MCP Text-to-Speech Server

Model Context Protocol server for text-to-speech synthesis using Azure Speech Services.

Features

• 🎵 High-Quality Speech: Azure Neural voices with natural sound

• 🌍 6 Languages: English, Finnish, Spanish, German, French, Swedish

• 🗣️ Smart Voice Selection: Auto-select optimal voices or specify manually

• 📊 Performance Metrics: Synthesis timing and audio stats

• 🔧 MCP Compatible: Works with Claude Desktop, VS Code, other MCP clients

Related MCP server: voiceroid_daemon-mcp

Supported Voices

Quick Start

# 1. Install
npm install

# 2. Configure (copy from parent or create .env)
cp ../.env .env

# 3. Test
npm run test:basic

# 4. Start
npm start

Required .env:

AZURE_SPEECH_KEY=your-key
AZURE_SPEECH_REGION=westeurope

MCP Integration

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "audio-tts": {
      "command": "node",
      "args": ["/path/to/mcp-server/mcp-server.mjs"],
      "env": {"AZURE_SPEECH_KEY": "your-key", "AZURE_SPEECH_REGION": "westeurope"}
    }
  }
}

VS Code

Use included .vscode/mcp.json or install MCP extension.

Usage

Natural language: "Convert to Finnish speech: Hei kaikki, olen Jenny."

Direct tool call:

{
  "tool": "synthesize_speech",
  "parameters": {
    "sentence": "Hei kaikki, olen Jenny ja puhun suomea.",
    "language": "fi-FI", 
    "voice": "en-US-JennyMultilingualNeural"
  }
}

Tool Parameters

Output

Audio saved to ./audio/mcp-generated/ as:

mcp-tts-fi_FI-en-US-JennyMultilingualNeural-2025-08-17T16-30-45-123Z.wav

Returns: file path, voice used, performance metrics (synthesis time, duration, etc.)

Troubleshooting

Server won't start: Check Azure credentials in .env, ensure Node.js 16+, run npm install

No audio output: Verify output directory exists, check Azure quota/billing, confirm supported language

Voice issues: Use exact voice names from table above, try language default, check Azure region support

Debug mode: DEBUG=* npm start

Requirements

• Node.js 16+

• Azure Speech Services API key

• MCP-compatible client (Claude Desktop, VS Code with MCP extension)

Built with Model Context Protocol for universal AI integration