Skip to main content
Use Cartesia MCP in Cursor, Claude Code, or other MCP clients to list voices, run TTS and STT, manage pronunciation dictionaries, download cloud-stored generations, and more — no custom scripts.

​
Setup

Pick your client, install, and sign in when prompted. A Cartesia MCP API key is created for your organization if one does not exist yet.

Install in Cursor

Click install, then sign in to the Playground when your browser opens.

​
Try it

Ask your agent things like:
  • List all available Cartesia voices
  • Convert text to audio with a chosen voice (speed, volume, emotion) — returns file_id and usually a shareable download_url
  • 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

​
Tools

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

​
Hosted server

Default endpoint: https://mcp.cartesia.ai/mcp. The install flows above use this automatically.You can also connect from API Keys in the Playground. Org admins can opt in to admin tools when approving connect.

​
Local development

To run your own checkout with stdio and env vars (OUTPUT_DIRECTORY, CARTESIA_ADMIN_API_KEY, etc.), see the cartesia-mcp README.

​
Audio files

speech_to_text and clone_voice take an audio file you already have. Pass one of:
  • file_path — an absolute path on the machine running MCP. Use this with local uvx.
  • file_id — a Cartesia cloud file, including one from text_to_speech or playground history. Use this on hosted MCP (mcp.cartesia.ai). A path on your computer is not on that server.
download_url is a 24-hour browser link. It is not an input to those tools.For speech_to_text, use the default batch mode for typical file transcription (mp3, flac, wav, and other common containers). Use mode="stream" for mono PCM WAV (for example TTS output) or raw PCM with encoding and sample_rate.

​
TTS downloads

text_to_speech persists audio to your org’s cloud storage by default (save=true) and returns:
  • file_id — pass to download_file for a fresh link. You can also pass it to speech_to_text or clone_voice when the audio to reuse is this generation
  • download_url — when link creation succeeds, a time-limited URL (24 hours) you can open in a browser. If omitted, call download_file with the file_id.
  • file_path — copy on the machine running MCP. Local uvx can pass this path into a later tool on the same machine.
Set save=false for a local-only generation with no cloud fields.

​
API version

Cartesia MCP uses Cartesia-Version: 2026-08-14.

cartesia-mcp

The official Cartesia MCP Server