Skip to main content
Glama

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

Language

Default Voice

Alternatives

English (en-US)

en-US-RyanMultilingualNeural

en-US-JennyMultilingualNeural, en-US-AndrewMultilingualNeural

Finnish (fi-FI)

en-US-RyanMultilingualNeural

en-US-JennyMultilingualNeural, fi-FI-SelmaNeural, fi-FI-NooraNeural

Spanish (es-ES)

es-ES-AlvaroNeural

es-ES-ElviraNeural

German (de-DE)

de-DE-ConradNeural

de-DE-KatjaNeural

French (fr-FR)

fr-FR-DeniseNeural

fr-FR-HenriNeural

Swedish (sv-SE)

sv-SE-MattiasNeural

sv-SE-SofieNeural

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

Parameter

Required

Description

sentence

✅

Text to convert (1-1000 chars)

language

✅

Language code (en-US, fi-FI, es-ES, de-DE, fr-FR, sv-SE)

voice

❌

Specific voice (uses language default if not specified)

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

Available Tools

1 tool
synthesize_speechA

Convert text to speech using Microsoft Azure Speech Services. Supports multiple languages and voices.

Inputs: language (required), sentence (required), voice.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool in the server, there is no possibility of confusion or overlap. The single tool has a clear and unique purpose of converting text to speech.

    Naming Consistency5/5

    The tool name 'synthesize_speech' follows a clear verb_noun pattern, which is consistent and predictable. Although there is only one tool, the naming convention is sound and would align with a well-structured set.

    Tool Count3/5

    The server has a single tool, which feels thin for a text-to-speech service. While a minimal server could focus solely on synthesis, a typical TTS backend would benefit from additional tools such as listing available voices or managing audio outputs, making the current count borderline.

    Completeness3/5

    The core action of synthesizing speech is covered, but there is a notable gap in metadata discovery—agents cannot query available voices or languages programmatically. This limits the surface's ability to fully support dynamic voice selection, though the synthesis itself is functional.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      An MCP server integrated with Microsoft Edge's high-quality speech synthesis capabilities, supporting multilingual speech generation, audio merging, and cloud storage.
      1
      2
      Apache 2.0
    • A
      license
      A
      quality
      D
      maintenance
      An MCP server that enables text-to-speech generation and phonetic kana conversion using VOICEROID2 via voiceroid_daemon. It supports customizable voice parameters and provides cross-platform audio playback for synthesized speech.
      3
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that leverages the Microsoft Edge TTS service to provide high-quality text-to-speech capabilities across over 80 languages. It enables users to generate audio files, query available voices, and create subtitle files using natural language commands.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that converts text into lifelike speech using Microsoft Edge's Text-to-Speech service, supporting customizable voice, rate, volume, and pitch.
      4
      MIT