VoiceMode MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

Local Whisper option — no cloud audio
Multiple TTS backends: OpenAI, ElevenLabs, local Coqui
Push-to-talk or voice-activated modes
Streams partial responses so you hear Claude thinking
Works in terminal alongside Claude Code CLI

Live-Demo

In der Praxis

voicemode-mcp.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "voicemode-mcp": {
      "command": "uvx",
      "args": [
        "voice-mode"
      ]
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "voicemode-mcp": {
      "command": "uvx",
      "args": [
        "voice-mode"
      ]
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "voicemode-mcp": {
      "command": "uvx",
      "args": [
        "voice-mode"
      ]
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "voicemode-mcp": {
      "command": "uvx",
      "args": [
        "voice-mode"
      ]
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "voicemode-mcp",
      "command": "uvx",
      "args": [
        "voice-mode"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "voicemode-mcp": {
      "command": {
        "path": "uvx",
        "args": [
          "voice-mode"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add voicemode-mcp -- uvx voice-mode

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: VoiceMode

Drive a Claude Code session hands-free while reading on another screen

👤 Devs who read docs or designs on one monitor while coding ⏱ ~30 min intermediate

Wann einsetzen: You're reading a design doc and want to dictate changes without alt-tabbing.

Voraussetzungen

Microphone + speakers — System audio configured — test with say "hello" or equivalent
Whisper model ready — voice-mode install-whisper downloads the local model

Ablauf

Start voice

Use voicemode. Listen for prompts and speak responses. Repeat after me: "ready"✓ Kopiert

→ TTS plays "ready"
Dictate a change

[spoken] Update src/auth.ts — use bcrypt instead of plain SHA256 for passwords.✓ Kopiert

→ Transcription correct; change applied; TTS confirms
Review

[spoken] Read me the diff.✓ Kopiert

→ TTS reads diff in chunks, pausable

Ergebnis: A working session where your hands never leave what they were doing.

Fallstricke

TTS talking over your prompts — Enable push-to-talk mode or a wake word

Kombinieren mit: filesystem

Code by voice for accessibility or RSI recovery

👤 Devs with RSI, low vision, or preferring speech input ⏱ ~60 min intermediate

Wann einsetzen: You can't type for a while and need to keep shipping.

Voraussetzungen

Tolerable ambient noise — Quiet room; headset mic beats laptop mic

Ablauf

Baseline

[spoken] Use voicemode. Read the latest git diff out loud, pausing between files.✓ Kopiert

→ Clear TTS read
Workflow

[spoken] Refactor the user model in src/models/user.ts. Move password hashing into a method. Show me the plan first.✓ Kopiert

→ Plan spoken; confirmation required before changes

Ergebnis: A full coding session without keyboard input.

Fallstricke

Code symbols mispronounced by TTS — Configure the TTS phoneme dictionary for common programming terms

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

voicemode-mcp + filesystem

Voice-dictated code changes land in the repo

I'll dictate changes; apply them in files after reading each back.✓ Kopiert

voicemode-mcp + github

Dictate a PR description after voice-reviewing the diff

Read me the staged changes, then open a PR with a description I'll dictate.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
start_listening	mode: "ptt"\|"vad"	Begin a voice session	free or OpenAI Whisper API
speak	text: str, voice?: str	Any time Claude wants to surface something audibly	TTS provider-dependent
transcribe_last	none	Fetch what the user just said	Whisper call
stop_listening	none	End voice session	free

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: Local: free. OpenAI Whisper: $0.006/min. ElevenLabs TTS: ~$0.30/1k chars.
Tokens pro Aufruf: Audio pipelines are not token-costed directly
Kosten in €: Free with local stack; metered with cloud providers
Tipp: Local Whisper + Coqui TTS is totally free but lower quality — start cloud, downgrade later

Sicherheit

Rechte, Secrets, Reichweite

Minimale Scopes: microphone speakers

Credential-Speicherung: TTS/STT API keys in env

Datenabfluss: Voice audio to TTS/STT provider if not local

Never use cloud STT in calls with confidential audio unless you trust the provider's retention policy

Fehlerbehebung

Häufige Fehler und Lösungen

Mic not detected

System audio permission — grant terminal/Claude Code mic access

Prüfen: `voice-mode test-mic` prints levels

TTS sounds robotic

Default is Coqui local — switch to OpenAI tts-1-hd via VOICE_MODE_TTS=openai

Lag between my speech and response

Use local Whisper-tiny for STT; cloud adds 500ms+

Alternativen

VoiceMode vs. andere

Alternative	Wann stattdessen	Kompromiss
macOS Dictation + say command	You just want basic OS-level voice	No integration with Claude's output — one-way only
Superwhisper / Wispr Flow	You want a polished native macOS dictation app	Not MCP-integrated; no agent-level workflows

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen