MCP - Cartesia Docs

The cartesia-mcp package exposes Cartesia through the Model Context Protocol (MCP) so MCP-capable clients—Cursor, Claude Code, Codex, and similar—can list voices, run TTS and STT, manage pronunciation dictionaries, clone voices, and more without custom scripts.

Requirements

uv — runs the server via uvx with no global install
Python 3.13+ (installed automatically by uvx)
A Cartesia API key (format sk_car_…)

Setup

Get an API key, then connect cartesia-mcp to your agent.

CLI (recommended)
Cursor
Claude Code

npx add-mcp "uvx cartesia-mcp" --name cartesia-mcp --env 'CARTESIA_API_KEY=${CARTESIA_API_KEY}'

Install Cartesia MCPSet CARTESIA_API_KEY in Settings → MCP.Or add to .cursor/mcp.json:

{
  "mcpServers": {
    "cartesia-mcp": {
      "command": "uvx",
      "args": ["cartesia-mcp"],
      "env": {
        "CARTESIA_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

claude mcp add -e CARTESIA_API_KEY=YOUR_API_KEY cartesia-mcp -- uvx cartesia-mcp

Try it

Ask your agent things like:

List all available Cartesia voices
Convert text to audio with a chosen voice (speed, volume, emotion)
Transcribe an audio file to text
Create a pronunciation dictionary and use it in TTS
Check credit usage for your account
Localize an existing voice into another language
Change an audio file to use a different voice

Tools

Tool	Description
`text_to_speech`	Convert text to audio; optional speed, volume, emotion, and pronunciation dict
`speech_to_text`	Stream-transcribe an audio file via STT WebSocket (`ink-2`)
`list_voices`	List available voices (filter by language, search, gender, etc.)
`get_voice`	Fetch metadata for a voice by ID
`clone_voice`	Clone a voice from an audio sample
`update_voice`	Update a cloned voice’s name or description
`delete_voice`	Delete a cloned voice
`voice_change`	Re-render audio with a different voice
`localize_voice`	Adapt a voice to another language or dialect
`list_pronunciation_dicts`	List pronunciation dictionaries
`create_pronunciation_dict`	Create a pronunciation dictionary
`get_pronunciation_dict`	Get a pronunciation dictionary by ID
`update_pronunciation_dict`	Update a pronunciation dictionary
`delete_pronunciation_dict`	Delete a pronunciation dictionary
`get_credit_usage`	Credit usage over time (admin API key)

See the cartesia-mcp source for parameters and return types.

Advanced configuration

Output directory

By default, generated audio is written to the server’s working directory. To choose a fixed folder, add OUTPUT_DIRECTORY to env:

"env": {
  "CARTESIA_API_KEY": "YOUR_API_KEY",
  "OUTPUT_DIRECTORY": "~/cartesia-output"
}

Local audio files

Tools like speech_to_text and voice_change need paths to existing audio files on disk. Pass the full path to each file when prompting your agent. For speech_to_text, use a mono PCM WAV file (or raw PCM with encoding and sample_rate).

Admin API key

Some tools call management endpoints that accept admin API keys only (sk_car_admin_...). To use get_credit_usage, set CARTESIA_ADMIN_API_KEY in env in addition to CARTESIA_API_KEY. Admin keys work only on management routes; API keys from play.cartesia.ai/keys do not work on those routes, and admin keys do not work on generation routes.Mint admin keys in the Playground under Keys → Admin (organization admins only).

"env": {
  "CARTESIA_API_KEY": "YOUR_API_KEY",
  "CARTESIA_ADMIN_API_KEY": "YOUR_ADMIN_API_KEY"
}

API version

Cartesia MCP is built using Cartesia-Version: 2026-03-01.

cartesia-mcp

The official Cartesia MCP Server

​Requirements

​Setup

​Try it

​Tools

​Output directory

​Local audio files

​Admin API key

​API version