The optional RNNoise speech-cleanup model is not part of the standard SYLIRI Sound package.
Without it, AI speech cleanup stays hidden and all other sound processing works normally.

To build a model-enabled package from the complete project, run:

  npm run neural:prepare
  npm run verify
  npm run package:neural

The build-time step downloads an exactly pinned third-party package and verifies SHA-256.
Nothing is downloaded while you watch videos. Licences: see NOTICE.txt in this folder
after preparation, and ../NOTICE.txt.
