Kokoro
TTS toolkit built on Kokoro-82M with librosa audio enhancement, MCP server for Claude/Cursor, CLI & Python API. Free & open-source for YouTube creators.
What is Kokoro?
Kokoro is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to tts toolkit built on kokoro-82m with librosa audio enhancement, mcp server for claude/cursor, cli & python api. free & open-source for youtube creators.
TTS toolkit built on Kokoro-82M with librosa audio enhancement, MCP server for Claude/Cursor, CLI & Python API. Free & open-source for YouTube creators.
This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- TTS toolkit built on Kokoro-82M with librosa audio enhanceme
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx kokoroConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Kokoro
Kokoro MCP Server brings the Kokoro-82M text-to-speech model into Claude Desktop and other MCP clients, enabling AI-assisted voiceover generation with librosa-based audio enhancement. It is free, open-source, and designed for YouTube creators and developers who need high-quality speech synthesis through a simple natural language interface.
Prerequisites
- Python 3.9+ with pip installed
- espeak-ng and ffmpeg installed (brew install espeak ffmpeg on macOS; apt-get install espeak-ng ffmpeg on Ubuntu)
- libsndfile1 installed (Linux: apt-get install libsndfile1)
- Claude Desktop application installed
- Git to clone the repository
Install system dependencies
Install the audio libraries required by Kokoro's librosa audio enhancement pipeline. On macOS use Homebrew; on Ubuntu/Debian use apt-get.
# macOS
brew install espeak ffmpeg
# Ubuntu/Debian
sudo apt-get install espeak-ng ffmpeg libsndfile1Clone the repository and create a virtual environment
Clone the Kokoro MCP Server repository from GitHub and set up an isolated Python environment to avoid dependency conflicts.
git clone https://github.com/aparsoft/kokoro-mcp-server.git
cd kokoro-mcp-server
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activateInstall the package with MCP and CLI extras
Install the complete package including the MCP server module and CLI tool. The [mcp,cli] extras are the minimum needed for Claude Desktop integration.
pip install -e ".[mcp,cli]"
# Or install the full suite including the web UI:
pip install -e ".[complete]"Configure environment variables
Create a .env file in the project directory to set the default voice, speed, and audio enhancement options. These values are used by the MCP server at startup.
TTS_VOICE=am_michael
TTS_SPEED=1.0
TTS_ENHANCE_AUDIO=true
TTS_SAMPLE_RATE=24000
TTS_TRIM_SILENCE=true
TTS_TRIM_DB=20.0
TTS_FADE_DURATION=0.1
LOG_LEVEL=INFOFind the virtual environment Python path
Claude Desktop requires an absolute path to the Python binary inside the virtual environment. Record this path before editing the config file.
which python # Run with the venv activated
# Example output: /Users/you/kokoro-mcp-server/venv/bin/pythonAdd the server to Claude Desktop configuration
Edit claude_desktop_config.json to register the Kokoro MCP server. Replace the command value with the absolute Python path you recorded in the previous step.
{
"mcpServers": {
"aparsoft-tts": {
"command": "/absolute/path/to/venv/bin/python",
"args": ["-m", "aparsoft_tts.mcp_server"]
}
}
}Restart Claude Desktop and verify
Restart Claude Desktop (Cmd+R on macOS). Open a new conversation and ask Claude to list available voices to confirm the MCP server is connected.
Kokoro Examples
Client configuration
Minimal claude_desktop_config.json entry for the Kokoro MCP server using the virtual environment Python binary.
{
"mcpServers": {
"aparsoft-tts": {
"command": "/Users/you/kokoro-mcp-server/venv/bin/python",
"args": ["-m", "aparsoft_tts.mcp_server"]
}
}
}Prompts to try
Sample natural language prompts to use with the Kokoro MCP server in Claude Desktop.
- "List all available TTS voices"
- "Generate speech for 'Welcome to my channel' using am_michael voice and save to intro.wav"
- "Create voiceovers for these three segments: 'Intro', 'Main content', 'Outro' at 1.2x speed"
- "Process video_script.txt and generate a complete voiceover file"Troubleshooting Kokoro
ImportError or ModuleNotFoundError when the MCP server starts
Ensure the venv is activated and the package was installed with pip install -e ".[mcp,cli]". Confirm the command in claude_desktop_config.json points to the Python binary inside the venv, not the system Python.
espeak or ffmpeg not found errors during audio generation
Install the required system packages (brew install espeak ffmpeg on macOS or sudo apt-get install espeak-ng ffmpeg libsndfile1 on Ubuntu). These must be on the system PATH visible to the Python process.
Claude Desktop does not show the TTS tools
Restart Claude Desktop fully after editing the config. Check the Logs section in Claude Desktop for MCP server errors. Verify the absolute path in the config file is correct by running it directly in a terminal.
Frequently Asked Questions about Kokoro
What is Kokoro?
Kokoro is a Model Context Protocol (MCP) server that tts toolkit built on kokoro-82m with librosa audio enhancement, mcp server for claude/cursor, cli & python api. free & open-source for youtube creators. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Kokoro?
Follow the installation instructions on the Kokoro GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Kokoro?
Kokoro works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Kokoro free to use?
Yes, Kokoro is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Kokoro Alternatives — Similar Communication Servers
Looking for alternatives to Kokoro? Here are other popular communication servers you can use with Claude, Cursor, and VS Code.
Slack
★ 86.1kEnables interaction with Slack workspaces through comprehensive channel management, messaging, user management, file uploads, and Block Kit formatting. Features secure credential storage via macOS Keychain and supports all major Slack operations incl
LibreChat
★ 37.3kEnhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenA
Note Gen
★ 11.9kA cross-platform Markdown AI note-taking software.
DeepChat
★ 5.8k🐬DeepChat - A smart assistant that connects powerful AI to your personal world
WhatsApp MCP
★ 5.7kConnects AI assistants to the official Meta WhatsApp Cloud API for managing conversations and sending various message types through natural language. It provides tools for media management, template messages, and real-time webhook processing without
Apple
★ 3.1kEnables interaction with Apple apps like Messages, Notes, and Contacts through the MCP protocol to send messages, search, and open app content using natural language.
Browse More Communication MCP Servers
Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Kokoro in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Kokoro?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.