Tidyware

MCP server · App Intents · CLI

LocalVoice
para agentes de IA

Un asistente de IA puede usar cada función. Todo se ejecuta localmente en el Mac: la IA envía una solicitud, LocalVoice hace el trabajo y LocalVoice no sube nada.

Conecta con un clic

03

Claude Desktop / Cursor

Abre LocalVoice → Ajustes → IA → Conectar. Reinicia la app de IA.

Claude Code

Ajustes → IA → Copiar comando y luego pégalo en Terminal.

Siri y Atajos

Las acciones aparecen en la app Atajos, en LocalVoice.

Configuración MCP manual:

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

Herramientas

10

Los nombres y descripciones de las herramientas se muestran en inglés: exactamente lo que recibe tu asistente de IA.

HerramientaQué hace¿Modifica archivos?
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.Sí
job_statusProgress and results of a background transcription job (job_id from transcribe, or "latest"). Read-only.No
cancel_jobStop a background transcription job (job_id from transcribe, or "latest"). Files already finished are kept.Sí
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.No
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).Sí
list_voicesList the Mac's installed speech voices, best quality first, optionally for one language (e.g. "en", "vi"). Read-only.No
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.No
list_transcriptsList saved transcripts, newest first. Read-only.No
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.No
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.Sí

Ejemplos de solicitudes

05

Línea de comandos

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