Local meeting transcription and AI summaries

Loofah transcribes meetings on your Mac. For AI meeting summaries, choose a local model through Ollama or LM Studio, or supply an API key for a hosted provider. Loofah does not charge for either workflow; hosted providers may charge for their API usage.

Loofah has two separate model settings:

• Transcription turns audio into text on your Mac.
• Intelligence writes summaries and note titles. It can use a local model or a provider you configure with your own API key.

Open Settings → Transcription or Settings → Intelligence to change the active model.

Transcription

Transcription is on-device only. Download a model from Settings → Transcription, wait for it to finish, then select it under Model being used.

A model marked Live can show text during a meeting. The streaming model supports English. If your language selection is not supported live, the app falls back to transcription after the recording. Models marked After recording always wait until you stop.

Configure the languages spoken in your meetings under Settings → App → Language & Region. See Languages for setup instructions and the supported language list for each bundled model.

A downloaded on-device Soniqo model also powers transcription from the terminal: loof transcribe MEETING_ID uses it without opening the app. The CLI never downloads models itself, so complete the download here first. See the CLI reference.

Speaker detection

Recordings that are transcribed after the fact, including imported files and models marked After recording, also get automatic speaker detection: the transcript separates who said what, and you can name each speaker by clicking their label. Live transcription does not separate speakers.

Speaker detection runs on your Mac and is included with on-device transcription. Its small model downloads automatically the first time it is needed; the Speaker detection row in Settings → Transcription shows its status and offers a Retry if the download failed.

Intelligence

You do not need an Intelligence model to record, write notes, or transcribe. Configure one only if you want generated summaries and titles.

For a hosted provider, open Configure Providers, add the API key, then select one of that provider’s models. The API key is stored in the macOS login Keychain.

You can also run summaries locally with LM Studio or Ollama.

LM Studio

1. Install LM Studio and download a model.
2. Start its local server on port 1234 and enable CORS.
3. Open Settings → Intelligence → Configure Providers → LM Studio.
4. Select the LM Studio model under Model being used.

Ollama

1. Install Ollama.

2. Start it and download a model:

   ollama serve
   ollama pull llama3.2

3. Open Settings → Intelligence → Configure Providers → Ollama.

4. Select the Ollama model under Model being used.

Check your first local summary

1. Keep your local server running and confirm its model is selected under Settings → Intelligence.
2. Record a short meeting or import a recording with enough conversation to summarize.
3. Review the generated summary against the transcript. Model quality, response time, and memory use depend on your Mac and the model you choose.
4. Edit your summary prompt and regenerate if you want a different structure.

Downloading the speech model does not install a summary model. If you see a transcript but no summary, check Intelligence separately. For use without internet, follow the offline preparation guide.

What leaves your Mac

Recording and transcription stay local. A local Intelligence provider also keeps summary processing on your Mac. If you select a remote Intelligence provider, the app sends the prompt and meeting context needed for that request to that provider.

See Data, privacy, and retention for more detail.