Edge TTS MCP
A cross-platform MCP server that enables Claude to speak using Microsoft Edge TTS with support for over 300 voices across 50+ languages. It requires no API keys and allows for customization of speech rate, volume, and pitch.
README
mcp-edge-tts - Give Claude a Voice!
Minimal cross-platform MCP server for text-to-speech using Microsoft Edge TTS.
Let Claude speak! Works with Claude Code and Claude Desktop.
Слава Україні!
Features
- 🎙️ 300+ voices in 50+ languages
- 🖥️ Cross-platform: Windows, macOS, Linux
- 🔑 Zero API keys required
- ⚙️ Customizable: speed, volume, pitch
- 🤖 Works with Claude Code and Claude Desktop
Installation
Via pip (recommended)
pip install mcp-edge-tts
From source
Windows
git clone https://github.com/s-n-n/edge-tts-mcp.git
cd edge-tts-mcp
python -m venv venv
venv\Scripts\activate
pip install -e .
macOS / Linux
git clone https://github.com/s-n-n/edge-tts-mcp.git
cd edge-tts-mcp
python3 -m venv venv
source venv/bin/activate
pip install -e .
Setup
Add to your MCP configuration:
If installed via pip
{
"mcpServers": {
"edge-tts": {
"command": "python",
"args": ["-m", "mcp_edge_tts"]
}
}
}
If installed from source
Claude Code (.mcp.json)
Windows:
{
"mcpServers": {
"edge-tts": {
"command": "C:\\path\\to\\edge-tts-mcp\\venv\\Scripts\\python.exe",
"args": ["-m", "mcp_edge_tts"]
}
}
}
macOS / Linux:
{
"mcpServers": {
"edge-tts": {
"command": "/path/to/edge-tts-mcp/venv/bin/python",
"args": ["-m", "mcp_edge_tts"]
}
}
}
Usage
speak
Speak text aloud.
speak("Hello, world!")
speak("Привіт!", voice="uk-UA-PolinaNeural")
speak("Fast!", rate="+50%")
Parameters:
| Parameter | Description | Example |
|---|---|---|
text |
Text to speak | "Hello" |
voice |
Voice name | "en-US-AriaNeural" |
rate |
Speed (-50% to +100%) | "+20%" |
volume |
Volume (-50% to +100%) | "+10%" |
pitch |
Pitch (-50Hz to +50Hz) | "+5Hz" |
list_available_voices
List voices, optionally filtered by language.
list_available_voices()
list_available_voices("uk")
get_config
Show current settings and available audio players.
Configuration
Set defaults via environment variables or .env file:
EDGE_TTS_VOICE=uk-UA-OstapNeural
EDGE_TTS_RATE=+0%
EDGE_TTS_VOLUME=+0%
EDGE_TTS_PITCH=+0Hz
EDGE_TTS_PLAYER=auto
Audio Players
Auto-detected by platform:
| Platform | Default Player | Alternatives |
|---|---|---|
| Windows | PowerShell MediaPlayer (built-in) | ffplay, mpv |
| macOS | afplay (built-in) | ffplay, mpv |
| Linux | ffplay | mpv, paplay |
Popular Voices
| Language | Voice | Gender |
|---|---|---|
| Ukrainian | uk-UA-OstapNeural | Male |
| Ukrainian | uk-UA-PolinaNeural | Female |
| English (US) | en-US-AriaNeural | Female |
| English (US) | en-US-GuyNeural | Male |
| German | de-DE-ConradNeural | Male |
| French | fr-FR-DeniseNeural | Female |
| Spanish | es-ES-AlvaroNeural | Male |
| Chinese | zh-CN-XiaoxiaoNeural | Female |
Run list_available_voices() for full list.
Requirements
- Python 3.10+
- No additional software on Windows/macOS (uses built-in players)
- Linux:
ffmpegormpvrecommended
License
MIT
Made with ❤️ in Ukraine
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。