Tidyware

MCP server · App Intents · CLI

LocalVoice
pour les agents IA

Chaque fonctionnalité peut être appelée par un assistant IA. Tout s’exécute localement sur le Mac — l’IA envoie une requête, LocalVoice fait le travail, et LocalVoice n’envoie rien en ligne.

Connexion en un clic

03

Claude Desktop / Cursor

Ouvrez LocalVoice → Réglages → IA → Connecter. Redémarrez l’app d’IA.

Claude Code

Réglages → IA → Copier la commande, puis collez-la dans Terminal.

Siri et Raccourcis

Les actions apparaissent dans l’app Raccourcis, sous LocalVoice.

Configuration MCP manuelle :

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

Outils

10

Les noms et descriptions des outils sont affichés en anglais — exactement ce que reçoit votre assistant IA.

OutilRôleModifie des fichiers ?
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.Oui
job_statusProgress and results of a background transcription job (job_id from transcribe, or "latest"). Read-only.Non
cancel_jobStop a background transcription job (job_id from transcribe, or "latest"). Files already finished are kept.Oui
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.Non
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).Oui
list_voicesList the Mac's installed speech voices, best quality first, optionally for one language (e.g. "en", "vi"). Read-only.Non
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.Non
list_transcriptsList saved transcripts, newest first. Read-only.Non
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.Non
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.Oui

Exemples de requêtes

05

Ligne de commande

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