Research · Discovery · Apache 2.0

Customer
Discovery
Transcripts

Auto-transcribe every customer discovery and user research interview across Google Meet, Microsoft Teams, and Zoom. Open-source, self-hostable, GDPR-friendly. Pipe transcripts to Dovetail, Notion, Airtable, or your synthesis tool of choice.

No credit card required
Starred by 2k+ developers on GitHub
vexa · live transcript
LIVE

Waiting for meeting participants…

Connected · Google Meet
Teams
Meet
Vexa
🦀
Real-time Meeting Data for AI

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 research teams

Research and product teams run dozens of customer interviews per month — discovery calls, jobs-to-be-done sessions, usability tests, win/loss reviews. The transcript is the input to every downstream artifact (research repository, persona library, synthesis report, leadership readout). Vexa drops a bot into each call, produces accurate transcripts with speaker tags, and pipes them to your synthesis tool. Apache 2.0 + self-host means consent-sensitive interviews (B2B customers, regulated industries, EU participants) can keep audio entirely in your infrastructure.

  • Drop a bot into every interview across Meet, Teams, and Zoom — one workflow, three platforms
  • Pipe transcripts to Dovetail, Notion, Airtable, or any synthesis tool via webhook / n8n / Zapier
  • Self-host for GDPR / consent-sensitive interviews — audio stays in your VPC, never leaves
Auto-transcribe every scheduled interview, route to your synthesis tool
# Trigger from your scheduler (Calendly, SavvyCal, Calendar API):
curl -X POST "$API_BASE/bots" \
  -H "X-API-Key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "platform":          "google_meet",
    "native_meeting_id": "abc-defg-hij",
    "transcribe_enabled": true,
    "transcription_tier": "realtime",
    "bot_name":           "Research Notetaker",
    "metadata": {
      "study_id":         "discovery-2026-q2",
      "participant_id":   "p-042",
      "research_topic":   "onboarding-friction"
    }
  }'

# After the call, fetch the full transcript:
curl "$API_BASE/transcripts/google_meet/abc-defg-hij" \
  -H "X-API-Key: $API_KEY" > interview.json

# Pipe to Dovetail / Notion / Airtable via n8n, Zapier,
# or your own webhook + synthesis pipeline.

Set $API_BASE to https://api.cloud.vexa.ai (hosted) or http://localhost:8056 (self-host). Get $API_KEY from /get-started.

Customer-discovery transcription FAQ

What research and product teams ask before swapping transcription services for Vexa.

Is Vexa accurate enough for verbatim research synthesis?

For English interviews with clean audio (single speaker turn, low background noise), Whisper-large-v3-turbo is research-grade — comparable to transcription services research teams already pay for. For accent-heavy interviews or noisy environments, you may want to validate against your specific call shape before relying on raw transcripts. Speaker diarization for 2-participant interviews (researcher + participant) is solid.

How does this fit with Dovetail / Notion / Airtable workflows?

Standard pattern: Vexa transcribes → webhook delivers the transcript → n8n / Zapier / Make (or your own script) creates the artifact in Dovetail (insight + tags), Notion (interview page), or Airtable (rows). Researcher synthesis still happens in your tool of choice; Vexa just removes the manual transcription step.

What about consent? Some participants don't want a bot in the call.

Vexa is a transparent participant — the bot appears in the participant list visibly named (default "Vexa Notetaker", customizable). Research best practice is to disclose recording + transcription in the consent script before the interview starts, and to allow opt-out. Vexa doesn't solve the consent layer; it does ensure the bot is visible (not stealthy) which makes the consent conversation honest.

Can I run this fully on my infrastructure for EU participants / GDPR?

Yes — self-host Vexa in your EU cloud (AWS Frankfurt, GCP Belgium, Hetzner, OVH). Audio capture, transcription, and storage all happen on your infrastructure. Zero sub-processors. Pair with your existing DPA template. We have research teams running exactly this setup for EU customer interviews.

Does it handle multi-language interviews?

Whisper supports 90+ languages with varying accuracy. For research interviews specifically, English / Spanish / French / German / Portuguese / Mandarin are well-supported; less common languages may need validation. See the transcription-quality doc for the full language matrix and accuracy notes.

Common patterns

What research teams build with Vexa

Three patterns design, product, and customer-research teams build with Vexa as the transcription layer.

01Pattern 1

Discovery interview → Dovetail synthesis pipeline

Scenario

Your product team runs 20-30 customer discovery interviews per quarter. Manual transcription costs $50-100/hour through services; researchers prefer to spend that budget on participant incentives.

What you get

Calendly trigger fires Vexa per scheduled interview → transcripts arrive in Dovetail via n8n / direct API → researcher tags and synthesizes in their normal flow. Transcription cost drops to compute COGS; researchers stay in Dovetail.

02Pattern 2

Jobs-to-be-done research at scale

Scenario

You're running a JTBD study with 50 interviews across 5 segments. You want the transcripts auto-organized by segment, persona, and theme — so synthesis happens on structured artifacts, not file folders.

What you get

Vexa metadata field carries study_id, segment, participant_id. Webhook routes transcripts to per-segment Notion pages or Airtable rows. Researchers see a structured library, not a folder of audio files.

03Pattern 3

Win/loss interviews tied to deal records

Scenario

Sales-product alignment runs win/loss interviews after every $25k+ deal closes (or loses). Findings need to feed product roadmap and sales playbook updates.

What you get

Vexa transcribes each interview; metadata carries the deal_id from HubSpot/Salesforce; transcripts land on the deal record AND in a win/loss research repository. Findings get traced back to specific deals + segments for product prioritization.

Quickstart

Auto-transcribe every interview in 5 minutes

Trigger from your scheduler. Route transcripts to your synthesis tool. Stay in Dovetail / Notion / Airtable for everything else.

  1. 1

    Get a Vexa API key

    Sign up at vexa.ai/get-started or run the self-hosted gateway (recommended for EU / consent-sensitive interviews).

  2. 2

    Wire the trigger

    Calendly / SavvyCal webhook, Calendar API automation, or your scheduling tool. Fire Vexa per scheduled interview with study + participant metadata.

  3. 3

    Capture transcripts

    Webhook chunks or GET /transcripts after the call. Most research teams use post-call (batch) — real-time isn't typically needed for synthesis.

  4. 4

    Route to synthesis tool

    Dovetail (via API), Notion (via API or n8n), Airtable, Confluence — anywhere your synthesis already lives.

  5. 5

    Validate consent flow

    Update your interview script to disclose the visible note-taker bot. Standard research-ethics practice — Vexa makes the disclosure honest because the bot is openly named.

How it works under the hood

customer interviews architecture

Vexa transcribes; your synthesis tool (Dovetail, Notion, Airtable, custom) holds research artifacts. Audio path stays in Vexa (hosted or self-hosted); transcripts are the artifact handed off. For GDPR / consent-sensitive interviews, the self-host path keeps audio and transcripts inside your EU infrastructure — pair with your existing DPA template for participant consent.

Pipeline

bot pod audio capture whisper-svc transcript chunks REST / WebSocket
Pricing

Pay only for
what you use

Self-host for free, or let us run it for you. Simple usage-based pricing—no per-seat tax.

Free
$0

Apache 2.0 · Self-host forever

Best for teams who need full control

View on GitHub
Full platform — no limits
Your infrastructure, your data
Google Meet + Teams + Zoom
Docker Compose / K8s deploy
REST API + WebSockets + Dashboard
Community support
Individual
$12/mo

1 bot · Flat monthly · Everything included

Best for personal use — 1 meeting at a time

No credit card required

1 concurrent bot
Google Meet + Teams + Zoom
Real-time transcription included
Audio capture + webhooks
12-month audio storage
REST API + WebSockets + Dashboard
Pay-as-you-go
$0.30/hr

Bot infrastructure · +$0.20/hr transcription

Best for teams & API builders · $5 free credit

No credit card required

Unlimited bots
Google Meet + Teams + Zoom
Transcription add-on: +$0.20/hr
Audio capture + webhooks
12-month audio storage
REST API + WebSockets + Dashboard
Enterprise

On-premises, OpenShift, Kubernetes. Dedicated support + SLA.

Book a call
Transcription API

For self-hosted Vexa bot users. Transcription only — $0.002/min.

Get started
Bot: Vexa $0.30/hr vs Recall.ai $0.50/hr —40% cheaper

Frequently asked questions

What's included in the $0.30/hr Bot Service?

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 ($0.50/hr total).

Which plan is right for me?

Choose Individual ($12/mo) if you need one bot for personal use—it includes real-time transcription, storage, and the Dashboard. Choose Pay-as-you-go ($0.30/hr) if you need multiple simultaneous bots or want to pay only for what you use—ideal for teams and API integrations. Both plans include Google Meet and Microsoft Teams support. Self-host for free from GitHub if you need full data control.

How does the free credit work?

Every new account gets $5 in free bot credit—no credit card required. That covers ~16 hours of bot time at $0.30/hr. 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?

The Individual plan ($12/mo) is for single users who need one concurrent bot with unlimited meetings. It includes real-time transcription, recording, storage, REST API, WebSockets, and the UI Dashboard—everything you need for personal meeting intelligence. It supports Google Meet and Microsoft Teams, with Zoom coming soon.

Ready when you are

Transcribe every interview.
Synthesize faster.

No credit card on Vexa side, no per-minute transcription service. Get an API key, wire it to your scheduler, transcripts flow into your synthesis tool.

Apache 2.0 · Self-host or cloud · No credit card required