Media generation

Let the model make a picture, a voice-over or a clip.

Built inMediaNo sign-in needed

The chat model calls a drawing, speaking or video model as one step of its work, and what comes back appears in the reply at that point — not as a link, not as a file on your disk. One call makes one thing, on the provider key you already added and at your own account’s price, and the result says which model answered and what it cost. Asks before every generation outside Auto.

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. mediagenerate an image
  2. mediaread this aloud
  3. mediamake a short clip
  4. medialist the models you can use

How it connects

Sign-in
No sign-in needed. No account and no key. Install it and it is ready.
Runs as
Built into Gantry. Part of Gantry itself, written in Rust. No runtime to install.
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 Media generation and choose Install. That is all.

  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.