A
licenseA
qualityC
maintenanceAn MCP server implementation that integrates with Minimax API to provide AI-powered image generation and text-to-speech functionality in editors like Windsurf and Cursor.
3
32
50
MIT
minimax-tts-mcp
minimax-tts-mcp
一个轻量级的 MCP（模型上下文协议）服务器，让 AI 能够说话。输入文本，输出音频 URL。
使用 Flask + MiniMax TTS API 构建。
功能
通过 MCP 协议暴露
generate_speech工具AI 发送文本 → 服务器调用 MiniMax TTS → 返回可播放的 mp3 URL
支持情绪控制、语速调整和语言选择（粤语、普通话等）
Related MCP server: Blabber-MCP
快速开始
1. 克隆并安装
git clone https://github.com/YOUR_USERNAME/minimax-tts-mcp.git
cd minimax-tts-mcp
pip install -r requirements.txt2. 配置
cp .env.example .env
# Edit .env with your MiniMax API key and voice ID从 MiniMax 平台 获取你的 API 密钥和语音 ID。
3. 运行
python server.py服务器启动于 http://localhost:5000。
端点
端点 | 方法 | 描述 |
| POST | 用于 AI 工具调用的 MCP 协议端点 |
| POST | 直接 TTS — 提交 JSON，获取 mp3 文件 |
| GET | 提供生成的音频文件 |
| GET | 健康检查 |
MCP 集成
添加到你的 MCP 客户端配置中：
{
"mcpServers": {
"tts": {
"url": "http://localhost:5000/mcp"
}
}
}服务器暴露一个工具：
generate_speech
参数 | 类型 | 必填 | 描述 |
text | string | 是 | 要朗读的文本 |
emotion | string | 否 | neutral, happy, sad, angry, fearful, surprised, disgusted |
speed | number | 否 | 0.5 - 2.0（默认 0.9） |
language | string | 否 | 例如 "Chinese,Yue" 表示粤语 |
直接 TTS 用法
curl -X POST http://localhost:5000/tts \
-H "Content-Type: application/json" \
-d '{"text": "Hello world", "speed": 1.0}' \
--output speech.mp3部署
适用于任何运行 Python 的环境——VPS、云虚拟机或容器。如需公网访问，请将其置于反向代理（nginx/caddy）之后并启用 HTTPS。
使用 systemd 的示例：
# /etc/systemd/system/tts-mcp.service
[Unit]
Description=MiniMax TTS MCP Server
[Service]
WorkingDirectory=/path/to/minimax-tts-mcp
EnvironmentFile=/path/to/minimax-tts-mcp/.env
ExecStart=/usr/bin/python3 server.py
Restart=always
[Install]
WantedBy=multi-user.target注意事项
生成的音频文件存储在
/tmp中，不会自动清理。生产环境请添加 cron 任务或清理逻辑。MiniMax API 是付费服务。请查看其 TTS 使用定价。
语音克隆需要先在 MiniMax 平台上设置自定义语音。
许可证
MIT
This server cannot be installed
Maintenance
–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that enables LLMs to generate spoken audio from text using OpenAI's Text-to-Speech API, supporting various voices, models, and audio formats.1121MIT
- FlicenseCqualityCmaintenanceAn MCP server that exposes speech-to-text and text-to-speech capabilities using a local speaches instance, allowing AI assistants to transcribe audio and generate speech.2
- Alicense-qualityDmaintenanceMCP server for MiniMax's multimodal generation models, enabling text-to-speech, voice cloning, image, video, and music creation through natural language.MIT
Related MCP Connectors
MCP server exposing the AceDataCloud Fish Audio API (text-to-speech with voice conditioning)
MCP server for Hailuo (MiniMax) AI video generation
MCP server for AI dialogue using various LLM models via AceDataCloud
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jb4f7mhbvf-svg/minimax-tts-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server