If you're building or extending Type4Me, this skill walks you through the full stack: compiling SherpaOnnx for local ASR, wiring up cloud providers like Volcengine or Deepgram, and implementing the SpeechRecognizer protocol to add your own engine. It covers the actual build scripts, model downloads, and the provider registration system. The source material is thorough with real Swift snippets for credential validation and audio buffering. Useful if you want offline voice input on macOS without telemetry, or if you need to understand how to bridge C APIs for local speech recognition. Most people will just download the release, but this is for when you need to fork it or plug in a custom ASR backend.
npx skills add https://github.com/aradotso/trending-skills --skill type4me-macos-voice-input