How to transcribe a Microsoft Teams meeting (live or recorded)

How to transcribe a Microsoft Teams meeting (live or recorded)

Yes — you can transcribe a Microsoft Teams meeting in two main ways. First, Teams offers built-in live transcription during meetings and transcripts for recorded sessions. Second, you can download the meeting recording and use a transcription tool like Wisprs to generate an editable transcript with speaker labels, timestamps, and export formats such as SRT, VTT, DOCX, or JSON depending on your plan.

Why transcribing Teams meetings matters

Transcripts turn meetings into usable, searchable assets instead of one-off conversations. Without a transcript, decisions get buried in video recordings or scattered notes. With one, your team can quickly find what was said, who said it, and what needs to happen next.

For product managers, transcripts help track decisions and user feedback without replaying long calls. For ops teams, they provide accountability and documentation across projects. For creators, transcripts make it easy to repurpose meetings into blogs, training materials, or summaries. Even simple use cases like accessibility or compliance benefit from having a reliable text version of every conversation.

Transcription also reduces the cognitive load during meetings. Instead of trying to capture everything manually, participants can focus on the discussion, knowing a transcript will capture the details.

Quick paths: your options at a glance

There are three practical ways to transcribe a Teams meeting, and each works best in different situations.

• Use Teams live transcription during the meeting for real-time captions and a basic transcript.
• Record the meeting and export the transcript afterward from Teams if available.
• Download the recording and upload it to Wisprs for more control over editing, speaker labels, and export formats.

Teams works well for quick, built-in needs, especially when you just want captions or a simple transcript. Exporting and using Wisprs becomes more useful when you need cleaner formatting, better speaker identification on paid plans, or flexible outputs like subtitles or structured documents.

Step-by-step: enable and export Teams live transcription

Teams includes live transcription as part of its meeting tools, but it needs to be started manually and depends on your organization’s settings. If transcription is disabled at the admin level, you may not see the option.

To enable live transcription during a meeting, the meeting organizer or a participant with the right permissions can start it from the meeting controls. Once active, captions appear in real time, and Teams stores a transcript tied to the meeting.

Here is how the typical flow works from a host’s perspective:

• Start or join your Teams meeting.
• Open the meeting controls (the toolbar).
• Click “More actions” (three dots).
• Select “Start transcription.”
• Confirm the spoken language if prompted.
• Let the meeting run while Teams captures speech.

After the meeting ends, the transcript is usually accessible in the meeting chat or details pane, depending on your Teams version and tenant settings. You can open it, review it, and in many cases download or copy it.

Keep in mind that transcript availability and export options can vary across organizations. Some tenants allow downloading directly, while others restrict access or limit retention. If you do not see the transcript, it may be due to permissions or policy settings rather than a missing feature.

Step-by-step: export a Teams recording and upload to Wisprs

If you need more control over your transcript, exporting the recording and processing it separately is often the most reliable workflow. This approach works even when Teams transcripts are unavailable or limited.

After a meeting is recorded, Teams stores the video in OneDrive or SharePoint, depending on how the meeting was created. From there, you can download the file to your device.

Once you have the recording, you can upload it to Wisprs and generate a transcript with more flexible output options. Wisprs supports a wide range of file formats, including MP3, MP4, WAV, M4A, WEBM, and others commonly used by Teams recordings.

Here is a simple end-to-end workflow:

• Open the meeting recording from Teams (via chat or calendar event).
• Locate the file in OneDrive or SharePoint.
• Download the video file (usually MP4).
• Go to Wisprs and upload the file.
• Click “Start transcription” after upload completes.
• Wait for processing, then review and edit the transcript.
• Export in your preferred format (TXT, SRT, VTT, DOCX, or JSON depending on plan).

This method gives you more control over the final output. You can edit text directly in the dashboard, adjust speaker labels on supported plans, and export in formats that Teams does not always provide.

Accuracy is typically excellent on clear audio, though it can vary based on accents, background noise, and overlapping speech. If your meeting has multiple speakers, paid plans offer native speaker identification, which helps organize the transcript into readable dialogue.

Live transcription with Wisprs (real-time use)

If you need live transcription outside of Teams’ built-in feature, Wisprs also supports real-time transcription through a streaming setup. This is useful when you want transcripts that are independent of Teams or when you need to integrate transcription into a broader workflow.

In a live setup, audio is streamed to Wisprs while the meeting is happening. This requires a bit more technical setup than simply clicking “Start transcription” in Teams, but it offers flexibility for teams that want to capture and process audio in real time.

A typical use case might involve routing system audio or microphone input into a streaming endpoint. Wisprs then processes the audio and returns transcription results continuously. This is especially useful for live events, webinars, or internal tooling where transcripts need to be consumed immediately.

Real-time transcription works best in controlled environments. Speaker labeling in live scenarios may be less consistent than post-processing, especially with overlapping speakers or noisy conditions. For high accuracy and clean formatting, many teams still prefer recording first and transcribing afterward.

Teams vs export + Wisprs: what’s the difference?

Teams’ built-in transcription is convenient, but it is not designed for every workflow. Exporting and using a dedicated transcription tool gives you more flexibility, especially when transcripts need to be reused or published.

Here is a quick comparison of the two approaches:

| Feature | Teams built-in | Export + Wisprs | | ------------------ | -------------------- | -------------------------------------- | | Setup | One click in meeting | Requires download + upload | | Live captions | Yes | Yes (via real-time setup) | | Transcript editing | Limited | Full editing in dashboard | | Speaker labels | Basic / varies | Available on paid plans | | Export formats | Limited | TXT, SRT, VTT, DOCX, JSON (plan-based) | | Accuracy control | Fixed | Speed vs quality options (free tier) | | Batch processing | No | Available on higher tiers | | Reusability | Moderate | High (content workflows) |

If your goal is quick reference, Teams may be enough. If your goal is structured documentation or content reuse, exporting and using Wisprs gives you more control.

Example workflows you can copy

Seeing how this works in practice helps clarify which path to choose. These scenarios reflect common ways teams handle transcription.

A product manager hosting weekly syncs might rely on Teams live transcription during meetings. Afterward, they skim the transcript to confirm decisions and action items. This works well for fast-moving teams that prioritize speed over formatting.

A content team recording interviews might download each Teams recording and upload it to Wisprs. They edit the transcript, clean up speaker labels, and export a DOCX file for writing articles. This workflow turns meetings into publishable content with minimal manual effort.

A remote operations team might standardize their workflow across all meetings. They record every call, upload recordings in batches, and generate transcripts with summaries and action items on paid plans. This creates a consistent archive of decisions and discussions.

In live event scenarios, teams sometimes stream audio into Wisprs for real-time transcription. This is useful for accessibility or live captioning outside of Teams, especially when integrating with other tools.

Common pitfalls and troubleshooting

Even straightforward transcription workflows can run into issues. Most problems come down to permissions, audio quality, or misunderstandings about where transcripts are stored.

If a transcript is missing after a Teams meeting, the most likely cause is that transcription was never started or was disabled by admin policy. Unlike recordings, transcripts do not always generate automatically.

Here are common issues and how to handle them:

• No transcript available after meeting: Check if transcription was enabled during the call and confirm admin permissions.
• Cannot download transcript: Some organizations restrict exports; try copying text or using the recording instead.
• Poor accuracy: Improve audio quality, reduce background noise, and avoid overlapping speech where possible.
• Missing speaker labels: Built-in tools may be limited; use post-processing with diarization on supported plans.
• Processing stuck or slow: Large files take longer; some tools allow canceling and retrying jobs.
• Watermarks on exports: Free plans may include watermarks; upgrading removes them.

When in doubt, the most reliable fallback is to download the recording and transcribe it separately. This bypasses most limitations tied to Teams’ built-in features.

How Wisprs handles Teams recordings

Wisprs fits naturally into Teams workflows by handling the part that Teams does not optimize for: clean, editable, reusable transcripts. Once you upload a Teams recording, Wisprs processes the audio using industry-leading speech recognition. The free tier uses self-hosted Whisper-based models, while paid plans use ElevenLabs Scribe with native speaker identification.

After processing, you can edit the transcript directly in the dashboard. This includes fixing wording, adjusting speaker labels, and organizing content. On paid plans, you can also generate meeting summaries, action items, and topic breakdowns, which saves time on post-meeting documentation.

Export flexibility is another key advantage. Free plans include TXT and SRT formats, while paid plans add VTT, DOCX, and JSON. This makes it easier to reuse transcripts for subtitles, reports, or structured data workflows.

If you handle multiple meetings, batch upload on higher-tier plans allows parallel processing. This is useful for teams that want to standardize transcription across all meetings without manual repetition.

For a broader look at how transcription fits into team workflows, see /use-cases/meeting-transcription-software. If you want a general walkthrough of transcription basics, /blog/how-to-transcribe-audio-to-text covers the fundamentals.

FAQ: Teams meeting transcription

Next steps: try it yourself

If you just need a quick transcript, start with Teams’ built-in transcription during your next meeting. It is fast and requires no setup.

If you need something more usable, download your next Teams recording and run it through a dedicated workflow. That is where you get cleaner formatting, better editing control, and flexible exports.

To try that workflow, upload a Teams recording and generate your first transcript here: /tools/free-audio-to-text

If you plan to transcribe meetings regularly, create an account and streamline your process with editing, speaker labels, and export options: /sign-up