Meeting Transcription - It Knows Who Said What

Meeting transcription: the hard part is who said it

In meeting transcription, turning an hour of audio into text is the easy part. The hard part is the wall of subject-less sentences that comes back — you have to re-listen to attribute anything.

Speaker diarisation solves exactly that step: attribution happens during transcription, so the output arrives shaped as a conversation rather than one undifferentiated block.

Real output

A two-person English exchange, uploaded with no configuration. Unedited response:

英語12秒

Detected language: eng  (confidence 99.3%)
Speakers detected: 2

speaker_0  @0.16s   So where did we land on the migration date?
speaker_1  @3.56s   I'd push it a week. QA hasn't signed off on
                    the rollback path yet.
speaker_0  @8.54s   Fine, a week, but I want the rollback tested
                    by Thursday

Three turns, all attributed correctly, each with a start time. Nothing was configured — the speaker count was not supplied, and no labelling was done.

Look at the third line: when speaker_0 talks again, the system recognises the same person rather than adding a third. That is the difference between diarisation and simply splitting on pauses.

One honest detail: the source script reads "Fine. A week. But I want…" and came back as "Fine, a week, but I want…". Punctuation is inferred from pauses and is the least stable part of any transcript. It does not matter for subtitles; it matters for a formal record.

Want a messier test? Below is a two-person stand-up in Chinese: people trading turns, cutting in, then splitting the work. Upload a recording like it to see how meeting transcription labels the speakers in your own audio.

ボイス: 科技大佬 / 知性御姐中国語43秒

Anonymous labels, no voiceprint identification

You get speaker_0 and speaker_1, not names. The guarantee is that one label means one person — the system never asks who that person is.

That is a deliberate limit. Matching voices against identities is biometric processing and should not be switched on by default in a transcription tool. Replacing the labels with names takes ten seconds and applies across the whole transcript.

Where meeting transcription fits

Take that last row seriously: the audio is processed by a speech recognition service. For highly sensitive meetings, confirm that fits your organisation's requirements before uploading.

Where it breaks

Overlapping speech is the known hard problem in meeting transcription. Turn-taking is highly accurate; two people speaking at once for more than a second or two can be misattributed.

Two practical mitigations: separate microphones where possible, or re-listen to the disputed passage — with timestamps that is one click, not a hunt along the playhead.

We put this on the page rather than letting you discover it after uploading.

Set the meeting up for a clean transcript

Much of the result is decided before anyone presses record:

• One microphone per person. In a room, avoid a single shared mic in the middle of the table.
• Note the headcount. State it at upload and the system will not split one person into two.
• Go round the table once at the start. A sentence from each person makes replacing speaker_0 and speaker_1 with names a matter of seconds.
• Keep cross-talk down. The fewer overlapping passages, the more accurate the attribution.

From transcript to meeting minutes

A usable set of minutes usually comes together like this:

1. Upload the recording and wait for the transcript.
2. Replace speaker_0, speaker_1 and the rest with real names — once, and it applies throughout.
3. Search for words like "owner", "deadline" or "next week" to find each commitment, and click the timestamp to re-hear anything in doubt.
4. Put decisions, actions and owners at the top; attach the full transcript underneath for reference.

Meeting transcription tells you who said what and when. Minutes need what was decided and who is doing it — that step still takes a person, but no longer a full re-listen.

How to use meeting transcription

1. Open the voice studio → transcribe
2. Upload the recording — audio or video, 200MB total per upload
3. Wait; an hour typically takes one to two minutes
4. Replace speaker_0 with real names, then export

Speaker separation needs no configuration, and the language is detected automatically across 90+ languages.

FAQ

How many speakers can meeting transcription separate, and do I declare the count first? Up to 32. The count is inferred automatically, so nothing needs declaring. If you do know how many people were in the room you can state it, which improves separation — with a known count the system will not split one person into two.

Can it identify who each person is by name? No, and it should not. The output uses anonymous labels like speaker_0 and speaker_1, guaranteeing only that one label means one person. It performs no voiceprint identification. You replace the labels with names once and it applies throughout. That is deliberate: matching voices against identities is biometric processing, and a transcription tool should not do it by default.

What about people talking over each other? Overlapping speech is the acknowledged hard problem in this field. Turn-taking meetings separate very accurately; where two people speak simultaneously for more than a second or two, attribution can be wrong. In practice, use separate microphones where you can, or re-listen to the disputed passage — the timestamps make that a single click.

The meeting is confidential. Is the audio retained? Transcription runs under your account and results live in your history, where you can delete them at any time. Note that the audio is processed by a speech recognition service — for highly sensitive material, confirm this meets your organisation's compliance requirements before uploading.

Start here

Cost: 20 credits per file (up to 200MB per upload), refunded automatically if it fails. The $3.90 trial pack has 150 credits, enough for 7 files, and they never expire.

Run your last team meeting through meeting transcription and see how long the minutes take now.

Upload a meeting recording →

Related: MP3 to text · video to text · subtitle generator · multi-speaker dialogue