Can I run an AI notetaker on my own server?
Yes. A standard server can run the full pipeline: an automated browser joins the meeting, server-side capture records it, Flocci Speech Recognition transcribes the audio, and an LLM writes the report. Donna packages exactly this stack — Playwright, server-side capture, Flocci Speech Recognition, Flocci Intelligence, and your own database — as one privately hosted product.
What does the server actually need?
Less than you would guess: your own server with the server-side capture stack and Node.js. Donna’s setup script installs the stack, and standard server tooling keeps the processes alive. No GPU is required, because the heavy models are reached via API — Flocci Speech Recognition with your key, Flocci Intelligence for analysis with yours. The server’s jobs are attending, recording, compressing, and storing, which ordinary server hardware does comfortably.
Why not just use a free cloud notetaker?
Three structural reasons. Custody: cloud tools keep a copy of every meeting on their servers; your own server keeps the only copy. Cost shape: per-seat subscriptions scale with headcount, while one server attends for the whole team and API usage is metered in pennies per meeting-hour. Control: your retention policy is a command on your own disk, not a plan feature. The trade is that you administer a server — which for teams already running standard server tooling is a familiar Tuesday.
What does Donna add over DIY scripts?
The join choreography (lobby, admission, meeting-end detection), crash-safe capture, post-call compression, chunked transcription of long recordings, a two-pass analysis that goes far beyond summarization, a dashboard with live status and full report viewing, an upload path for past recordings, and your own database for persistence — the difference between a weekend proof-of-concept and a colleague you can rely on.
Related questions
Do I need a GPU to self-host meeting transcription?
Not with Donna’s architecture — Flocci Speech Recognition runs on your key, so your own server only records and orchestrates. If you require fully local inference, fully local speech models are possible but are a different cost and quality trade.
How much server do I need?
An ordinary server of the class teams already rent for web apps: enough disk for compressed recordings and enough CPU for compression after calls. There is no per-seat scaling — one server serves the whole team.
Is maintenance heavy?
It is a standard Node service running with standard server tooling: the same shape as any small production app. Updates are a git pull and a build; the database is a single secure database instance with migrations included.
Put Donna in your next meeting
Access is open — sign in with your Google account and she’s in your dashboard in minutes. Rolling out to a whole team, or want a hand with the server setup? We’re glad to help.