Use Facecast with your AI

Facecast has no built-in AI. Your own AI, Claude, ChatGPT or Grok, works with Facecast through Geenius OS: it writes a script in the three layers, reads your kept recordings and their chapters, captions your screenshots and saves studio Looks. A person records, in a browser.

Connect it#

Add Facecast to your Geenius OS workspace and connect your AI to Geenius OS once, by the steps in the Geenius OS docs. Your AI then has a tool called geenius_facecast.

How a call looks#

The tool takes a tool (the area), an action (the verb) and args.

List the scripts

{ "tool": "scripts", "action": "list", "args": {} }

Your first ask#

A first ask

Use Geenius OS and my Facecast account. Write a five-minute script for a product demo in three parts, with a # topic per part, two or three bullets under it and the spoken paragraph. Save it and give me the record link.

Your AI saves the script and gives you a link. You open it, read it as topics, bullets or full text, and record.

The tools#

Tool	What it is for	Actions
`scripts`	Teleprompter scripts	`create` `delete` `list` `read` `update`
`recordings`	Kept recordings	`chapters` `list` `read` `usage`
`shots`	Screenshots	`delete` `list` `update`
`looks`	Looks	`create` `delete` `list` `set_default` `update`

Ask for the actions of an area with action: "help", and for one action's arguments with action: "help" and of.

Habits that work#

Write all three layers. A # topic per part, two to four points under it, then the spoken paragraph. You can then read as topics, bullets or every word.
Set the pace. wpm is 60 to 260; the default is 140. Count your words and divide to know how long the take runs.
Caption after the take. shots update takes a note and a star, and recordings chapters gives you the lines for a video description.
Save a Look once. looks create keeps a studio setup you can open again.

What your AI cannot do#

It cannot record, and it cannot change or delete the recording file. It cannot make a picture or a voice: Facecast records you.