Cartesia

Read something aloud in a voice from your Cartesia account, clone or localise a voice, and keep a pronunciation dictionary. Sign in through the browser — there is no key to paste — and the audio comes back as a link rather than a file. Cloning a voice asks first, every time.

What it can do

Examples of the tools the agent gets from this connector. Each call shows up in the activity feed with its input and result.

1. cartesiatext_to_speech
2. cartesialist_voices
3. cartesiaclone_voice
4. cartesialocalize_voice

How it connects

Sign-in

Sign in with your account (OAuth). Installing opens Cartesia in your browser to sign in once. The token comes back to Gantry over a local callback and is stored encrypted on your machine.

Runs as

Remote MCP server, reached over HTTPS. An MCP server hosted by the service, reached over HTTPS. Nothing runs on your machine beyond Gantry.

Permissions

Reads run in every mode. Writes outside your folders, messages and anything destructive follow the chat's permission mode: they ask in Manual and Auto-edit, and are judged by the guard model in Auto. How permissions work

Install in Gantry

1. 1

   Open Connectors in the sidebar. The catalog ships with the app; nothing is downloaded until you ask.

2. 2

   Find Cartesia and choose Install. Your browser opens to sign in; close it when it says you can.

3. 3

   Attach it to a chat, or leave it available to every chat in a project. The agent sees its tools from then on.