what? The per-line speaker labels are a Google Meet feature today; Teams captions aren't speaker-labelled that way. You still get the per-person translated captions, transcript, and summary on Teams.
Does it cost anything to try? Every plan starts with a free 60-minute trial, no credit card required. After that, Professional is $49/month and Teams is $99 per seat/month; Enterprise is custom.
If your Teams meetings are already multilingual, the fastest way to feel the difference is to run one real call with it. Add the bot to your next cross-language meeting and watch what happens to the parts of the conversation people usually let slide.
For the wider picture — how the same setup works across your stack — see our guide to real-time translation for remote teams, the per-person captions that make it work, and how the same thing looks on Google Meet.