Back to directory

Vexa

An open-source meeting-transcription platform whose bot joins Google Meet, Microsoft Teams, and Zoom calls and streams real-time, speaker-attributed transcripts that agents can turn into a shared knowledge base.

Vexa

Vexa runs a bot that joins Google Meet, Microsoft Teams, and Zoom calls and streams speaker-attributed transcripts in real time, either through a hosted API or a fully self-hosted deployment. The transcripts feed sandboxed agents that compile them into a Markdown knowledge base stored in a git repository, so a team's meeting history stays portable, diffable, and searchable rather than living only inside a vendor's chat interface.

The hosted service can be used purely as a transcription API, sending a bot into a meeting and reading back its stream without touching the agent layer at all, while the sandboxed knowledge-agent pipeline, which reads and writes the repository through isolated containers with no network egress, is only available when self-hosting. Support for Jitsi meetings is offline-proven, with live validation still pending.

It is written in Python and released under the Apache License 2.0.

More in Speech

See all 119
  • ELI v2.0

    geteli.tech

    A private AI assistant and local runtime that runs entirely on the user's own hardware: it holds conversations by voice or text, controls the desktop, reads the screen, writes code, and builds a private model of the user over time.

  • VoiceAssistant

    github.com

    A fully local, full-duplex voice assistant for Windows that lets a user interrupt it mid-sentence and answers using visual context captured from the desktop the instant the user speaks.

  • vibe

    github.com

    A cross-platform desktop application for transcribing audio and video offline using OpenAI's Whisper models on the user's own machine, with an optional OpenAI backend when a user supplies an API key.