메뉴
Native macOS menu bar app for live voice-to-text with auto-type using WhisperKit on Apple Silicon
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | whisper-voice |
| description | Native macOS menu bar app for live voice-to-text with auto-type using WhisperKit on Apple Silicon |
| allowed-tools | ["Bash","Read","Write","Edit"] |
Build and run a native macOS menu bar app that captures live microphone audio, transcribes it offline using WhisperKit (on Apple Silicon), and auto-types the text wherever the cursor is.
| Name | Type | Required | Description |
|---|---|---|---|
| model_size | string | No | Whisper model: tiny, base (default), small |
| language | string | No | "en" (default) or "hi" for Hindi mode |
| chunk_duration | float | No | Seconds per audio chunk (default: 3.0) |
cd YourProject/WhisperApp
swift build
swift run WhisperApp
# Or open in Xcode: open Package.swift → Cmd+R
| Name | Type | Description |
|---|---|---|
| transcribed_text | string | Live transcribed text typed at cursor |
| history | array | Last 50 transcription entries in menu bar |
| Name | Type | Required | Description |
|---|---|---|---|
| model_size | string | No | tiny / base / small |
| language | string | No | en / hi |
| chunk_duration | float | No | 2.0 - 8.0 seconds |
| silence_threshold | float | No | 0.002 - 0.05 |
| Name | Type | Description |
|---|---|---|
| transcription | string | Live text output |
| auto_typed | boolean | Whether text was injected at cursor |
| Name | Source |
|---|---|
| None | Fully offline, no API keys |
video-edit (add transcription captions), send-telegram (send transcriptions to phone)
Free — runs entirely on-device. Model download is one-time (~140MB for base).
DEPRECATED. Koyeb removed its free tier. Use github-actions-deploy or n8n-workflow-deploy instead.
Deploy any automation to run on schedule using GitHub Actions. Use when user asks to deploy with cron, schedule an automation, run code automatically, or deploy for free.
Deploy serverless Python functions and AI workloads to Modal. Use when user needs GPU, AI inference, serverless Python, or scheduled AI tasks.
Deploy automations as n8n workflows — visual, webhook-driven, multi-step. Use when user asks to create a workflow, connect services visually, or deploy to n8n.
Deploy frontends, dashboards, webhooks, and API endpoints to Vercel. Use when user needs a web UI, dashboard, webhook receiver, or Next.js/React frontend.
Add 6-layer guardrail pipeline to any AI agent — RBAC, injection defense, output filtering, monitoring