VoiceMode MCP — ユースケース, インストール & ライブデモ

なぜ使うのか

主な機能

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

ライブデモ

実際の動作

voicemode-mcp.replay ▶ 準備完了

0/0

インストール

クライアントを選択

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

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

Claude Desktop → Settings → Developer → Edit Config を開く。保存後、アプリを再起動。

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor は Claude Desktop と同じ mcpServers スキーマを使用。プロジェクト設定はグローバルより優先。

VS Code → Cline → MCP Servers → Edit

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

Cline サイドバーの MCP Servers アイコンをクリックし、"Edit Configuration" を選択。

~/.codeium/windsurf/mcp_config.json

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

Claude Desktop と同じ形式。Windsurf を再起動して反映。

~/.continue/config.json

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

Continue はマップではなくサーバーオブジェクトの配列を使用。

~/.config/zed/settings.json

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

context_servers に追加。保存時に Zed がホットリロード。

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

ワンライナー。claude mcp list で確認、claude mcp remove で削除。

ユースケース

実用的な使い方： 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

使うタイミング： You're reading a design doc and want to dictate changes without alt-tabbing.

前提条件

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

フロー

Start voice

Use voicemode. Listen for prompts and speak responses. Repeat after me: "ready"✓ コピーしました

→ TTS plays "ready"
Dictate a change

[spoken] Update src/auth.ts — use bcrypt instead of plain SHA256 for passwords.✓ コピーしました

→ Transcription correct; change applied; TTS confirms
Review

[spoken] Read me the diff.✓ コピーしました

→ TTS reads diff in chunks, pausable

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

注意点

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

組み合わせ： filesystem

Code by voice for accessibility or RSI recovery

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

使うタイミング： You can't type for a while and need to keep shipping.

前提条件

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

フロー

Baseline

[spoken] Use voicemode. Read the latest git diff out loud, pausing between files.✓ コピーしました

→ 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.✓ コピーしました

→ Plan spoken; confirmation required before changes

結果： A full coding session without keyboard input.

注意点

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

組み合わせ

他のMCPと組み合わせて10倍の力を

voicemode-mcp + filesystem

Voice-dictated code changes land in the repo

I'll dictate changes; apply them in files after reading each back.✓ コピーしました

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.✓ コピーしました

ツール

このMCPが提供する機能

ツール	入力	呼び出すタイミング	コスト
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

コストと制限

運用コスト

APIクォータ: Local: free. OpenAI Whisper: $0.006/min. ElevenLabs TTS: ~$0.30/1k chars.
呼び出しあたりのトークン: Audio pipelines are not token-costed directly
金額: Free with local stack; metered with cloud providers
ヒント: Local Whisper + Coqui TTS is totally free but lower quality — start cloud, downgrade later

セキュリティ

権限、シークレット、影響範囲

最小スコープ： microphone speakers

認証情報の保管： TTS/STT API keys in env

データ送信先： 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

トラブルシューティング

よくあるエラーと対処法

Mic not detected

System audio permission — grant terminal/Claude Code mic access

確認： `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+

代替案

VoiceMode 他との比較

代替案	代わりに使う場面	トレードオフ
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

その他

リソース

📖 GitHub の公式 README を読む

🐙 オープンな issue を見る

🔍 400以上のMCPサーバーとSkillsを見る