type4me-macos-voice-input — Claude Code skill: setup guide
Guides building and customizing Type4Me, a macOS voice input tool built in Swift. Useful for adding speech providers and managing local ASR models.
npx skills add reason-machines/trending-skills --skill type4me-macos-voice-input -a claude-codeWhat type4me-macos-voice-input does
This skill instructs your coding assistant on compiling and extending Type4Me, a native macOS dictation utility written in Swift. The application records audio through a global hotkey, transcribes it with SherpaOnnx or Deepgram, and injects the text into any active program. All credentials and transcripts remain strictly on disk without telemetry.
The assistant receives guidance on implementing the SpeechRecognizer and ASRProviderConfig protocols. This structure allows connecting alternative speech services, such as OpenAI Whisper, by defining custom credential fields and audio buffers.
Precompiled DMG releases omit the local Sherpa engine and run cloud providers only. Running speech recognition entirely offline requires compiling the repository from source using CMake and Xcode tools.
What it helps with
- implement custom speech recognition providers in Swift
- compile and package Type4Me from source via build scripts
- configure local SherpaOnnx streaming models inside macOS folders
- resolve audio capture and text injection issues in active windows
Example prompts for the agent
- Build Type4Me from source with local SherpaOnnx engine support
- Add an OpenAI Whisper provider using the SpeechRecognizer protocol in Type4Me
- Set up offline Zipformer model files in Type4Me Application Support
How to install type4me-macos-voice-input
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill type4me-macos-voice-input -a claude-code2Manually: put the files in place
~/.claude/skills/type4me-macos-voice-input/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/type4me-macos-voice-input/
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill type4me-macos-voice-input -a codex2Manually: put the files in place
.agents/skills/type4me-macos-voice-input/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill type4me-macos-voice-input -a cursor2Manually: put the files in place
.cursor/skills/type4me-macos-voice-input/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/trending-skills type4me-macos-voice-input2Manually: put the files in place
.github/skills/type4me-macos-voice-input/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill type4me-macos-voice-input -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/trending-skills --path skills/type4me-macos-voice-inputManually: put the files in place
.devin/skills/type4me-macos-voice-input/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill type4me-macos-voice-input -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about type4me-macos-voice-input
How to install type4me-macos-voice-input in Claude Code?
Run npx skills add reason-machines/trending-skills --skill type4me-macos-voice-input -a claude-code.
What does type4me-macos-voice-input do?
It guides your agent on compiling the Type4Me Swift codebase, connecting local speech models, and writing new ASR provider modules.
Does the pre-built DMG package support local speech models?
Pre-built DMG releases only connect to cloud speech APIs. To run local SherpaOnnx transcription, you must compile the project from source with cmake installed.