Tidyware

MCP server · App Intents · CLI

AI 에이전트를 위한
LocalVoice

모든 기능을 AI 어시스턴트가 호출할 수 있어요. 모든 작업은 Mac에서 로컬로 실행돼요 — AI가 요청을 보내면 LocalVoice이(가) 작업을 처리하고, LocalVoice은(는) 아무것도 업로드하지 않아요.

클릭 한 번으로 연결

03

Claude Desktop / Cursor

LocalVoice 열기 → 설정 → AI → 연결. 그런 다음 AI 앱을 다시 시작하세요.

Claude Code

설정 → AI → 명령어 복사 후 터미널에 붙여 넣으세요.

Siri 및 단축어

단축어 앱의 LocalVoice 항목에 동작이 표시돼요.

MCP 수동 설정:

{
  "mcpServers": {
    "localvoice": {
      "command": "/Applications/LocalVoice.app/Contents/MacOS/localvoice",
      "args": ["mcp"]
    }
  }
}

도구

10

도구 이름과 설명은 영어로 표시돼요 — AI 어시스턴트가 실제로 받는 내용 그대로예요.

도구기능파일 변경?
transcribeTranscribe an audio or video file — or every file in a folder — on this Mac. Files over ~90 s and folders run as a background job (returns job_id; poll job_status). Always saves a Markdown transcript to the LocalVoice library; 'formats' also writes txt/srt/vtt/md files next to the source (or to output_dir). Use srt or vtt for subtitles. Returns the transcript text (truncated if long) and file paths. Long files can take minutes.예
job_statusProgress and results of a background transcription job (job_id from transcribe, or "latest"). Read-only.아니요
cancel_jobStop a background transcription job (job_id from transcribe, or "latest"). Files already finished are kept.예
list_mediaList audio/video files in a folder (default ~/Downloads), optionally only those added since a date. Use before transcribe when the user describes a recording by date ("yesterday's meeting"). Read-only.아니요
read_aloudTurn text, a text/Markdown file, or a PDF into a spoken M4A audio file using the Mac's built-in voices (offline). Give 'path' or 'text'. The voice is chosen automatically from the text's language unless 'voice' is set (see list_voices).예
list_voicesList the Mac's installed speech voices, best quality first, optionally for one language (e.g. "en", "vi"). Read-only.아니요
search_transcriptsFind where a word or phrase was said across saved transcripts (case- and accent-insensitive). Returns transcript, timestamp and the surrounding sentences. Read-only.아니요
list_transcriptsList saved transcripts, newest first. Read-only.아니요
get_transcriptGet the full text of a saved transcript ("latest" for the newest, an id, or part of the title), with timestamps. Use this to summarise or quote a recording. Read-only.아니요
download_modelDownload a Whisper speech model (needed for Vietnamese and other languages Apple's engine lacks). base ~150 MB (fast), small ~490 MB, turbo ~550 MB (best). Downloads from Hugging Face once; transcription itself stays offline. Ask the user before downloading.예

요청 예시

05

명령줄

CLI
localvoice list
localvoice transcribe --path ~/Downloads/meeting.m4a --formats srt