Meeting
Transcription
API
Waiting for meeting participants…
Real-time Transcription
Transcripts arrive while the meeting is still running. With speaker names, delivered over WebSocket.
▌
Alice ▌
Multilingual
Set each meeting's language and every segment is transcribed in it.
Aino ▌
For your agent, your product,
or your company
Your agent hears your meetings.
Paste one prompt into Claude Code, Codex or any MCP client. Your meetings arrive in the agent you already use.
Per seat · Google Meet, Teams, Zoom
Meeting bots inside your product.
Send a bot with one API call, stream the transcript over WebSocket, keep the recording. Your users, your product, our engine.
$ curl -X POST "$API_BASE/bots"$ curl "$API_BASE/transcripts/google_meet/abc-defg-hij"
Pay per bot-hour · REST + WebSocket
Your meetings, on your own servers.
Vexa runs in your own cloud, with your own model, instead of a vendor’s. You choose when to take each release, and we sit with you and merge your PRs.
Let's talk
In fund distribution, private credit or wealth? Vexa for finance
Feed meetings into
your agent
Copy one prompt, paste it in Claude Code, Codex or any MCP client. Your agent joins the meeting and reads the transcript as it happens.
Transcription, recording, and bot control — all via API.
Real-time transcripts, audio capture, and interactive bots. Use the full platform or pick individual primitives.
Storage
All data in Postgres. Query history, search conversations, export via API. Your database, when you self-host.
| meeting_id | speaker | text |
|---|---|---|
| m_9f2a | Alice | We need to finalize... |
| m_9f2a | Bob | I'll have the spec... |
| m_3b7c | Carol | Let's review the... |
Dashboard UI
Full-featured web dashboard included. Manage bots, view transcripts, monitor meetings — ready to use or fork and customize. Fully open-source like the rest of the stack.
Your company’s meetings,
on your own servers
Vexa is open-source AI that turns your company’s meetings into knowledge it owns, on your own servers, with your own model. You run it instead of renting a vendor’s cloud, and when you need something changed, we sit with you and merge your PRs.
You take each release
Releases ship as open-source images and a Helm chart. You choose when to upgrade, and nobody from us touches your cluster.
Your servers, your model
Kubernetes, OpenShift or Docker Compose on your own infrastructure. Transcription and the AI model run where you choose.
Activation sprint
Two weeks, fixed fee. Vexa installed on your servers, and the first teams live.
We sit with you
Your engineers open PRs against the open-source engine. We review, merge, and the next update carries them.
A seat, an hour,
or free
A seat for your agent. An hour for what you build. No licence fee when you run it yourself.
Apache 2.0 licensed open source · self-host forever
Best for teams who need full control
Real-time meeting data, directly in your agent (MCP)
The API · +$0.20/hr transcription · $0.50/hr all-in
Best for builders — pay as you go
Self-hosted in your own cloud, with us beside you
Best for teams running Vexa in production
Frequently asked questions
What's included in Build on Vexa?
The base rate covers bot infrastructure: audio capture, webhooks, and 12 months of audio storage. Add real-time transcription for +$0.20/hr, so $0.50/hr all-in.
Which plan is right for me?
Individual is for one person and their agents. Build on Vexa is for products built on the API. Self-host from GitHub with no licence fee, and talk to us for Enterprise.
How does the free credit work?
Every new account gets $2 in free bot credit—no credit card required. That covers ~6 hours of bot time at $0.30/hr. Top-ups start at $10; automatic top-ups follow the same minimum. All features are available.
Can I self-host Vexa?
Yes. Vexa is Apache 2.0. Deploy it with Docker Compose, Kubernetes or OpenShift on your own servers. Run your own transcription unit and model, and the audio stays inside your network.
How does Vexa compare to Recall.ai?
Recall.ai is a hosted API, so its bots run on its infrastructure. Vexa is open source under Apache-2.0 and can run on yours, with the recordings, the transcripts and the model under your control. See our detailed comparison.
What's the Individual plan for?
Individual is the seat: $12 per seat per month for one person and the agents they connect over MCP. One concurrent bot, unlimited meetings, the REST API, WebSockets, and the UI Dashboard.