Every answer here stands on its own. If yours is missing, ask us and a person will reply within one business day.
Yes. The app makes no network call of its own accord. The only request it ever makes is downloading a speech model, once, from Hugging Face, when you choose one. After that the model is on your disk and transcription never contacts a server.
No. EddyLoop is an open mic recorder. You arm it once and it transcribes in the background until you pause or disarm it.
Into one plain .txt file per recording session, named for the time it started, in a folder you pick. Nothing is stored in a database and nothing is encrypted, so any text tool can read them.
It does less on purpose. No voice commands, no formatting engine, no upload. It listens and it writes files.
Yes. Install it on as many machines as you like. EddyLoop is free, there is no limit on machines, no key to paste and no account, so a new computer is just another install.
No. Audio is transcribed in memory and discarded. The only artifact is the text log.
The transcription path sends nothing, and there is no telemetry. The only request the app ever makes is downloading a speech model from Hugging Face, once, when you choose one.
Windows only for now, on 64 bit Windows 10 and 11. Other platforms are not ready, and nothing is listed for download until it is real.
A few CPU cores or any recent GPU. On a 2020 laptop the medium model transcribes faster than speech, which is the only benchmark that matters for background capture.
First check the tray icon. If it is not blue, the microphone is not live. Then check the Windows microphone permission, under Settings, Privacy and security, Microphone, and make sure desktop apps are allowed to use it.
