n8n
Meeting
Transcription
Drop a meeting bot into Google Meet, Microsoft Teams, or Zoom from any n8n workflow. Real-time transcripts piped to Notion, Slack, Airtable, HubSpot — anything n8n supports. Open source, self-host or cloud.
Waiting for meeting participants…
Feed meetings into your AI. Live.
AI needs data, and the best data is real-time. Vexa streams transcripts, audio, and context from any meeting straight to your models and agents — as it happens.
Built for n8n
Vexa fits into n8n as an HTTP Request node: one call kicks off a bot in the meeting platform of your choice, transcripts come back in real time via webhook or polling, and you wire them anywhere n8n reaches. No custom node required (though one is on the roadmap). Same Apache-2.0 license, same self-host story — your n8n instance and your Vexa instance can both run inside your VPC, no audio crosses the public internet.
- No custom node required — Vexa works today via n8n HTTP Request + Webhook nodes
- Works across Google Meet, Microsoft Teams, and Zoom — one config, three platforms
- Self-host n8n + self-host Vexa = both halves under your VPC, no third-party SaaS in the audio path
{
"method": "POST",
"url": "{{$env.VEXA_API_BASE}}/bots",
"authentication": "headerAuth",
"headerAuth": {
"name": "X-API-Key",
"value": "{{$env.VEXA_API_KEY}}"
},
"body": {
"platform": "google_meet",
"native_meeting_id": "{{$json.meeting_code}}",
"transcribe_enabled": true,
"transcription_tier": "realtime"
},
"options": {
"response": { "fullResponse": true }
}
}
// Step 2 — Webhook node receives transcript chunks
// Configure Vexa to POST to: {{$env.N8N_WEBHOOK_URL}}/vexa-transcripts
// Each chunk becomes a workflow trigger.Set $API_BASE to https://api.cloud.vexa.ai (hosted) or http://localhost:8056 (self-host). Get $API_KEY from /get-started.
n8n integration FAQ
What automation builders ask before they wire Vexa into n8n.
Do you have a dedicated n8n community node?
Not yet — a community node is on the roadmap. Today Vexa works via standard n8n HTTP Request + Webhook nodes, which is enough for every workflow we've seen customers build: trigger bots, receive transcripts, push to downstream tools.
Can the n8n workflow trigger automatically when a calendar invite arrives?
Yes. The common pattern: Calendar trigger node (Google Calendar / Outlook) → IF node (meeting matches a rule) → HTTP Request to Vexa /bots. We document the full pattern in the n8n integration doc.
How do transcripts come back into n8n?
Two options. (1) Webhook: configure Vexa to POST to an n8n Webhook node URL — each transcript chunk triggers your downstream workflow. (2) Polling: schedule an n8n cron to call GET /transcripts/{platform}/{native_meeting_id} every few seconds. Webhook is preferred for near-real-time pipelines.
What downstream tools are easy to wire up?
Anything n8n supports — Notion (auto-create a page per meeting), Slack (post summary to a channel), Airtable (append rows), HubSpot / Salesforce (attach transcript to deal), Google Drive (export to doc), OpenAI / Anthropic (run summarization). Customers most commonly run Notion + Slack + CRM in parallel.
Can I self-host both n8n and Vexa for full data residency?
Yes — that's the canonical setup for regulated industries. Both n8n and Vexa ship as Docker images; you run them in your VPC behind your firewall. No audio leaves your infrastructure. We have GDPR / SOC 2 customers running exactly this stack.
Common patterns
What teams build with Vexa + n8n
Three patterns we see repeatedly across n8n + Vexa customers.
Meeting → Notion knowledge base
Scenario
You run a research-heavy team and want every customer call automatically captured into your Notion knowledge base, tagged by participant and topic.
What you get
Calendar invite triggers n8n → HTTP Request kicks off Vexa → Webhook receives transcript chunks → n8n Notion node creates a page per meeting with structured frontmatter. Zero manual note-taking.
Sales call → CRM enrichment
Scenario
Sales reps live in HubSpot / Salesforce. You want transcripts attached to the deal record, with summaries and action items extracted automatically.
What you get
n8n triggers on the calendar invite, fires Vexa for the matched meeting, ingests transcripts, runs them through an OpenAI / Anthropic summarization node, attaches results to the CRM deal record. Reps don't touch a thing.
Slack live alerts on meeting events
Scenario
You want real-time alerts when key phrases come up in a customer call — "cancel", "renewal", competitor names — so a manager can join or follow up in seconds.
What you get
Webhook receives each transcript chunk → n8n IF node matches keywords → Slack node posts to a channel with the chunk + meeting link. Sub-5-second latency from speech to alert.
Quickstart
Wire up Vexa in n8n in 5 minutes
No custom node required. HTTP Request + Webhook nodes cover every pattern we've seen.
- 1
Get a Vexa API key
Sign in at vexa.ai/signin with Google and copy your key from your account page — free credit, no card. Or mint one locally on your self-hosted gateway.
- 2
Set env vars in n8n
Add VEXA_API_BASE and VEXA_API_KEY to your n8n environment so workflows can reference them.
- 3
Wire the trigger
Calendar node → IF (filter meetings) → HTTP Request to POST /bots. See the JSON config to the right.
- 4
Receive transcripts
Add an n8n Webhook node; configure Vexa to POST transcript chunks to its URL. Each chunk becomes a workflow run.
- 5
Wire the downstream
Pipe transcript chunks into Notion / Slack / Airtable / HubSpot / OpenAI nodes — anything n8n supports.
How it works under the hood
n8n architecture
n8n acts as the orchestration layer; Vexa is the meeting-bot capability. n8n HTTP Request → Vexa /bots → bot pod joins meeting → Whisper transcribes audio → chunks POSTed back to n8n Webhook node → your downstream nodes consume them. Both halves can self-host in the same VPC.
Pipeline
Documentation
Go deeper on the n8n integration
n8n setup, webhook patterns, downstream node recipes.
n8n integration guide
Full setup: Calendar trigger, HTTP Request, Webhook node, downstream patterns.
Bots API reference
POST /bots payload, status polling, lifecycle hooks.
Webhooks
Transcript chunk delivery format, retry semantics, signature verification.
Local webhook development
Develop the webhook side of the n8n integration locally with tunnels.
Authentication
API keys, admin tokens, scoping for multi-tenant n8n setups.
Platforms — Google Meet, Teams, Zoom
Per-platform setup notes referenced from your n8n workflows.
Full reference at docs.vexa.ai.
Related reading
Keep going on n8n
Tutorials, deep-dives, and adjacent surfaces from across the Vexa substrate.
Google Meet transcription n8n workflow (tutorial)
Step-by-step n8n setup with Calendar trigger + Vexa HTTP Request node.
Claude MCP integration
Alternative agent-orchestration path: connect Claude or ChatGPT via MCP instead of n8n.
Zapier integration
Same patterns, Zapier instead of n8n — useful when teams already standardize on Zapier.
A seat, an hour,
or free
A seat for your agent. An hour for what you build. Free 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
Vexa Delivery: self-hosted, self-updating, in your own cloud
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 across Google Meet, Microsoft Teams, and Zoom. Add real-time transcription for +$0.20/hr, so $0.50/hr all-in.
Which plan is right for me?
Two tracks, by the door you come in through. Individual ($12/seat/mo) is for one person and their agents—MCP to connect agents, one concurrent bot, unlimited meetings. Build on Vexa ($0.30/bot-hr) is for products built on the API—pay as you go, unlimited bots. Self-host for free from GitHub if you need full data control, 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 — Stripe charges a fixed fee per payment, so smaller amounts would mostly be fees; automatic top-ups follow the same minimum. All features are available: audio capture, transcription, real-time data, and full API access.
Can I self-host Vexa?
Yes. Vexa is Apache 2.0 licensed and fully self-hostable. Deploy with Docker Compose, Kubernetes, or OpenShift on your own infrastructure with complete data sovereignty.
How does Vexa compare to Recall.ai?
Vexa is open source, self-hostable, and up to 40% cheaper. Bot: $0.30/hr vs Recall.ai ~$0.50/hr. Transcription add-on: $0.20/hr vs ~$0.15/hr. 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, real-time transcription, recording, storage, REST API, WebSockets, and the UI Dashboard. It supports Google Meet, Microsoft Teams and Zoom.
Ready when you are
Build the workflow.
Wired in 5 minutes.
No credit card, no Marketplace approval. Get an API key, paste the HTTP Request config, receive transcripts in your n8n workflow.
Apache 2.0 · Self-host or cloud · No credit card required