# type4me-macos-voice-input

Guides building and customizing Type4Me, a macOS voice input tool built in Swift. Useful for adding speech providers and managing local ASR models.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 861 installs · ★ 88
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/type4me-macos-voice-input/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/type4me-macos-voice-input

## What it 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.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill type4me-macos-voice-input -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/type4me-macos-voice-input/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/type4me-macos-voice-input/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill type4me-macos-voice-input -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/type4me-macos-voice-input/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill type4me-macos-voice-input -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/type4me-macos-voice-input/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/trending-skills type4me-macos-voice-input
```

2. **Manually: put the files in place**
- File: `.github/skills/type4me-macos-voice-input/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill type4me-macos-voice-input -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/trending-skills --path skills/type4me-macos-voice-input
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/type4me-macos-voice-input/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill type4me-macos-voice-input -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/type4me-macos-voice-input/SKILL.md

## When to use it
- 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
- 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

## Similar
- [voice-ai-development](https://affpapa.org/en/nevibecode/skills/sickn33-voice-ai-development.md) — skill · 959 installs
- [voice-agents](https://affpapa.org/en/nevibecode/skills/sickn33-voice-agents.md) — skill · 890 installs
- [reminders-for-macos](https://affpapa.org/en/nevibecode/plugins/reminders-for-macos.md) — plugin · ★ 10
- [macos-development](https://affpapa.org/en/nevibecode/skills/macos-development.md) — skill · 1600 installs
- [macos-spm-app-packaging](https://affpapa.org/en/nevibecode/skills/macos-spm-app-packaging.md) — skill · 1400 installs
- [axiom-macos](https://affpapa.org/en/nevibecode/skills/axiom-macos.md) — skill · 1300 installs

From the same set: [reason-machines/trending-skills](https://affpapa.org/en/nevibecode/by/reason-machines/trending-skills.md) — 199 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md