#64 · Primary category: Speech & Audio
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.
Project last updated:08/29/26
GitHub Stars
2.7K
Forks
448
Contributors
36
License
Apache-2.0
Why we included this project
Commercial meeting notetakers generally keep your recordings in their own cloud, which is a dealbreaker for teams with strict data rules. Vexa takes the opposite approach: you run the stack yourself, and a real bot joins Google Meet, Microsoft Teams, Zoom, or Jitsi calls to stream speaker-attributed transcripts live through an API you control. The transcription side works on its own, so if that's all you need you can deploy a bot, read the WebSocket stream, and skip the agent layer entirely. Teams that want more can let the same transcripts feed sandboxed agents that turn meeting notes into a Markdown knowledge base inside a git repo you own. That makes it worth a look for privacy-conscious teams and regulated environments that need self-hosted, air-gap-ready transcription without handing their meeting data to a third party.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
whisper.cpp
Port of OpenAI's Whisper model in C/C++
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
VibeVoice
Open-Source Frontier Voice AI
voicebox
The open-source AI voice studio. Clone, dictate, create.
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production