Microsoft Teams Transcription API for Meeting Text
A Microsoft Teams transcription API sends a bot into the call and returns a speaker-labelled transcript, live while people speak or after the call. From $0.45 per hour all-in.
*Get started in minutes*
What is a Microsoft Teams transcription API?
A Microsoft Teams transcription API turns a live Teams call into text your code can use. One request, and the transcript arrives at your webhook.
It does two jobs: capture the audio out of the meeting, then convert it to text. The meeting transcription API covers all three platforms.
What you get from every Microsoft Teams call
One request in. Speaker-labelled text out, live while the call runs or once it ends.
*Get started in minutes*
Where Teams speaker labels come from
Speaker identity comes from the audio channel, not from a model reading a mixed track.
*Get started in minutes*
Teams capture is tagged by speaker as people talk, on the same model as Google Meet, and falls back to the dominant speaker.
A speaker timeline maps byte offsets to participants. The speaker diarization entry sets out the other model.
Choose a transcription engine for Microsoft Teams
MeetStream ships its own engine and routes audio to a provider you choose. Each figure below is that provider's own published number.
| Engine | Published language support | Real-time | Best for |
|---|---|---|---|
| MeetStream engine | In-house, auto language detection | No, post-call | One vendor, one bill, no extra key |
| AssemblyAI | 99 languages on Universal-2 | Yes | Broadest published language list |
| Gemini | 97 languages on the Live API | Yes | Teams already building on Gemini |
| Deepgram | 10 languages in real-time multilingual mode | Yes | Low-latency streaming workloads |
| Sarvam | 11 Indic languages plus English | No, post-call | Indian languages and accents |
| JigsawStack | Auto-detect or 162 languages | No, post-call | Batch jobs on a Whisper stack |
On Teams you can also choose the meeting captions engine, and the bot reads the captions Teams produces.
Which Teams rules affect transcription?
Five Teams rules decide what a transcription bot may do. Each one links to Microsoft's own documentation.
| Teams rule | What it means for a bot |
|---|---|
| External bot access | ExternalBotAccessMode defaults to RequireApprovalWhenDetected. External bots land in the lobby. |
| Bot detection | Microsoft describes built-in detection mechanisms that spot external AI bots during the join. |
| Recording banner | It cannot be removed. An admin can only change the consent text and the privacy link by an admin. |
| External participants | Microsoft says external participants cannot record, unless you are a certified partner. |
| Native recordings | They land in the organizer's OneDrive or SharePoint, with a default 120-day expiry. |
How a Teams bot starts transcribing
Most tenants hold external participants in the lobby, so an organiser admits the bot. Teams accepts a waiting window of up to 1800 seconds.
Teams admits and records in one step, so text follows within about a second. Participant events tell your app where the bot is.
From a Microsoft Teams link to your product
One request puts a bot in the call. Text streams while people speak, then a webhook says the final transcript is ready.
*Get started in minutes*
Transcribe a Microsoft Teams meeting with one request
Post the meeting link and name an engine. The bot joins, transcribes, and fires a webhook when the call ends.
curl -X POST https://api.meetstream.ai/api/v1/bots/create_bot \
-H "Authorization: Token $MEETSTREAM_API_KEY" \
-d '{
"meeting_link": "https://teams.microsoft.com/l/meetup-join/19%3ameeting",
"bot_name": "Acme Notetaker",
"recording_config": { "transcript": { "provider": { "meetstream": {} } } },
"callback_url": "https://your-app.example.com/meetstream"
}'Can I get a Teams transcript without a bot?
Teams transcribes on its own terms, set by the tenant. A bot sits above them.
*Get started in minutes*
Teams transcribes automatically when the tenant policy allows it, and Graph access follows tenant permissions and licensing.
A bot captures the audio directly and can stream text while the call runs. The Teams bot API page sets both routes side by side.
Live transcripts and the final record
Both come off the same bot. The question is when you need the words.
The Teams integration page covers the speaker timeline and how to turn byte offsets into seconds.
Microsoft Teams transcription API pricing
Capture costs $0.35 per bot-hour and transcription adds $0.10, so a transcribed meeting is $0.45 per hour all-in.
The rate falls toward $0.25 per bot-hour at volume, and every account starts with $5 of free credit. The pricing page has the full breakdown.
The comparison hub sets MeetStream beside the other meeting bot vendors, on their own published rates.
Microsoft Teams transcription limits and defaults
Transcripts are kept for thirty days by default, or written into your own S3 bucket from the first byte.
One integration for all three platforms
The same request, the same webhook, the same transcript. Only the link changes.
Teams transcripts from a join link, with no Azure setup.
One request captures the audio and returns the words, live or after the call.
*Get started in minutes*
Got a question? We got the answer.
Common questions about transcribing Microsoft Teams calls. Where labels come from, which engines run, and what it costs.
*Get started in minutes*
Can I transcribe a Teams meeting through an API?
Yes. One request puts a bot in the Teams call, captures the audio, and returns a speaker-labelled transcript to your webhook.
Does a Teams transcription bot need an Azure app registration?
A join link is all it takes. The bot enters as a participant, with nothing registered in Azure and no Graph permission of its own.
How are Teams speakers labelled?
Capture is tagged by speaker as people talk, on the same model as Google Meet, and a byte-accurate speaker timeline places every turn.
Can I use Teams native captions?
Yes. Choose the meeting captions engine and the bot reads the captions Teams produces, alongside the six transcription engines.
Can I get a live Teams transcript during the call?
Yes. Choose a streaming engine and text chunks arrive at your webhook while people are still speaking, ready for live coaching or an in-meeting assistant.
Which transcription engines work on Microsoft Teams?
The MeetStream engine plus AssemblyAI, Gemini, Deepgram, Sarvam and JigsawStack, or Teams' own captions. Pick one per request.
What does a Teams transcript contain?
A list of utterances, each tied to a named participant with start and end times, so a summary or a search index needs no extra speaker step.
How much does the Microsoft Teams transcription API cost?
Capture is $0.35 per bot-hour and transcription adds $0.10, so $0.45 per hour all-in, falling toward $0.25 at volume. Every account starts with $5 of credit.
Transcribe your next Teams call
$5 of free credit, self-serve API keys, and no sales call between you and your first transcript.