VoiceMode MCP — Сценарии использования, Установка & Живое демо

Зачем использовать

Ключевые функции

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

Живое демо

Как выглядит на практике

voicemode-mcp.replay ▶ готово

0/0

Установка

Выберите клиент

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

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

Откройте Claude Desktop → Settings → Developer → Edit Config. Перезапустите после сохранения.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor использует ту же схему mcpServers, что и Claude Desktop. Конфиг проекта приоритетнее глобального.

VS Code → Cline → MCP Servers → Edit

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

Щёлкните значок MCP Servers на боковой панели Cline, затем "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Тот же формат, что и Claude Desktop. Перезапустите Windsurf для применения.

~/.continue/config.json

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

Continue использует массив объектов серверов, а не map.

~/.config/zed/settings.json

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

Добавьте в context_servers. Zed перезагружается автоматически.

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

Однострочная команда. Проверить: claude mcp list. Удалить: claude mcp remove.

Сценарии использования

Реальные сценарии: 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

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

Предварительные требования

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

Поток

Start voice

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

→ TTS plays "ready"
Dictate a change

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

→ Transcription correct; change applied; TTS confirms
Review

[spoken] Read me the diff.✓ Скопировано

→ TTS reads diff in chunks, pausable

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

Подводные камни

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

Сочетать с: filesystem

Code by voice for accessibility or RSI recovery

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

Когда использовать: You can't type for a while and need to keep shipping.

Предварительные требования

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

Поток

Baseline

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

→ 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.✓ Скопировано

→ Plan spoken; confirmation required before changes

Итог: A full coding session without keyboard input.

Подводные камни

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

Комбинации

Сочетайте с другими MCP — эффект x10

voicemode-mcp + filesystem

Voice-dictated code changes land in the repo

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

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.✓ Скопировано

Инструменты

Что предоставляет этот MCP

Инструмент	Входные данные	Когда вызывать	Стоимость
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

Стоимость и лимиты

Во что обходится

Квота API: Local: free. OpenAI Whisper: $0.006/min. ElevenLabs TTS: ~$0.30/1k chars.
Токенов на вызов: Audio pipelines are not token-costed directly
Деньги: Free with local stack; metered with cloud providers
Совет: Local Whisper + Coqui TTS is totally free but lower quality — start cloud, downgrade later

Безопасность

Права, секреты, радиус поражения

Минимальные скоупы: microphone speakers

Хранение учётных данных: TTS/STT API keys in env

Исходящий трафик: 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

Устранение неполадок

Частые ошибки и исправления

Mic not detected

System audio permission — grant terminal/Claude Code mic access

Проверить: `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+

Альтернативы

VoiceMode в сравнении

Альтернатива	Когда использовать	Компромисс
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

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills