Audio and video · Independent · 20 Oct 2026

Vexa-ai/vexa

Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.

← Audio and video
Vexa: open-source meeting bots. Sends bots to calls and transcribes speech locally.

In simple English

This tool sends a virtual bot into your online meetings on Google Meet, Microsoft Teams, and Zoom. The bot records the audio, transcribes who said what in real time, and feeds the notes into an artificial intelligence assistant. You can use a hosted cloud service or run the entire software stack on your own server. Running it yourself requires a modern computer and some technical setup time. It gives you complete control over your private meeting data without paying a monthly per-seat fee.

What it is

Vexa is an open-source meeting transcription system with an API (Application Programming Interface, a way for different software programs to talk to each other) and an optional AI workspace. It features a set of Docker containers that handle bot dispatch, speech-to-text processing, and automated note-taking.

What it is good for

Solo builders and teams who want to record, transcribe, and search their video calls without sending sensitive business conversations to a third-party cloud service.

Stars2.9k
LicenceApache-2.0
Latestv0.12.28 (2026-10-09)checked 20 Oct 2026
Last code change2026-10-11
Written inPython
Setup effort
4 / 5
Payoff
4 / 5
Good
  • Supports Google Meet, Microsoft Teams, and Zoom out of the box.
  • Licensed under Apache-2.0, so you can host and modify it freely.
  • Keeps all your meeting transcripts and workspace files stored locally.
Watch for
  • Requires Docker (a way to run a program inside its own sealed box, so it cannot break anything else on your server) and familiarity with the command line.
  • Running the full stack locally needs significant hardware resources and a separate transcription service.
  • Some advanced features and mid-call controls are not yet available in the open-source version.
Replaces

Paid cloud transcription services and manual meeting note-taking.

Works well with

Docker

Similar repositories
  • attendee-labs/attendee766 stars

    Another meeting bot API, but available under a restrictive source-available licence instead of Apache-2.0.

  • ggml-org/whisper.cpp55k stars

    A fast transcription library for turning raw audio into text locally, without the meeting bot capture layer.

Also reviewed on Repo Radar
  • snapcast/snapcast8.0k stars

    A server and clients that play one audio stream in several rooms, kept in time with each other.

  • MusicPlayerDaemon/MPD2.8k stars

    A background music player with no interface of its own, controlled over a network by separate client programs.

  • AcademySoftwareFoundation/OpenTimelineIO2.0k stars

    An interchange format and library for editing timelines: the order and length of cuts, and references to the media, but not the media.

Install
git clone https://github.com/Vexa-ai/vexa.git && cd vexa
make all

Independent: reviewed for Repo Radar outside the daily editions. Every independent repository

On Stack Radar: Productivity & Collaboration › Meetings, Scheduling & Calendar › AI Notetakers.

Get the next edition in your inbox

A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.

No tracking pixels. One click to leave. The archive stays free either way.

We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.