Agent skill · software engineering · aradotso
type4me-macos-voice-input
MacOS voice input tool with local/cloud ASR engines, LLM text optimization, and fully local storage built in Swift
Why this skill is useful
Adds executable scripts for building and deploying the Type4Me tool, along with specific ASR engine integration patterns that are not widely known.
What it needs
Requires cmake installed locally. About 6k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
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. Architecture Overview Installation Prerequisites Build & Deploy from Source Download Pre-built App Download Type4Me-v1.2.3.dmg from releases (cloud ASR only, no local engine): If macOS blocks the app: Download Local ASR Models Expected structure for Paraformer model: Key Protocols SpeechRecognizer Protocol Every ASR client must implement this protocol: ASRProviderConfig Protocol Each vendor's credential definition: Adding a New ASR Provider Step 1: Create Provider Config Create Type4Me/ASR/Providers/OpenAIWhisperProvider.swift: Step 2: Implement the ASR Client Create Type4Me/ASR/OpenAIWhisperASRClient.swift: Step 3: Register the Provider In Type4Me/ASR/ASRProviderRegistry.swift, add to the all array: Credentials Storage Credentials are stored at ~/Library/Application Support/Type4Me/credentials.json with permissions 0600. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/type4me-macos-voice-input