local-first meeting scribe · macOS

Your meetings, transcribed.
Never uploaded.

Every meeting note-taker sends a bot into your call and your audio to their cloud. MeetingScribe does neither — your computer was already in the meeting, so it records at the OS audio layer, transcribes on the Apple Neural Engine in about 90 seconds, and keeps everything as plain files on your Mac.

free · open source · no account · no API keys · works with Zoom, Meet, Teams — anything that makes sound
MeetingScribe app showing a transcribed meeting: speaker chips with talk-time bars, a searchable transcript with timestamps, and an audio waveform transport bar.
a real recording — who said what, talk-time stats, click any line to replay that moment
  the difference

No bot joins your call. Nothing leaves your laptop.

Otter, Fireflies, Fathom — they all get audio the same way: a bot participant in your meeting, or a platform integration, plus your conversation uploaded to their servers. MeetingScribe taps a different layer entirely: the Mac's own audio system. That one architectural choice is where everything else falls out of — it works with any app that makes sound, nobody sees a recorder join, and the audio physically cannot leave the machine because no part of the pipeline needs a network.

~90s
to transcribe a 45-min call
60×
faster than realtime · neural engine
0
bytes uploaded · bots joined
$0
no subscription · no api keys
  how it works

Two tracks. That's the whole trick.

When you hit record, MeetingScribe builds a virtual audio device on the fly and splits the meeting into two synchronized recordings — and keeping them separate is what makes the transcript trustworthy.

mic.wav

Your microphone

Anything on this track is physically guaranteed to be you. No voice-matching guesswork — cloud tools record one mixed stream and have to infer which voice is theirs.

labelled You with certainty
system.wav

Everyone else

A clean copy of what comes out of your speakers, captured through a virtual loopback device — while you keep hearing everything normally. Routing happens automatically.

split into Speaker 1, 2, … by voice
1

Transcribe on the Neural Engine

Apple's on-device speech engine — the same one behind Notes and Voice Memos — chews through both tracks at roughly 60× realtime with word-level timestamps, using about two seconds of CPU. Your laptop stays cold and silent.

macOS 26+ · older Macs fall back to Whisper on the GPU, then CPU
2

Cancel the echo

No headphones? The other side's voice leaks from your speakers into your mic and gets transcribed twice. Because the system track is a perfect reference copy, the duplicates are detected and removed — single-stream tools have nothing to check against.

cross-track word matching · time-windowed
3

Fingerprint the voices

Each stretch of speech becomes a voice embedding; similar fingerprints cluster into speakers. The fingerprints are saved with the meeting, so if the split is ever wrong, picking the real speaker count re-clusters the whole transcript in a fifth of a second.

ECAPA-TDNN · on-device GPU · instant re-cluster
4

Name it from your calendar, polish it with Claude

Recordings name themselves after the calendar event you're in — read locally via EventKit, never a cloud API. And if you use Claude, an optional one-click tidy sends the transcript text (never audio) through your own subscription to merge leftovers and fix labels, with every edit validated locally.

EventKit · claude CLI · both optional
  your data

A meeting is a folder.

No database, no account, no export step, no vendor. Every meeting lives in a folder named after it, holding plain files you can open in anything. If MeetingScribe vanished tomorrow, every transcript you ever made still opens in TextEdit.

mic.wav
your side of the conversation
system.wav
everyone else, clean copy
transcript.md
readable forever, auto-updated
meeting.json
speakers, stats, timestamps
bot note-takersmeetingscribe
gets audio viaa bot joins your callthe Mac's own audio layer
your audiouploaded to their cloudnever leaves the laptop
works withsupported platforms onlyanything that makes sound — calls, webinars, in-person
"you" in the transcriptguessed by voice matchphysically certain — separate mic track
speedminutes in a cloud queue~90 s on-device
cost$10–30 / monthfree, open source
your transcriptstheir servers, their retentionplain files in your own folders

One honest note: a bot announces itself to everyone on the call. MeetingScribe doesn't — telling people you're recording, and following local consent law, is on you.

Five minutes to your first transcript.

Grab the zip above or clone the repo. One setup script installs everything — including the free BlackHole audio driver that captures the other side of your calls — and drops a proper MeetingScribe.app in Applications. From then on it's a normal Mac app.

 terminal
git clone https://github.com/sharique2004/MeetingScribe
cd MeetingScribe
bash setup.sh
# downloads the on-device models, installs BlackHole (asks first),
# and builds MeetingScribe.app into /Applications.
# done — launch it from Spotlight like any app. no terminal again.

Needs a Mac (Apple Silicon recommended; the Neural Engine path needs macOS 26+, older versions use Whisper locally instead). Windows works too via the same dual-track trick on WASAPI. Transcription quality is best with headphones. First run downloads the speech models once; after that it's fully offline.