VoiceMode MCP — Casos de uso, Instalar & Demo en vivo

Por qué usarlo

Características clave

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

Demo en vivo

Cómo se ve en la práctica

voicemode-mcp.replay ▶ listo

0/0

Instalar

Elige tu cliente

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

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

Abre Claude Desktop → Settings → Developer → Edit Config. Reinicia después de guardar.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor usa el mismo esquema mcpServers que Claude Desktop. La configuración del proyecto prevalece sobre la global.

VS Code → Cline → MCP Servers → Edit

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

Haz clic en el icono MCP Servers de la barra lateral de Cline y luego en "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Mismo formato que Claude Desktop. Reinicia Windsurf para aplicar.

~/.continue/config.json

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

Continue usa un array de objetos de servidor en lugar de un mapa.

~/.config/zed/settings.json

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

Añádelo a context_servers. Zed recarga en caliente al guardar.

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

Un solo comando. Verifica con claude mcp list. Quita con claude mcp remove.

Casos de uso

Usos del mundo real: 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

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

Requisitos previos

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

Flujo

Start voice

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

→ TTS plays "ready"
Dictate a change

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

→ Transcription correct; change applied; TTS confirms
Review

[spoken] Read me the diff.✓ Copiado

→ TTS reads diff in chunks, pausable

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

Errores comunes

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

Combinar con: filesystem

Code by voice for accessibility or RSI recovery

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

Cuándo usarlo: You can't type for a while and need to keep shipping.

Requisitos previos

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

Flujo

Baseline

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

→ 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.✓ Copiado

→ Plan spoken; confirmation required before changes

Resultado: A full coding session without keyboard input.

Errores comunes

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

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

voicemode-mcp + filesystem

Voice-dictated code changes land in the repo

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

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.✓ Copiado

Herramientas

Lo que expone este MCP

Herramienta	Entradas	Cuándo llamar	Coste
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

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API: Local: free. OpenAI Whisper: $0.006/min. ElevenLabs TTS: ~$0.30/1k chars.
Tokens por llamada: Audio pipelines are not token-costed directly
Monetario: Free with local stack; metered with cloud providers
Consejo: Local Whisper + Coqui TTS is totally free but lower quality — start cloud, downgrade later

Seguridad

Permisos, secretos, alcance

Ámbitos mínimos: microphone speakers

Almacenamiento de credenciales: TTS/STT API keys in env

Salida de datos: 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

Resolución de problemas

Errores comunes y soluciones

Mic not detected

System audio permission — grant terminal/Claude Code mic access

Verificar: `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+

Alternativas

VoiceMode vs otros

Alternativa	Cuándo usarla	Contrapartida
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

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills