Offline meeting notes — record and transcribe on-device

Daisy makes offline meeting notes: the recording, the transcript, the speaker labels, and the search all run on your own device, and the audio never leaves it. No bot joins your call. The AI layer can stay local too: on iPhone and iPad, Daisy's on-device AI writes summaries on the device, and on a computer you can point Daisy at a model on your own hardware.

What runs on your machine

These steps are fully on-device. Once the speech model is on your device, you can record and transcribe with the wifi off:

• Recording. On a computer, Daisy captures system and mic audio straight to disk; on iPhone and iPad it records the microphone. No calendar, no meeting link, no bot in the room — you press record. Audio is saved in open formats.
• Transcription. Speech-to-text runs on-device. You get a timestamped markdown transcript when the meeting ends.
• Speaker ID / diarization. Figuring out who spoke when is always on-device and always free. It never leaves your machine and never costs a credit.
• Keyword search. Once a transcript exists, searching across your notes runs locally.

That covers the whole core loop: capture, transcribe, separate speakers, find it later. None of it sends your audio or transcript anywhere.

What needs a model (and how to keep that local too)

There is exactly one thing that wants a language model: the higher-level stuff — summaries, Q&A over the transcript, and analysis. A raw transcript doesn't need a model; turning it into a summary does.

You choose how that runs, and most of the choices keep the AI local:

• Use on-device AI. Daisy comes with AI built in, so summaries and answers are written on the device, with no key. It needs recent hardware: iPhone 15 Pro or later, or a computer with a graphics card.
• Run a local LLM. Point Daisy at Ollama or LM Studio on your own hardware and summaries, Q&A, and analysis stay local. The transcript and the model both live on hardware you control, so the AI layer sends nothing out either.
• Bring a cloud key (BYOK). If you'd rather use OpenAI, Anthropic, or Groq, Daisy sends the meeting's text, never its audio, straight to that provider with your own key. That path uses the internet, because the model lives somewhere else.
• Use no LLM at all (desktop). Daisy hands you the transcript plus a ready-made, copy-paste prompt. Take it to whatever tool you like — or nothing at all.

On a computer, the built-in model or a local LLM keeps the AI layer local.

This is what "private by default, your choice to extend" means: the on-device core is the default, and the cloud is something you opt into deliberately, key in hand.

Your notes live on your disk

On a computer, everything Daisy produces is a plain file in a folder you chose. Audio is saved in open formats; transcripts and summaries are markdown. There's no proprietary database to export from and no server-side copy to delete. Back them up, grep them, drop them in your own vault, or check them into a repo — they're yours, in formats that will still open in a decade.

No bot in your call, no usage meter, and your recordings never reach us.

Works when you're offline

The core loop doesn't need a connection, so being offline is fine:

• On a plane. Record an interview or a working session at 35,000 feet with the wifi off, and walk off with a finished, searchable transcript.
• Spotty or no connection. Recording, transcription, speaker labels, and search keep working while you're disconnected; on-device AI, or a local LLM, keeps summaries working too.
• No-cloud-for-your-data policies. When sending audio or transcripts to a third party is off the table — compliance, contracts, classification — Daisy keeps that data on the device. (The AI stays local when you use on-device AI or a local model; a BYOK cloud key sends transcript text out by design.)

One license covers three devices, on Linux, Windows, and macOS (Apple Silicon), with a 30-day trial. Daisy for iPhone and iPad is on the App Store.