The Murf MCP Server offers seamless integration with MCP clients like Claude Desktop, enabling developers and creators to convert text into lifelike speech effortlessly. With over 130 natural-sounding voices across 13+ languages and 20+ speaking styles, Murf provides unparalleled speech customization for a wide range of applications.
-
Get your API key from Murf API Dashboard.
-
Install
uv
(Python package manager), install with: macOS:curl -LsSf https://astral.sh/uv/install.sh | sh
Windows:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Check out their official guide for more details.
-
There are two ways to proceed with the setup:
Option 1: Automated Setup (Recommended)
uvx setup-murf-mcp-claude
This will automatically configure Claude Desktop with the Murf MCP server.
Option 2: Manual Setup
If you prefer to configure manually, continue with the following steps:
-
Update Claude Desktop Config to install murf, open the config file: Go to
Claude → Settings → Developer → Edit Config → claude_desktop_config.json
or if you have VS Code installed, run:
macOS:
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows:
code $env:AppData\Claude\claude_desktop_config.json
-
This will open the config file, add the following lines to the
"mcpServers"
section:"mcpServers": { "Murf":{ "command": "uvx", "args": ["murf-mcp"], "env": { "MURF_API_KEY": "YOUR_MURF_API_KEY" } } }
-
Install FFmpeg (required for audio processing):
macOS:
brew install ffmpeg
Windows: Download FFmpeg from here
-
-
Restart the Claude Desktop app to start the MCP server, you should be able to see a small hammer icon in the chat input box. This indicates that the MCP server is running and tools are available.
Note: For Windows users, "Developer Mode" must be enabled in Claude Desktop to utilize the MCP server. To enable it, click the hamburger menu in the top-left corner, select "Help," and then choose "Enable Developer Mode."
-
Prompt the LLM to create a voiceover: For example:
-
Create a one-minute podcast on Generative AI featuring a conversation between two speakers. Choose suitable voice styles and accents, incorporate natural pauses, and generate a voiceover for it.
-
Create a 15-second introduction for my YouTube channel about indoor plants. Use a friendly and conversational tone to generate a voiceover for it.
These should generate a voiceover and save it to file on your Desktop.
-
-
You can also prompt the LLM to recommend a voice style for a specific use case. For example:
- What is the best voice style for a YouTube video about indoor plants?
- What is the best voice style for a podcast about Generative AI?
-
The TTS API supports a variety of features such as rate, pitch, speed, and custom pronunciations. You can explore these options here. You can prompt the LLM to apply these settings to the overall voiceover or tailor them individually for each speaker.
Contributions are welcome! If you’d like to improve the MCP server, follow these steps:
-
Fork the repository and clone it to your machine.
-
Create a new branch for your feature or bugfix.
-
Make your changes and ensure everything runs smoothly.
-
Write clear commit messages and keep the code clean.
-
Open a pull request describing your changes.
Feel free to open an issue if you have questions, feature requests, or need help getting started.
If you encounter any issues, please check the following:
-
spawn uvx ENOENT
error: If you see aspawn uvx ENOENT
error, it means the system can't locate the uvx executable. To fix this:- Run the following command to get the absolute path of
uvx
:which uvx
- Update your
claude_desktop_config.json
file with the absolute path in thecommand
field. For example:"command": "/absolute/path/to/uvx"
- Restart the Claude Desktop app.
- Run the following command to get the absolute path of
-
Check the logs for any other error messages or warnings here:
- macOS:
~/Library/Logs/Claude/mcp-server-Murf.log
- Windows:
%APPDATA%\Claude\logs\mcp-server-Murf.log
- macOS: