Cartesia MCP Server

What is Cartesia MCP Server about?

The server acts as a bridge between local client applications and Cartesia's cloud API, enabling operations like voice list retrieval, text‑to‑speech synthesis, speech localization to different languages, and audio segment infilling.

How to use Cartesia MCP Server?

Create a Cartesia account and obtain an API key from the Cartesia playground.
Install the package:
```
pip install cartesia-mcp
```
Find the executable path:
```
which cartesia-mcp
```
Configure the client (Claude Desktop, Cursor, etc.) by specifying the command (absolute path to the executable) and required environment variables:
- CARTESIA_API_KEY: your Cartesia API key
- OUTPUT_DIRECTORY (optional): directory where generated audio files will be saved
Issue commands from the client UI (e.g., ask Claude to list voices, synthesize text, localize speech, etc.).

Key features of Cartesia MCP Server

Voice listing: retrieve all available Cartesia voices.
Text‑to‑speech: generate high‑quality audio from any text using a selected voice.
Speech localization: translate and re‑voice existing audio into a different language.
Audio infill: create seamless audio between two existing clips.
Voice swapping: re‑render an audio file with a different voice.
Simple integration: works with Claude Desktop, Cursor, and other MCP‑compatible agents.

Use cases of Cartesia MCP Server

Building AI assistants that can speak in multiple languages.
Generating narration or podcast segments programmatically.
Creating multilingual audio assets for games or e‑learning.
Automating voice‑over production pipelines.
Enhancing chat‑based agents (Claude, Cursor) with on‑the‑fly audio responses.

FAQ from the Cartesia MCP Server

Q: Do I need a paid Cartesia plan? A: No. The free tier provides 20,000 credits per month, sufficient for most development and testing scenarios.

Q: Which environment variable stores the API key? A: CARTESIA_API_KEY.

Q: Where are generated audio files saved? A: By default they are written to the current working directory; you can set OUTPUT_DIRECTORY to change the location.

Q: Can I run the server on Windows? A: Yes, as long as Python and the cartesia-mcp package are installed and the executable is on the system PATH.

Q: How do I integrate with Cursor? A: Create a .cursor/mcp.json (project‑level) or ~/.cursor/mcp.json (global) containing the same configuration used for Claude Desktop.

The Cartesia MCP server provides a way for clients such as Cursor, Claude Desktop, and OpenAI agents to interact with Cartesia's API. Users can localize speech, convert text to audio, infill voice clips etc.

Cartesia Setup

Ensure that you have created an account on Cartesia, there is a free tier with 20,000 credits per month. Once in the Cartesia playground, create an API key under API Keys --> New.

Installation

pip install cartesia-mcp
which cartesia-mcp # absolute path to executable

Claude Desktop Integration

Add the following to claude_desktop_config.json which can be found through Settings --> Developer --> Edit Config.

{
  "mcpServers": {
    "cartesia-mcp": {
      "command": "<absolute-path-to-executable>",
      "env": {
        "CARTESIA_API_KEY": "<insert-your-api-key-here>",
        "OUTPUT_DIRECTORY": // directory to store generated files (optional)
      }
    }
  }
}

Try asking Claude to

List all available Cartesia voices
To convert a text phrase into audio using a particular voice
To localize an existing voice into a different language
To infill audio between two existing audio segments (specify absolute paths to audio files)
To change an audio file to use a different voice

Cursor Integration

Create either a .cursor/mcp.json in your project or a global ~/.cursor/mcp.json. The same config as for Claude can be used.

Cartesia MCP Server