Type4me Macos Voice Input

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.

skills.sh installs: 816
GitHub stars: 61
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add aradotso/trending-skills --skill type4me-macos-voice-input --agent claude-code

Installs into .claude/skills of the current project.

Files

Type4Me macOS Voice Input

Skill by ara.so — Daily 2026 Skills collection.

Type4Me is a macOS voice input tool that captures audio via global hotkey, transcribes it using local (SherpaOnnx/Paraformer/Zipformer) or cloud (Volcengine/Deepgram) ASR engines, optionally post-processes text via LLM, and injects the result into any app. All credentials and history are stored locally — no telemetry, no cloud sync.