Whisper MCP-Server | PlugMCP
Zum Inhalt springen Verzeichnis Produkt Ressourcen Pricing Vom Herausgeber
Dokumentation MCP server for local audio transcription using Whisper
Beliebiges Tool in beliebigen Agenten. MCP-Verzeichnis für Leute, die keine Server schreiben.
Produkt
Verzeichnis
Entwickler
Unternehmen
2026-10-28
Features
Local transcription - All processing happens on your machine
Multiple models - Choose from tiny, base, small, medium, or large models
Various formats - Supports wav, mp3, m4a, and other audio formats
Timestamps - Get transcriptions with or without timestamps
Requirements
macOS (tested on Apple Silicon)
Node.js 18+
whisper-cpp: brew install whisper-cpp
ffmpeg: brew install ffmpeg
Installation npm install -g whisper-mcp
Configuration
Claude Desktop Add to your Claude Desktop config file:
macOS : ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"whisper-mcp": {
"command": "npx",
"args": ["-y", "whisper-mcp"]
}
}
}
After editing, restart Claude Desktop.
Claude Code (CLI) For Claude Code, add to your project's .mcp.json file:
{
"mcpServers": {
"whisper-mcp": {
"command": "npx",
"args": ["-y", "whisper-mcp"]
}
}
}
Or for user-wide configuration, add to ~/.claude/settings.json:
{
"mcpServers": {
"whisper-mcp": {
"command": "npx",
"args": ["-y", "whisper-mcp"]
}
}
}
Tip : Use /mcp in Claude Code to verify the server is connected.
Local Development Setup If running from source instead of npm:
{
"mcpServers": {
"whisper-mcp": {
"command": "node",
"args": ["/path/to/whisper-mcp/dist/index.js"]
}
}
}
With Apple Voice Memos MCP For a complete voice memo workflow, use alongside apple-voice-memo-mcp:
{
"mcpServers": {
"apple-voice-memo-mcp": {
"command": "npx",
"args": ["-y", "apple-voice-memo-mcp"]
},
"whisper-mcp": {
"command": "npx",
"args": ["-y", "whisper-mcp"]
}
}
}
MCP Tools
transcribe_audioTranscribe an audio file using Whisper.
file_path (required): Absolute path to the audio file
model (optional): Model to use (tiny.en, base.en, small.en, medium.en, large). Default: base.en
language (optional): Language code. Default: en
output_format (optional): text, timestamps, or json. Default: text
{
"file_path": "/path/to/audio.m4a",
"model": "medium.en",
"output_format": "timestamps"
}
list_whisper_modelsList available Whisper models and their download status.
{
"models": [
{
"name": "base.en",
"size": "142 MB",
"downloaded": true,
"path": "/Users/you/.whisper/ggml-base.en.bin"
}
]
}
download_whisper_modelDownload a Whisper model for local use.
model (required): Model to download (tiny.en, base.en, small.en, medium.en, large)
Models Models are stored in ~/.whisper/.
Workflow Example
List your voice memos: list_voice_memos
Get audio path: get_audio with memo ID
Transcribe: transcribe_audio with the file path
Save to your vault
Development # Clone and install
git clone https://github.com/jwulff/whisper-mcp.git
cd whisper-mcp
npm install
# Build
npm run build
# Test with MCP inspector
npm run inspector
License
Verzeichnis-Score 10/100 Gelistet 10 von 10
In der offiziellen MCP Registry 0 von 18
Vom Maintainer beansprucht 0 von 8
Antwortet mit einer Tool-Liste 0 von 12
GitHub-Sterne 4 von 16
Wöchentliche Downloads 0 von 10
FunASR Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving. FunASR Transcribe local audio with FunASR and SenseVoice using private, on-device inference. Ffmpeg Skill Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No clou Vexa Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS. ToolSnap MCP Connect directly: https://mcp.toolsnap.app/mcp (Streamable HTTP, free tools need no account). The run.tools URL on this page stopped working when Smithery's proxy shut down on 2026-10-31.
Determinist MiniMax Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs. Voicemode Natural voice conversations for AI assistants - STT/TTS via MCP Voicemode Natural voice conversations with Claude Code Xiaozhi Esp32 Server Java 小智ESP32的Java企业级管理平台,提供设备监控、音色定制、角色切换和对话记录管理的前后端及服务端一体化解决方案 Claude Video Vision Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis Jarvis Assistant Vocal Assistant vocal local en francais : Claude ou Ollama (offline), domotique Hue, OBS, agenda, navigateur, appels Twilio, serveur MCP. Python. Orkas VideoStudio Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file. MCP-Server für Speech Die besten MCP-Server für Speech
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
Wie installiere ich Whisper? Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
Benötigt Whisper einen API-Schlüssel? In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
Welchen Transport verwendet Whisper? Whisper läuft lokal über stdio.
Wann wurde Whisper zuletzt geprüft? Zuletzt geprüft: 2026-10-28. MCP server for local audio transcription using Whisper
Tools haben Beschreibungen 0 von 6
Seit drei Tagen nicht gesehen -8