How to generate AI videos automatically using OpenClaw

OpenClaw is a self-hosted AI agent that connects to your messaging platforms and runs tools on your behalf. If you already use it for automation, you can use it to create videos with Program by giving it the Program context.

What you need

A Program account (free tier works)
The Program CLI installed (npm i -g @program-video/cli)
OpenClaw installed and running
An LLM provider configured (Claude, OpenAI, or any supported model)

Give OpenClaw the context

Copy the Program instructions below and paste them to OpenClaw in your preferred chat client — Telegram, Slack, WhatsApp, Discord, or the web dashboard. OpenClaw will use these to authenticate you, create projects, and build videos on your behalf.

SKILL.mdAdd this as a skill at ~/.openclaw/skills/program-video/SKILL.md

---
name: program-video
version: 1.0.0
requirements:
  exec: [npx]
---

You have access to Program (program.video), an AI video composition platform.
Use the CLI commands below to authenticate the user, manage projects, and build
video compositions.

## Getting Started

You can also copy the context by clicking the "OpenClaw" button on program.video.

Build a video

Send a message to OpenClaw through any connected channel:

You: Create a 30-second explainer video about our new API. Title card, three feature slides, and a call to action. Dark theme.

OpenClaw will:

Run auth login to authenticate you with Program

Create a new project via the CLI

Generate each scene as a React/Remotion component

Pass each scene to the CLI using addScene

Add voiceover with generateSpeech if you ask for narration

What a scene looks like

Each scene is a React component:

import { AbsoluteFill } from "remotion";

export default function TitleCard() {
  return (
    <AbsoluteFill
      style={{
        backgroundColor: "#0a0a0a",
        display: "flex",
        alignItems: "center",
        justifyContent: "center",
      }}
    >
      <h1 style={{ color: "white", fontSize: 72, fontWeight: 300 }}>
        Introducing the Acme API
      </h1>
    </AbsoluteFill>
  );
}

You never write this yourself. OpenClaw generates it from your description and passes it to the CLI.

Tips for better results

Be specific about timing. Tell OpenClaw how long each scene should be and the total video length.
Describe visual style upfront. Say "dark background, white text, minimal" in your first message.
Iterate scene by scene. Ask OpenClaw to read the composition, then adjust individual scenes.
Use the desktop app for preview. The Program desktop app gives you a live preview as scenes are added.
Use from any device. Since OpenClaw connects to messaging platforms, you can start a video from your phone and refine it on desktop later.

Rendering

Once your composition is ready, open the Program desktop app or web editor to preview and render.

On the desktop app, rendering happens locally on your hardware. No cloud queue, no upload wait.

What comes next

This workflow is powerful for teams. Anyone with access to your OpenClaw instance can create videos through their preferred messaging platform. Build a template once, then let anyone on your team produce variations by sending a message.

For more on the CLI, see the documentation. For OpenClaw setup, see the OpenClaw docs.

How to generate AI videos automatically using OpenClaw

What you need

Give OpenClaw the context

Build a video

What a scene looks like

Tips for better results

Rendering

What comes next

More articles

How to generate AI videos automatically using Claude Code

How to generate AI videos automatically using Codex

How to generate AI videos automatically using OpenCode