Offline meeting transcription for Mac
Loofah records and transcribes meetings on your Mac without an internet connection once you have downloaded a speech model. Recording and transcription are free, with no account or monthly allowance. For a complete offline workflow, use a local language model for optional summaries too.
New to Loofah? Start with installation and your first recording.
What works offline
Section titled “What works offline”- Create and edit notes.
- Record and play meeting audio.
- Export existing memos, summaries, and transcripts.
- Transcribe with a downloaded on-device model.
- Separate speakers in imported and after-recording transcripts, once the speaker-detection model has been downloaded.
- Import and transcribe recordings from the terminal with
loof importandloof transcribe, when the selected model is an on-device Soniqo model. - Generate summaries through a local LM Studio or Ollama server.
A remote Intelligence provider still needs internet access.
Prepare transcription
Section titled “Prepare transcription”- Open Settings → Transcription.
- Download a model.
- Select it under Model being used.
- Make a short test recording before you disconnect.
Do the download in advance. The model files are not bundled with the app.
The speaker-detection model downloads automatically in the background the first time it is needed. Before you disconnect, check that Settings → Transcription → Speaker detection shows Ready.
Prepare local summaries
Section titled “Prepare local summaries”Set up LM Studio or Ollama, download a language model, and select it in Settings → Intelligence. The local server needs to be running, but it does not need an internet connection once the model is available.
If you want a meeting to remain fully local, check that the active Intelligence model belongs to LM Studio or Ollama. Transcription is already local.
Live text and speaker detection
Section titled “Live text and speaker detection”Live transcription is available for supported English meetings. Other supported languages use transcription after recording. Speaker detection runs on imported and after-recording transcripts; live transcription does not separate speakers. Check the supported language list before choosing a model.
Bring existing recordings
Section titled “Bring existing recordings”Import audio files to transcribe recordings from another tool on-device. Your notes, summaries, and transcripts remain accessible in the local vault. If you later enable a hosted summary provider or connect an agent, review what can leave your Mac.
