Never lose what was said

Earkeep records everything said, transcribes it locally, and lets you mark which stretch of the day was a meeting after it happened.

No bot · No cloud · No record button

14-day full trial, no account required.

Four ways Earkeep is different

A day of capture: an activity strip from 08:00 to 18:00 under a header reading "Recording since 07:12 · no button pressed", and below it the live transcript line listening to mic and system audio, with a Pause control at its end A day of capture: an activity strip from 08:00 to 18:00 under a header reading "Recording since 07:12 · no button pressed", and below it the live transcript line listening to mic and system audio, with a Pause control at its end

Always-on, zero interaction

A quick huddle at someone's desk turns out to matter, and it was already being transcribed. Mark the span afterwards.

Read how always-on works →

Everything inside one machine: microphone and system audio into memory, transcribed by Whisper on this device, out to a .jsonl file – with the network outside the boundary and nothing going to it Everything inside one machine: microphone and system audio into memory, transcribed by Whisper on this device, out to a .jsonl file – with the network outside the boundary and nothing going to it

Audio never leaves your computer

Mic and system audio stay in memory, never on disk, and are transcribed on-device with Whisper or Parakeet. No upload, no account, and nothing from your meetings leaves the device.

See how private-by-design works →

A ~/meetings folder of four .jsonl day files beside a terminal counting their lines, listing the day's meeting titles and pulling one sentence out of a file with grep A ~/meetings folder of four .jsonl day files beside a terminal counting their lines, listing the day's meeting titles and pulling one sentence out of a file with grep

Plain files you own, on your own disk

Open them in any editor, back them up, hand them to any tool. No database, no proprietary format, nothing to export.

Read the full plain-files story →

A meeting's own panel with an agent session on it: the question asked, the transcript it read, the decisions and open questions it answered, and a composer set to Codex A meeting's own panel with an agent session on it: the question asked, the transcript it read, the decisions and open questions it answered, and a composer set to Codex

Your agents, right where your meetings are

Run the agents you already use inside Earkeep against your meetings: anything that speaks ACP connects by picking it. An MCP server opens the same meetings to outside tools.

See agents and MCP in Earkeep →

14-day full trial, no account required.

Pricing: one payment, no subscription

€39

once, for one device, not a subscription.

No tiers, no per-seat billing, no recurring bill. Try it free for 14 days, no account required. See full pricing →

Frequently asked questions

How does the 14-day trial work?

Full functionality for 14 days, no email or account required.

Does audio ever leave my computer?

No. Mic and system audio are processed in memory and transcribed on-device. Nothing is uploaded to a server or an external API.

Does Earkeep support my language?

Whisper covers 99+ languages; Parakeet-TDT v3 covers 25 European ones, faster. Full language list →

How does licensing work across devices?

One device at a time: deactivate on the old one, activate on the new. Email [email protected] for help.

Does Earkeep work offline?

Yes. Everything runs on-device, and the license check has an offline grace period.

How big is the model download?

75 MB to 3.1 GB, once, depending on your device and the fidelity you want. Model details →

What do I need to run it?

macOS 13 or later, or Windows 10 or later (64-bit). All builds →

Do I have to let it record all day?

No. A calendar-driven mode opens the microphone only around the events on your agenda, with Record now for anything unbooked. How it works →

Does always-on capture drain my battery or slow down my device?

Transcription runs only when someone is speaking, so it costs no more than a start-and-stop transcriber for the same speech.

What is the refund policy?

Email [email protected] within 14 days of purchase for a full refund, no questions asked.

Stop losing what was said

14-day full trial, no account required.