> ## 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.

# Live transcript and retrieval API

> Read a Vexa meeting transcript over HTTP while the meeting is still running, or stream segments over a WebSocket as they are produced.

**Can Vexa give me a meeting transcript while the meeting is still running?**

**Today:** Yes. Read it over HTTP during the meeting, or stream segments over a WebSocket as they are produced.

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

***

*Read the transcript while the meeting is still running.*

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

## What it does

* `GET` the transcript during or after the meeting.
* Segments carry speaker, start, end, language and confidence.
* Stream over a WebSocket, or poll for what is new.

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

## Questions

<AccordionGroup>
  <Accordion title="Can Vexa give me a meeting transcript while the meeting is still running?">
    Yes. Read it over HTTP during the meeting, or stream segments over a WebSocket as they are produced.
  </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="Where does it run?">
    On your own infrastructure. Vexa is Apache-2.0 and self-hosted — the audio and the transcript stay inside it.
  </Accordion>
</AccordionGroup>

***

*Shipped upstream under Apache-2.0.*