Managing Local AI

Manage local speech models, language models, embeddings, and the on-device runtimes used by RecapFox.

Step-by-Step Guide

  1. Open Settings → Models to inspect installed local runtimes.
  2. Choose the speech model that fits your hardware and transcription needs.
  3. Choose the local language-model profile used for summaries and question answering.
  4. Keep the bundled embedding model available for semantic meeting retrieval.
  5. Remove unused model files whenever you want to reclaim disk space.
Privacy Architecture: Meeting-content inference is designed to run locally. Model downloads and application updates are separate from sending meeting audio, transcripts, summaries, screenshots, or retrieval context to a hosted inference API.