cd elevenlabs-mcp
bun install

PORT=3000
AUTH_STRATEGY=api_key
API_KEY=xi_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
API_KEY_HEADER=xi-api-key
ELEVENLABS_API_KEY=xi_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

bun dev
# MCP: http://127.0.0.1:3000/mcp

bunx @modelcontextprotocol/inspector
# Connect to: http://localhost:3000/mcp

{
  "mcpServers": {
    "elevenlabs": {
      "command": "bunx",
      "args": [
        "mcp-remote",
        "http://localhost:3000/mcp",
        "--header",
        "x-api-key: ${ELEVENLABS_API_KEY}"
      ]
    }
  }
}

// Input
{}

// Output
{
  count: number;
  voices: Array<{
    voice_id: string;
    name: string;
    category: string;
    labels: Record<string, string>;
    preview_url: string | null;
  }>;
}

// Input
{
  text: string;                    // Required — text to convert
  voice_id: string;                // Required — from list_voices
  model_id?: string;               // Default: eleven_multilingual_v2
  output_format?: string;          // Default: mp3_44100_128
  language_code?: string;          // ISO 639-1 code
  voice_settings?: {
    stability?: number;            // 0-1
    similarity_boost?: number;     // 0-1
    speed?: number;                // 0.1-3.0
    style?: number;                // 0-1
  };
}

// Output: base64-encoded audio as a data URI resource

// Input
{
  file_url?: string;               // HTTPS URL of the file
  file_base64?: string;            // Base64-encoded file content
  file_name?: string;              // Filename when using base64
  model_id?: string;               // scribe_v1 (default) or scribe_v2
  language_code?: string;          // ISO 639-1/3 code (auto-detect if omitted)
  diarize?: boolean;               // Identify speakers
  num_speakers?: number;           // Expected speaker count (1-32)
  tag_audio_events?: boolean;      // Tag (laughter), (footsteps), etc.
  timestamps_granularity?: string; // none, word, character
}

// Output
{
  text: string;
  language_code: string;
  language_probability: number;
  transcription_id: string | null;
}

// Input
{ voice_id: string }

// Output: voice details including name, category, labels, settings, preview_url

// Input
{ transcription_id: string }

// Output: full transcript text with language and word count

// Input
{ transcription_id: string }

// Output: deletion confirmation

// First, find a voice
{ "name": "list_voices", "arguments": {} }

// Then generate audio
{
  "name": "text_to_speech",
  "arguments": {
    "text": "Hello, this is a test of the ElevenLabs text to speech system.",
    "voice_id": "JBFqnCBsd6RMkjVDRZzb",
    "output_format": "mp3_44100_128"
  }
}

{
  "name": "speech_to_text",
  "arguments": {
    "file_url": "https://example.com/recording.mp3",
    "diarize": true,
    "language_code": "en"
  }
}

{
  "name": "speech_to_text",
  "arguments": {
    "file_url": "https://example.com/meeting.mp3",
    "diarize": true,
    "num_speakers": 3,
    "tag_audio_events": true
  }
}

bun dev           # Start with hot reload
bun run typecheck # TypeScript check
bun run lint      # Lint code
bun run build     # Production build
bun start         # Run production

src/
├── shared/
│   └── tools/
│       └── elevenlabs/        # ElevenLabs tool definitions
│           ├── api.ts         # Shared API helpers
│           ├── text-to-speech.ts
│           ├── speech-to-text.ts
│           ├── list-voices.ts
│           ├── get-voice.ts
│           ├── get-transcript.ts
│           └── delete-transcript.ts
├── config/
│   ├── env.ts                 # Environment config
│   └── metadata.ts            # Tool & server metadata
├── core/
│   ├── capabilities.ts        # MCP capabilities
│   ├── context.ts             # Request context
│   └── mcp.ts                 # MCP server builder
├── http/
│   ├── app.ts                 # Hono HTTP app
│   ├── middlewares/            # Auth, CORS
│   └── routes/                # Health, MCP
├── index.ts                   # Node.js entry
└── worker.ts                  # Workers entry