@angrysky56
基本情報
Zonos MCP server modified for Linux and GPU optimizations.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"Zonos-TTS-MCP-Linux": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@PhialsBasement/zonos-tts-mcp",
"--client",
"claude"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
The Zonos TTS MCP for Linux is a Model Context Protocol (MCP) server that integrates Zonos text‑to‑speech with Claude on Linux systems. It enables Claude to generate natural‑sounding speech in multiple languages and emotions, using a running Zonos API instance and PulseAudio or PipeWire for audio playback.
Install via Smithery (npx -y @smithery/cli install @PhialsBasement/zonos-tts-mcp --client claude) or manually: clone the repo, install dependencies (npm install @modelcontextprotocol/sdk axios zod), build (npm run build), then add the server to Claude’s config under mcpServers. Once configured, Claude can call the speak_response tool with parameters text, language (e.g., "en-us"), and emotion ("neutral", "happy", "sad", "angry").
Console output has been redirected to a log file (`/tmp/zonos-tts-mcp.log`) to prevent JSON parsing errors. Check that file for details; the server uses optimized TTS parameters to avoid common compatibility issues.
Performance optimizations are included: the server uses more efficient sampling parameters (`top_p` and `min_p`). If needed, you can adjust these values in the server code to further lower GPU load.
Node.js, PulseAudio or PipeWire with its PulseAudio compatibility layer, a working audio output device, a running instance of the Zonos API (from [PhialsBasement/zonos-api](https://github.com/PhialsBasement/Zonos-API)), and the Claude Desktop app.
No. This fork is specifically adapted for Linux environments and includes GPU optimizations for that platform. The original upstream project ([PhialsBasement/zonos-tts-mcp](https://github.com/PhialsBasement/Zonos-TTS-MCP)) may support other systems.
Audio is played directly through the system’s audio output (PulseAudio/PipeWire). No audio files are stored by default; the server sends the audio stream for immediate playback.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep
Painless E2E Automation for Mobile and Web
See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one
コメント