> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vexa.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Named speakers on Meet and Zoom, bound at capture

> On Google Meet and Zoom, each participant arrives on their own audio track and the speaker name is bound at the moment of capture — carried, never guessed.

**Does Vexa label who said what?**

**Today:** Yes on Google Meet and Zoom, for each person joining from their own device — the name is bound to the audio at the moment of capture, never matched to a voice afterwards.

**Sponsorable:** no — this one is shipped.

***

*Speaker names carried from capture, never matched to a voice after the fact.*

|                 |                                              |
| --------------- | -------------------------------------------- |
| **Status**      | shipped                                      |
| **Size**        | —                                            |
| **North star**  | 2 · Dependable capture                       |
| **Measured by** | served-transcript share and named-word share |

## What it does

* Each participant on their own device arrives on their own audio track.
* The name is bound to the audio at the moment of capture.
* A segment either carries a real name or carries none.

<Note>
  Speaker separation **separates** speakers. Names come from a roster you supply. Nobody enrols a voice.
</Note>

This one is shipped — there is nothing to sponsor. See the [roadmap](/roadmap) for what is not.

## Questions

<AccordionGroup>
  <Accordion title="Does Vexa label who said what?">
    Yes on Google Meet and Zoom, for each person joining from their own device — the name is bound to the audio at the moment of capture, never matched to a voice afterwards.
  </Accordion>

  <Accordion title="Do I have to pay for this?">
    No. It is shipped and open source under Apache-2.0. Run it yourself, or use the hosted service.
  </Accordion>

  <Accordion title="Does this require voice enrolment?">
    No. Speaker separation separates speakers; names come from a roster you supply. Nobody enrols a voice.
  </Accordion>
</AccordionGroup>

***

*Shipped upstream under Apache-2.0.*