Transcribe a meeting recording into minutes
Choose a meeting recording and it is transcribed with speakers distinguished. The audio never leaves your device, so recordings that cannot go outside your organisation can be processed as they are. Speaker diarization (labelling who spoke when) is enabled from the start.
You can normally leave this on Auto. Change it only if the result clearly has the wrong number of speakers
How to transcribe a Zoom or Teams meeting
- Save the meeting recording to your computer. Zoom's local recording saves a video (MP4) and an audio-only file (M4A) in the Zoom folder inside Documents. Choosing the M4A starts faster, since no audio has to be extracted from video. Teams meeting recordings can be downloaded from the Recordings folder in the organiser's OneDrive.
- Set the language to the one spoken in the meeting and choose a model. For meetings with many proper nouns or technical terms, Small or larger is recommended. Speaker diarization is already on for this page.
- Choose the file to start transcription. When it finishes, give each speaker a participant's name, merge anyone who was split into several speakers, and export as TXT.
Getting usable minutes
This page enables speaker diarization from the start, because a meeting involves several voices and minutes are hard to use unless you can tell who said what. The number of speakers is estimated automatically, so even if you know how many people took part, you can leave the speaker count on Auto. For recordings heavy with proper nouns or jargon, switching to the small model or larger reduces dropped words.
How the meeting was recorded matters too. Two things help most: every voice captured at a similar level, and people not talking over each other. Recordings made with an online meeting tool's built-in recorder tend to separate better than a single microphone in the middle of a conference table.
Teams and Zoom have transcription features of their own, but depending on your organisation's admin settings or your plan, they may not be available. As long as you have the recording file, this tool transcribes it regardless of those settings. Note that this tool stops at transcription and telling speakers apart; it does not summarise the meeting or pull out decisions.
If something goes wrong
- If one person's remarks are split across several speakers, click the speaker's name and choose "Merge into another speaker".
- If two people end up under the same speaker, use the person icon that appears when you hover over a line to change that line's speaker. If one line contains remarks from two people, split it first with the pencil icon.
Frequently asked questions
How many participants can it handle?
Up to eight speakers can be distinguished. The number of speakers is estimated automatically, so the speaker count can normally stay on Auto. Short remarks, such as the chair calling on the next speaker, may be attributed to the person speaking just before or after. If that happens, you can split the line or reassign individual lines on screen.
Could the meeting audio be sent outside?
No. Both transcription and speaker diarization run inside your browser, and neither the audio nor the resulting text is sent to any external server. Confidential meetings are safe to process.
Can I use real participant names for the speakers?
Yes. You can name each speaker on screen, and merge speakers if one person was split into two. Individual lines can be reassigned as well.
Does it work with online meeting recordings?
Yes. Pick the recording file from Zoom, Teams, Google Meet and so on (MP4 or M4A) directly. For video files, only the audio track is extracted.
Getting the audio ready, and after transcribing
Help us improve the service
Sending us the circumstances of a run — successful or failed — helps us track down problems (a failure rate needs both). Knowing which devices and settings fail most often lets us revise the recommended defaults and fix the bugs behind them. If you don't mind, leaving this on is a real help.
What is sent
Your device specs (GPU model, memory, core count), browser and OS, the model and language you chose, how far the run got, the error details, the file's format with a rough size and length, and how long it took.
What is never sent
Audio, transcripts, file names, and IP addresses. The data goes only to this site's own server, never to a third-party service.