Skip to content
Meetings

The transcript

A locked document that behaves like any other document — with one difference.

Last updated 1 min readFor team members

The transcript is a document

Once every segment is transcribed and the meeting is ended, a single stitched transcript is built: a real document in the pool, with a page marker per segment, linked to that meeting.

So everything you do with any document, you do with it — review, download, search, ask the assistant.

The difference is that its access is not its own: a meeting transcript follows that meeting's access list and never takes a separate one.

Persian transcription quality

Transcription is built for Persian rather than translated from an English-first model. Speakers are separated, and the text improves with the names and terms of that particular meeting.

The names come from the meeting itself: its participants, the people seated at the anchoring organisation, and the anchoring engagement with its service. The whole contacts directory is never loaded in — a big list does not raise accuracy, it raises cost.

If the model stalls and repeats a phrase over and over, that run is collapsed and the text keeps a single occurrence.

The transcript is built once

Stitching only happens when the meeting has ended, every segment has succeeded, and no transcript exists yet.

Running it again does nothing; a second transcript is never created.

Still stuck?

If the answer wasn't here, write to us. It is a real inbox and it gets answered.

Talk to us