> ## 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.

# Overlapping-speech separation on Teams

> Separate speakers who talk over each other on Microsoft Teams, where the audio arrives as a single mixed stream rather than one track per participant.

**Can Vexa separate people talking over each other on Microsoft Teams?**

**Today:** No. Teams delivers a single mixed stream, so speakers are separated by diarization rather than by track, and overlapping speech is not handled.

**Sponsorable:** yes — Overlap handling on that mixed lane.

***

*Keep two people talking at once from collapsing into one speaker on Teams.*

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

## What it does

* Handles overlapping speech on the mixed Teams lane.
* Separates concurrent speakers rather than attributing the overlap to one.

## What exists today

Teams delivers a single mixed stream to every participant, so speakers are separated by diarization rather than by track — labels are derived, not carried.

## What this adds

Overlap handling on that mixed lane.

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

## How sponsorship works

You fund the item. It moves to the front of the queue. You co-write the acceptance criteria, so "done" means done on your meetings. Your name goes on the release note. Sponsorship buys **the order of the queue** — never exclusivity, never a private build, and never a date the work has not earned. The fee basis is per item or per stage, agreed in writing before work begins.

## Two doors

<Columns cols={2}>
  <Card title="Sponsor this" icon="handshake" color="#0D9373" href="https://cal.com/dmitrygrankin/web?utm_source=docs&utm_medium=roadmap&utm_campaign=sponsor&utm_content=overlapping-speech-teams" horizontal arrow cta="Book fifteen minutes">
    Fifteen minutes. Bring the constraint you are under.
  </Card>

  <Card title="Watch this" icon="envelope" color="#0D9373" href="mailto:dmitry@vexa.ai?subject=Roadmap%20update%3A%20Overlapping-speech%20separation%20on%20Teams&body=watch" horizontal arrow cta="Email me">
    One email when it ships. The mail is already written — send it as it is.
  </Card>
</Columns>

## Questions

<AccordionGroup>
  <Accordion title="Can Vexa separate people talking over each other on Microsoft Teams?">
    No. Teams delivers a single mixed stream, so speakers are separated by diarization rather than by track, and overlapping speech is not handled.
  </Accordion>

  <Accordion title="What would sponsoring this add?">
    Overlap handling on that mixed lane.
  </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>

***

*Ships upstream Apache-2.0 when sponsored.*