On-premise AI notetaker for Arabic and English meetings: every meeting, distilled to what matters
Bilingual meeting notes for Arabic and English teams
From join to summary, every step is automated and secure.
On-premise meeting AI, on your own infrastructure
Deploy on-premise or as a dedicated private cloud, for regulated teams that need meeting data to stay inside their own infrastructure. The speech and language models can run on your own hardware, and the accuracy figures we publish describe exactly that self-hosted configuration.
Joins & records automatically
Schedule a meeting and the bot joins on time across Google Meet, Zoom, and Microsoft Teams.
Bilingual transcription
Transcribes Arabic and English in one sentence, keeping English terms in Latin script instead of transliterating them.
Meeting notes that decide
Get the summary, decisions, risks, and owner-assigned action items — not just a wall of text.
Roles & sharing
Organization roles, workspace groups, and per-recording sharing keep access exactly where it should be.
On-premise meeting AI, on your own infrastructure
Deploy on-premise or as a dedicated private cloud, for regulated teams that need meeting data to stay inside their own infrastructure. The speech and language models can run on your own hardware, and the accuracy figures we publish describe exactly that self-hosted configuration.
How it works
Paste a meeting link
Or schedule it — one-off or recurring.
The bot records
It joins, captures audio or video, and stores the recording in your organisation's space.
Get your meeting minutes
Summary, decisions, and action items, ready to share.
AI notetaker for Google Meet, Zoom and Microsoft Teams
One notetaker for the three platforms your meetings already run on. Khulasa joins as a named participant, records the room, and returns the same Arabic and English meeting notes whichever link you paste — with nothing to install on the platform side.
Google Meet AI notetaker
Joins from its own Google account and asks the host to admit it. Works with Google Meet links from personal accounts and Google Workspace alike; nothing changes in Workspace and nothing is installed.
Zoom AI notetaker
Joins from the browser as a guest named KhulasaBot (Recording). No Zoom cloud recording and no paid Zoom plan — the invite link with its passcode is all it needs.
Microsoft Teams AI notetaker
Joins as a guest from the lobby, with no Microsoft 365 Copilot licence, no Microsoft account for the bot and nothing installed in your tenant.
Go deeper
How Arabic, English and code-switched meetings become a transcript, a summary and minutes — and what we measured.
Private cloud or on-premise: self-hosted speech and language models, no outbound connection, and audio that stays with you.
The five-minute admit window, the chat notice, what attendees see on each platform, and what can go wrong.
Measured against other systems
+16.3 … +34.7points
Paired intervals at 95% confidence, all excluding zero — most conservative lower bound≥ +8.8
English words inside Arabic speech
More accurate on the English words spoken mid-Arabic-sentence than each of the four competing configurations, one by one — paired intervals at 95% confidence, all excluding zero. This is the one axis where we claim the lead.
>3×
Arabic–English switch points kept
When someone switches between Arabic and English mid-sentence, more of those moments survive into the transcript — over three times as many as any of the three Speechmatics configurations kept. The error counted is a script collapse: an English word written in Arabic letters.
Every figure here describes the self-hosted configuration, running on your own hardware. We ran this comparison ourselves on 80 code-switched utterances of real UN ESCWA meeting audio. It is not a measurement of our hosted tiers.
We do not claim an overall win. On overall word error rate we report parity with the leading vendors rather than a ranking, and all three Speechmatics configurations are ahead of us on the Arabic words.
Product and company names are the trademarks of their respective owners. Khulasa is not affiliated with, sponsored by or endorsed by any of them, and no vendor reviewed or approved these results.
Your meetings stay yours
Protection built in from the moment the bot joins to long-term storage.
Encrypted connections and encrypted backups
Recordings and transcripts reach Khulasa over HTTPS (TLS 1.2 or later), and database backups are encrypted.
Granular access control
Organization roles, workspace groups, and per-recording sharing decide exactly who can see what.
Tenant isolation
Every organization's data is strictly separated — your recordings never mix with anyone else's.
Not used to train AI models
Your meeting content is processed to produce your analysis and to run and secure the service. We do not use it to train AI models.
Simple, seat-based pricing
Start free. Add seats and power as your team grows.
Business
$34 / seat / mo
- Add seats as you grow
- 120 hours of recording / user / month
Private Cloud
Contact us
A dedicated, isolated cloud deployment run for your organization.
On-Premise
Contact us
For regulated, government, and data-sovereignty-bound teams. Deployed and run on your own servers.
Questions about the AI notetaker
The short answers. The pricing page and the integration pages go into detail.
Is Khulasa an AI note taker?
Yes. Khulasa is an AI notetaker: it sends a bot that joins your Google Meet, Zoom or Microsoft Teams call as a named participant, records it, transcribes Arabic and English, and writes the meeting notes — a summary, the decisions taken and the action items with their owners. The notes are ready to share from the meeting page once the meeting ends.
Does it take meeting notes in Arabic?
Yes. Arabic and English are both first-class. Transcription handles either language, or a meeting where people switch between Arabic and English mid-sentence, and keeps English terms in Latin script. The summary, decisions and action items come back in whichever language dominated the conversation, and the app itself is fully bilingual, with a right-to-left Arabic interface.
Can it run on-premise?
Yes. Private Cloud is a dedicated, isolated deployment we run for you, hosted where you need it — the location is agreed when we set it up. On-Premise is the same system installed on your own hardware, able to run with no outbound connection at all. Both are built to run self-hosted speech and language models, so audio does not have to leave the deployment; the model setup is confirmed with you when we size it, and both are quoted per organisation.
Which meeting platforms does it join?
Google Meet, Zoom and Microsoft Teams. Khulasa joins as a named participant and records the room, with nothing to install on the platform side: paste a meeting link, or connect your Google or Microsoft calendar and let it join on time. Action items can be sent to Jira from the meeting page.