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

Por que usar

Principais recursos

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 ao vivo

Como fica na prática

voicemode-mcp.replay ▶ pronto

0/0

Instalar

Escolha seu cliente

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

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

Abra Claude Desktop → Settings → Developer → Edit Config. Reinicie após salvar.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor usa o mesmo esquema mcpServers que o Claude Desktop. Config de projeto vence a global.

VS Code → Cline → MCP Servers → Edit

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

Clique no ícone MCP Servers na barra lateral do Cline, depois "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Mesmo formato do Claude Desktop. Reinicie o Windsurf para aplicar.

~/.continue/config.json

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

O Continue usa um array de objetos de servidor em vez de um map.

~/.config/zed/settings.json

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

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

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

Uma linha só. Verifique com claude mcp list. Remova com claude mcp remove.

Casos de uso

Usos do 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

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

Pré-requisitos

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

Fluxo

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.

Armadilhas

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

Combine com: filesystem

Code by voice for accessibility or RSI recovery

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

Quando usar: You can't type for a while and need to keep shipping.

Pré-requisitos

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

Fluxo

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.

Armadilhas

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

Combinações

Combine com outros MCPs para 10× de alavancagem

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

Ferramentas

O que este MCP expõe

Ferramenta	Entradas	Quando chamar	Custo
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

Custo e limites

O que custa rodar

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

Segurança

Permissões, segredos, alcance

Escopos mínimos: microphone speakers

Armazenamento de credenciais: TTS/STT API keys in env

Saída de dados: 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

Solução de problemas

Erros comuns e correções

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. outros

Alternativa	Quando usar	Troca
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

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills