MCP server · App Intents · CLI
Jede Funktion lässt sich von einem KI-Assistenten aufrufen. Alles läuft lokal auf dem Mac – die KI schickt eine Anfrage, LocalVoice erledigt die Arbeit, und LocalVoice lädt nichts hoch.
Öffne LocalVoice → Einstellungen → KI → Verbinden. Starte die KI-App neu.
Einstellungen → KI → Befehl kopieren, dann im Terminal einfügen.
Die Aktionen erscheinen in der Kurzbefehle-App unter LocalVoice.
MCP manuell konfigurieren:
{
"mcpServers": {
"localvoice": {
"command": "/Applications/LocalVoice.app/Contents/MacOS/localvoice",
"args": ["mcp"]
}
}
}
Toolnamen und Beschreibungen stehen auf Englisch – genau so, wie dein KI-Assistent sie erhält.
| Tool | Funktion | Ändert Dateien? |
|---|---|---|
transcribe | Transcribe 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. | Ja |
job_status | Progress and results of a background transcription job (job_id from transcribe, or "latest"). Read-only. | Nein |
cancel_job | Stop a background transcription job (job_id from transcribe, or "latest"). Files already finished are kept. | Ja |
list_media | List 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. | Nein |
read_aloud | Turn 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). | Ja |
list_voices | List the Mac's installed speech voices, best quality first, optionally for one language (e.g. "en", "vi"). Read-only. | Nein |
search_transcripts | Find where a word or phrase was said across saved transcripts (case- and accent-insensitive). Returns transcript, timestamp and the surrounding sentences. Read-only. | Nein |
list_transcripts | List saved transcripts, newest first. Read-only. | Nein |
get_transcript | Get 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. | Nein |
download_model | Download 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. | Ja |
localvoice list localvoice transcribe --path ~/Downloads/meeting.m4a --formats srt