Deploy Now

SaaS Alternative

Otter.ai Fireflies.ai Recall.ai Gong

Categories

Self-Hosted Developer Tools Productivity AI Communication API Meeting Transcription

Stars

2,774

Forks

472

Watchers

13

Developer links

Last Updated: 09-11-2026
Share on X

Vexa

Vexa is the only Apache 2.0 meeting bot API that self-hosts the complete transcription pipeline, from bot dispatch to Whisper speech-to-text to knowledge agents, with zero audio leaving your infrastructure. A single POST /bots request sends a transcription bot into any Google Meet, Microsoft Teams, or Zoom call, where it captures audio, runs speaker-attributed transcription through faster-whisper or any OpenAI-compatible endpoint, and streams results to your application via real-time WebSocket with sub-second latency. The built-in agent framework watches live transcripts and your accumulated workspace context, answering mid-call questions grounded in your own meeting history and wiki. An MCP server connects Vexa to Claude, Cursor, and other compatible AI tools, turning every captured meeting into queryable context for external agents. The Terminal, a bundled Next.js web workbench, lets you send bots, watch live transcripts, manage users and API tokens, and chat with your meeting archive from a browser. Docker Compose brings the full stack up on one Linux host in five minutes; the Helm chart scales to thousands of users on Kubernetes with a Pod-per-bot architecture and built-in RBAC. Recordings persist in MinIO or any S3-compatible store, transcripts in Postgres, with Redis handling queues and scheduling. Deploy on RepoCloud for a dedicated VPS with full root SSH access and browser console. Apache 2.0 licensed.

Vexa
Vexa
Vexa
Vexa
Vexa

Benefits

  • Complete Air-Gapped Data Sovereignty
  • Every component, including bot dispatch, Whisper transcription, agent inference, and recording storage, runs inside your own VPC. No audio or transcript data ever crosses your firewall, meeting healthcare and legal compliance requirements.
  • One API for All Platforms
  • A single POST /bots endpoint handles Google Meet, Microsoft Teams, Zoom, and experimental Jitsi support. No platform-specific SDKs or integrations needed; one request dispatches a bot to any meeting.
  • AI Agents Inside Your Meetings
  • Sandboxed knowledge agents access live transcripts and your accumulated workspace context during calls. Ask questions mid-meeting and receive answers grounded in your entire meeting history and connected wiki documents.
  • Scales from Laptop to Cluster
  • Docker Compose runs the full stack on a single host for development. The Helm chart deploys to Kubernetes with Pod-per-bot isolation, RollingUpdate strategies, and PodDisruptionBudgets for production workloads.

Features

  • Real-Time WebSocket Transcripts
  • Speaker-attributed transcription streams via WebSocket with sub-second latency. Powered by faster-whisper with automatic language detection per segment and configurable model sizes.
  • MCP Server Integration
  • Built-in Model Context Protocol server exposes meeting transcripts and agent capabilities to Claude, Cursor, and any MCP-compatible AI tool for external automation workflows.
  • Terminal Web Workbench
  • Next.js dashboard at port 13000 provides meeting management, live transcript viewing, user administration, API token management, and bot monitoring without writing any API calls.
  • Flexible Runtime Backends
  • Choose Docker containers via socket, child processes without Docker dependency, or Kubernetes Pods for cluster-scale deployments. Switch backends with a single environment variable.
  • Recording and Storage
  • Audio recordings persist in MinIO or any S3-compatible object store. Transcripts and metadata live in Postgres with Redis handling message queues and job scheduling.