Interactive Voice MCP Server
交互式语音 MCP 服务器 (Kokoro TTS + NeMo ASR)
模型上下文协议服务器使用 Kokoro 提供文本转语音 (TTS) 功能,使用 NVIDIA NeMo Parakeet 模型提供语音转文本 (STT) 功能,从而实现交互式语音对话。
可用工具
interactive_voice_dialog- 将文本合成为语音,播放,然后监听用户语音输入并返回转录。必需参数:
text_to_speak(字符串):助手要说的文本。
可选参数:
voice(字符串):用于 TTS 的语音(例如“af_heart”)。默认为“af_heart”。
安装
先决条件
一些底层 TTS 模型需要在您的系统上安装espeak-ng 。
Windows 安装:
点击“最新版本”。
下载适当的
*.msi文件(例如espeak-ng-20191129-b702b03-x64.msi)。运行下载的安装程序。
本地开发安装
要允许 Claude Desktop 使用python -m mcp_server_tts启动此服务器,您需要将其安装为 Python 模块。建议在开发过程中以“可编辑”模式 ( -e ) 安装,因为这意味着对源代码的更改会立即生效,而无需重新安装。
导航到包含pyproject.toml文件的目录(此服务器项目的根目录)并运行:
pip install -e .安装后,您可以使用以下命令将其作为脚本运行:
python -m mcp_server_tts.server # Assuming the main module is still server.py within mcp_server_tts
# Or, if you create a new package structure:
# python -m mcp_interactive_voice_serverRelated MCP server: Voice MCP
配置
要将此服务器与 Claude Desktop 一起使用,您需要将其添加到claude_desktop_config.json文件中。该文件通常位于: C:\Users\<YourUsername>\AppData\Roaming\Claude\claude_desktop_config.json
在claude_desktop_config.json中的mcpServers对象下添加以下条目:
"tts": {
"command": "python",
"args": ["-m", "mcp_server_tts"]
}例如,您的mcpServers部分可能如下所示:
{
// ... other configurations ...
"mcpServers": {
// ... other servers ...
"tts": {
"command": "python",
"args": ["-m", "mcp_server_tts"]
}
// ... other servers ...
}
// ... other configurations ...
}Related MCP Connectors
Intimate voice AI: 29 voices, 22 languages, emoji vocal cues, multi-voice scenes.
1Voice and chat for AI agents — Discord, Teams, Meet, Slack, Zoom, Telegram, WhatsApp, NC Talk, SIP
Audio and video tools for your AI assistant: remove noise, enhance voices, transcribe, and more.
Transcribe audio and video with Speechmatics speech-to-text from Claude and any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables hands-free voice conversations with Claude using real-time speech recognition and text-to-speech on macOS. Creates a self-sustaining conversation loop where Claude can autonomously listen, respond, and continue the interaction without keyboard input.MIT
- AlicenseNot gradedqualityDmaintenanceEnables bidirectional voice interaction for Claude Code using local speech-to-text and text-to-speech models optimized for Apple Silicon. It provides tools to listen to user speech via microphone and speak responses aloud through system speakers.16Apache 2.0
- AlicenseNot gradedqualityDmaintenanceProvides text-to-speech generation using the Kokoro-82M model, enabling AI assistants to generate voiceovers and audio content directly within Claude Desktop and Cursor.15Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables text-to-speech, voice cloning, audio generation, and transcription using Kokoro TTS and Whisper STT.6 npm34 PyPI1MIT