Transcribe & Summarize your Meetings
Input limits
Audio only, max 100MB, max 30 minutes.
The transcript does not separate speakers: participants are inferred from how people address each other, so sometimes the list stays empty.
The audio sits on private storage, transcription happens on our own servers, and the file is deleted as soon as processing ends.
Upload an audio file
Frequently Asked Questions
Everything about Meeting Minutes AI
How does Meeting Minutes AI work?
The audio is transcribed by Whisper on a server of ours, and the resulting text is summarized into structured minutes with decisions and action items. The transcript does not separate speakers, so the participant list is inferred from how people address each other.
Is my audio safe?
Yes. The audio sits on private storage, never public, and only our own transcriber reaches it through a short-lived signed link. It is deleted as soon as processing ends, and it is never sent to an external transcription service: only the text leaves, for the summary.
How much does it cost?
Nothing: it is free. There is a daily number of meetings and you need a Bink account, also free. Since transcription moved onto our own servers instead of a pay-per-minute service, there is no cost left to pass on.
What formats and limits?
Common audio formats (MP3, M4A, WAV, OGG), max 100MB and 30 minutes.
What do you get back from a recording?
The full transcript plus a summary built around what a meeting is for: who took part, what was decided and which action items came out of it, with the points separated rather than run together.
Where is the audio processed?
On European servers, and it is deleted once the work is done. The file is not passed to a third party service outside the European Union, which is the part that matters when a meeting is confidential.
How accurate is the transcription?
Good on clear recordings with one speaker at a time. Crosstalk, background noise and a distant microphone all cost accuracy, so a recording made close to the speakers is worth more than any later correction.
Where does my upload go?
To a server of ours, and we say so plainly because this is one of the few tools that cannot run inside the browser: the processing needs a real machine. The file is uploaded, processed, and deleted automatically within an hour. Nobody opens it, it does not end up in an archive, and it is never used to train anything.
Do you use it for anything else?
No. The file does the job you asked for and then it is gone: we do not link it to you, we do not resell it, we do not pass it to third parties and we do not train any model on it. Most other Binatomy tools upload nothing at all and work only in your browser; this is one of the few that cannot.
Do you profile me? Are you GDPR compliant?
We do not profile you: there is no account to create, we never ask for your email to use a tool, and we keep no profile of what you do. We are an Italian company and we work under the GDPR and the other European rules, with the privacy notice and the consent request in plain sight. One thing we say in full rather than hiding it behind a slogan: the ads on the page are Google's, and Google may use cookies to personalise them. You decide from the consent banner: if you say no the ads stay, but they are not personalised, and the tool works exactly the same.
If it is free, how do you make money?
From the ads on the page, and that is all. We do not sell your data, there is no hidden paid plan, there is no limit that eventually asks for your card, and you do not have to sign up. The ads pay for the servers and for the time we spend writing the tools: that is how we can keep them open to everyone.