Nobody joins your call.
OpenNoteTaker records the meeting from your own browser tab, transcribes it on your machine and works out who said what. No bot appears in the participant list, no audio is uploaded, and there is no subscription to cancel.
Free for everything that runs on your device. Works in Chrome, Edge, Safari and Firefox — nothing to install, and no account needed to start.
The difference
Every other note taker sends a guest into the room.
Otter, Fireflies and Read all work the same way: a bot dials into the call, sits in the participant list, and has to be admitted. Everyone present can see it. Plenty of companies block it outright, and plenty of guests object to it. OpenNoteTaker takes a different route into the audio.
OpenNoteTaker
- Records the audio already playing in your tab, plus your microphone
- Nothing joins the meeting, so there is nothing to admit or explain
- Transcribed by Whisper compiled to WebAssembly, in the tab
- Works on a call your employer would never let a bot into
- Works on anything with sound — a webinar, a recording, a phone on the desk
Bot-based note takers
- A named participant appears in the call
- Someone has to let it in, every time
- The audio is uploaded and transcribed on their servers
- Blocked by many IT policies, and awkward with external guests
- Only works on the platforms their bot supports
How it works
Four steps, none of them on a server.
Join
Join the meeting as yourself. An optional browser extension notices Google Meet, Zoom, Teams and VooV calls and offers to record; without it you press the button.
Consent
Every recording opens on a consent screen with words you can read out. It cannot be skipped or remembered, because consent is something you get from people rather than a setting.
Record
The tab and your microphone are captured together, so both sides of the call are on the recording. You can change microphone mid-meeting without breaking the file.
Read
Whisper transcribes it in the tab, speakers are separated, and you get a searchable note you can export as subtitles, Markdown, text, JSON, CSV or HTML.
Privacy
“Private” here means the audio has nowhere to go.
This is a property of how the thing is built, not a policy that could be changed later. The transcription engine is compiled into the page. There is no upload step to turn off, because there is no upload step.
What stays on your machine
- The recording itself — and it is discarded unless you ask to keep it
- Every transcript, title and speaker name, in your own browser storage
- Transcription, speaker separation, search and the free summary
- Every export format
What can leave, only if you press it
- AI-written minutes — sends the transcript text
- A question across your meetings — sends the passages it found
- Translating a finished transcript — sends the lines
- Never audio, on any of them. The privacy page shows the request body
Pricing
Free for everything that runs on your machine.
Not a trial and not a tier — work done on your own hardware costs us nothing to provide, so charging for it would be charging for the login. The three things that use our backend are bought as credits that do not expire and do not renew.
| What | Where it runs | Price |
|---|---|---|
| Recording, with no bot in the call | Your browser | Free |
| Transcription, 99 languages | Your browser | Free |
| Telling speakers apart | Your browser | Free |
| Topics, action items and decisions | Your browser | Free |
| Search across every meeting | Your browser | Free |
| Subtitles, Markdown, text, JSON, CSV, HTML | Your browser | Free |
| AI-written minutes | Our backend | Credits |
| A question across your library | Our backend | Credits |
| Translating a finished transcript | Our backend | Credits |
The exact price of a job is on the button before you press it, computed by the same code that does the charging. A job that fails costs nothing.
Questions
Before you start.
Does it join my meeting as a participant?
No. It records the audio already playing in your browser tab, so nothing appears in the participant list and nobody has to admit a guest. That is the whole reason this exists: bot-based note takers are visible to everyone in the call and blocked outright by many companies.
Is it legal to record a meeting this way?
That depends on where everyone in the call is, and OpenNoteTaker cannot answer it for you — so it does not pretend to. Every recording opens on a consent screen that gives you words to say out loud, and there is no way to skip it or tell it to stop asking. Consent is something you get from people, not a checkbox you tick once.
Where does the audio go?
Nowhere. Whisper is compiled to WebAssembly and runs in the tab, so the recording never leaves the machine. The model weights are downloaded once from Hugging Face and cached; after that, transcription works offline.
Do you keep my recordings?
There is nowhere for us to keep them. Notes live in your own browser storage, and the audio is discarded when you close a note unless you turn on “keep the audio”. An account, if you make one, holds a sign-in method and a credit balance — no transcripts and no titles.
Can it tell who said what?
Yes, on your own device, with no model to download. It works well for two or three people with distinct voices and struggles with similar voices, crosstalk, and one person who changes microphone mid-call. You can set the number of people by hand and move any line to someone else in one click.
What about a meeting held in two languages?
The language is detected every few seconds rather than chosen once for the whole file, so a meeting that moves between English and Chinese comes back in both scripts, on one timeline. Choosing a single language up front is the usual reason a bilingual recording comes out as nonsense.
Will recording only my microphone work?
Badly, and the app says so. Your browser’s echo cancellation removes what is coming out of your speakers — which on a call is everyone else. Record the tab as well; that is the default, and the app warns you if you turn it off during a call.
Is it open source?
Yes, under MIT and Apache-2.0. The engine is Rust compiled to WebAssembly — the timeline, speaker separation, the extractive summariser and every export format — so the privacy claims on this page can be checked rather than taken on trust.