Ross ROSS = Recommend OSS · open-source software intelligence for agents

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. observed · 2026-08-28

github.com/Vexa-ai/vexa · homepage · Python · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

87/100

  • Activity 99
  • Release rhythm 98
  • Longevity 40
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: 2.0
  • age_days: 572
  • days_rel: 13
  • days_push: 7
  • n_releases_24m: 39

Full methodology

Adoption not part of the score

2719 stars · 443 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Vexa is an open-source (Apache-2.0) meeting transcription API that dispatches bots to join Google Meet, Microsoft Teams, and Zoom calls and streams speaker-attributed transcripts in real time over REST and WebSocket. It ships an MCP server for AI agents, integrates with workflow tools like n8n and Zapier, and can be self-hosted via Docker Compose or Kubernetes or used as a hosted SaaS.

Use cases

  • transcribe google meet meetings in real time via api
  • auto-join a bot to zoom and teams calls to take meeting notes
  • stream live meeting transcripts to my ai agent over websocket
  • connect claude desktop to live meeting data via mcp
  • self-host a meeting transcription service for data privacy
  • pipe meeting transcripts into salesforce or hubspot records
  • trigger meeting bots from n8n or zapier workflows
  • build meeting minutes and a searchable knowledge base from transcripts

When to choose

  • you need programmatic, API-first meeting transcription across Meet, Teams, and Zoom
  • you want full data control and self-hosting of the audio path
  • you want AI agents to access live meeting context via MCP

When to avoid

  • you only need a simple one-click notetaker app with no API or self-hosting
  • you need platforms beyond Meet/Teams/Zoom with production support (Jitsi is still pending live validation)
  • you cannot run bot infrastructure and prefer a fully managed per-seat product

Facets

service · maturity active

speech-recognition api-framework websocket mcp agent-framework webhook self-hosted sdk speech-processing artificial-intelligence apis self-hosted developer-tools self-hosted python cloud meeting-bots google-meet microsoft-teams zoom transcription-api real-time-transcription meeting-notes speaker-diarization rest-api knowledge-as-code ai-agents automation docker kubernetes web-server

9 sources

Member repositories

RepositoryRoleHealth v2
Vexa-ai/vexamain87

For agents

markdown · JSON · MCP: product_card(name="Vexa-ai/vexa")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem