One conversation,
every meeting.
Private, on-device transcription with an AI that knows what was said, who said it, and exactly when — and cites every line.
macOS 15+ · Free during beta · No account needed to start
Your meetings never leave your Mac.
Transcription runs locally. Audio, transcripts, and voice profiles stay on your machine — even the AI runs against only what it's allowed to see.
Local-first, cloud-optional.
FluidAudio's neural transcription runs natively on Apple silicon. No upload, no third-party processing, no audio leaving your laptop unless you explicitly enable cloud features.
- Whisper-class accuracy on-device
- Speaker diarization per microphone channel
- Voice profiles stored in the macOS keychain
- Disable network entirely and the app keeps working
Every AI answer is citable.
Ask anything across all your meetings. Each claim links back to the exact transcript timestamp — click and you're playing the original audio.
- No cite, no claim — answers without sources are flagged
- One-click to the exact moment in the audio
- Scope conversations to a meeting, person, or date range
Built for conversations you can't risk leaking.
Voice prints are biometric data. We treat them that way: encrypted at rest, local by default, deletable in one click, with a signed consent receipt for every action.
Stop taking notes.
Download kiromi for macOS. Free during beta. No account needed.
Or join the list — we'll email when there's news worth your time.