VoiceMode MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

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

Démo en direct

Aperçu en pratique

voicemode-mcp.replay ▶ prêt

0/0

Installer

Choisissez votre client

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

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

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit

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

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

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

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

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

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

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

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : 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

Quand l'utiliser : You're reading a design doc and want to dictate changes without alt-tabbing.

Prérequis

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

Déroulement

Start voice

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

→ TTS plays "ready"
Dictate a change

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

→ Transcription correct; change applied; TTS confirms
Review

[spoken] Read me the diff.✓ Copié

→ TTS reads diff in chunks, pausable

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

Pièges

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

Combiner avec : filesystem

Code by voice for accessibility or RSI recovery

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

Quand l'utiliser : You can't type for a while and need to keep shipping.

Prérequis

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

Déroulement

Baseline

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

→ 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.✓ Copié

→ Plan spoken; confirmation required before changes

Résultat : A full coding session without keyboard input.

Pièges

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

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

voicemode-mcp + filesystem

Voice-dictated code changes land in the repo

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

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.✓ Copié

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
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

Coût et limites

Coût d'exécution

Quota d'API: Local: free. OpenAI Whisper: $0.006/min. ElevenLabs TTS: ~$0.30/1k chars.
Tokens par appel: Audio pipelines are not token-costed directly
Monétaire: Free with local stack; metered with cloud providers
Astuce: Local Whisper + Coqui TTS is totally free but lower quality — start cloud, downgrade later

Sécurité

Permissions, secrets, portée

Portées minimales : microphone speakers

Stockage des identifiants : TTS/STT API keys in env

Sortie de données : 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

Dépannage

Erreurs courantes et correctifs

Mic not detected

System audio permission — grant terminal/Claude Code mic access

Vérifier : `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+

Alternatives

VoiceMode vs autres

Alternative	Quand l'utiliser	Compromis
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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills