System audio (Mac)

Listen saves a transcript of audio playing on your Mac, such as a meeting or video. It captures system output, not microphone dictation, and writes to a file rather than typing into an app.

This task needs a separate model and permission. First check Mac dictation or terminal dictation, depending on how you installed Aria.

Model

The default Whisper model cannot run Listen. Use the Moonshine Base model below for English audio. Setup does not download this model for you.

1. Download the model’s three files:

   mkdir -p ~/models/moonshine/base
   cd ~/models/moonshine/base
   base=https://huggingface.co/onnx-community/moonshine-base-ONNX/resolve/b1e9b6aae3c3c7298f10c3798393fdf38e8fbbad
   curl -fLO "$base/onnx/encoder_model.onnx"
   curl -fLO "$base/onnx/decoder_model_merged.onnx"
   curl -fLO "$base/tokenizer.json"
   

2. Add this section to ~/.aria/config.yaml, or edit its existing listen section:

listen:
  backend: moonshine
  model: ~/models/moonshine/base
  transcripts_dir: ~/.aria/transcripts

Check it with aria config show. The next aria listen start reads it; no restart is needed. Keep Aria’s background service running.

Record

You need two terminals: one to show the transcript and one to stop recording.

1. Start the audio you want to transcribe, then run:

   aria listen start \
     --follow
   

2. Allow System Audio Recording if macOS asks. The terminal prints listening -> and an output path when the request is accepted. Confirm that recognized text appears as the audio plays.

3. When finished, stop capture in a second terminal:

   aria listen stop
   aria listen status
   

4. Check that status says not listening, then open the file at the path printed when the session started.

Ctrl-C stops the terminal display, not the recording. Always use aria listen stop to end capture. Use aria listen follow to show live text again during a session.

Transcript files

By default, files are saved under ~/.aria/transcripts. To choose another path:

aria listen start \
  --output "$PWD/meeting.txt"

If the file exists, Listen appends to it. This command starts a session; do not run it while another session is recording.

These files have no history expiry. Turning off dictation history does not stop Listen from saving them, and clearing history does not delete them. They do not get history’s private-file protections, so delete them yourself when you no longer need them.

Voice profiles can give speakers names. For permission or model failures, see Troubleshooting.