Vexavexa
Book a demo
Comparison

Vexa vs Recall.ai

Recall.ai is a hosted API you rent. Vexa is open source: the meeting bot, plus knowledge and agents on top, on your own servers.

Renting
Owning

Renting
or owning

Both send a bot and return a transcript. The choice: rent that infrastructure, or own it and your data.

Where recordings and transcripts live

Own · Vexa, self-hosted

Recordings in your object storage, transcripts in your database.

Rent · Recall.ai

Recall.ai’s cloud (US, EU or Tokyo); Zero Data Retention streams media without storing it.

Who can change the terms

Own · Vexa, self-hosted

Apache-2.0, perpetual and irrevocable: we cannot withdraw it from your copy.

Rent · Recall.ai

Recall.ai can change fees with notice, amend terms, or withdraw the service.

If the vendor is sold or changes direction

Own · Vexa, self-hosted

Your deployment keeps running, and you can fork the code.

Rent · Recall.ai

Your product keeps running on Recall.ai, under the terms then in force.

Which model it runs on

Own · Vexa, self-hosted

A speech-to-text model you choose and deploy, via an OpenAI-compatible endpoint.

Rent · Recall.ai

Built-in, a provider like Deepgram, or yours. The bot runs on Recall.ai.

Vexa is also available hosted, at the prices below. That is renting from us. Recall.ai details are from its pricing, Terms of Use, comparison page and documentation, read 3 October 2026.Weighing another meeting bot API? See Vexa vs Meeting BaaS.

Feature
comparison

FeatureVexaRecall.ai
Open source
Self-hostable
Google Meet
Microsoft Teams
Zoom
Real-time transcription
Recording + storage
MCP server
REST API
WebSocket streaming
Webhooks
Price
Vexa
Hosted: $0.30 per bot-hour, plus $0.20/hr transcription.
Self-hosted: no licence fee.
Recall.ai
$0.50/hr of recording, plus $0.15/hr built-in transcription; recall.ai/pricing, read 3 October 2026.
Knowledge and agents
Knowledge from your meetings
Vexa
A workspace of people, decisions and notes, on your servers (early)
Recall.ai
Transcripts, recordings and metadata by API; you build the knowledge.
Agents on that knowledge
Vexa
Self-hosted: an agent drafts the write-up; a person approves it (early)
Recall.ai
Infrastructure for live agents and an MCP server; you bring the model.

Knowledge and agents: from Recall.ai’s notetaker API page, Output Media docs and MCP docs, read 4 October 2026.

Switching from Recall.ai?

Both are REST APIs: you send a bot with one call and get the transcript by webhook or WebSocket.

No credit card required

Other comparisons

Frequently asked questions

Is Vexa a drop-in replacement for Recall.ai?

No. Both use REST patterns for sending bots, managing meetings and retrieving transcripts, but the endpoints are different, so your client code needs changes.

Where does my meeting data live?

With self-hosted Vexa, on your infrastructure. With hosted Vexa, on our cloud, with 12 months of audio storage. Recall.ai stores media in its cloud, in a region you choose, for as long as your retention setting keeps it.

Can I start with Vexa cloud and move to self-hosted later?

Yes. Start with our managed cloud. When you are ready to scale or need the audio to stay inside your network, deploy the same open-source code on your own infrastructure with Docker, Kubernetes, or OpenShift.