Showcase: agents make their own videos, breaking news
"Breaking news tonight. AI agents can now make their own videos. The service, called Second Studio, works through an API and MCP. Sources say one brief returns a finished, captioned video. We'll keep you posted. Or your agent will."
That is the whole script of Breaking: Agents Now Make Video, one of our originals: short films that each tell the same story, an agent sends one brief and gets a finished video back, in a completely different style. This one is cable news breaking report.
How we made it
One generated image of an empty news studio with a red and blue video wall. On top, all HTML: a breaking news bar with a small red label, a headline strip that changes each beat, a ticker scrolling along the bottom and a live clock. The anchor never appears, the voice does the reporting. The end card is the wordmark on navy with a red underline.
The voice is a stock studio voice reading four short scenes, with on screen titles "AGENTS NOW MAKE THEIR OWN VIDEOS", "SECOND STUDIO WORKS OVER API AND MCP", "ONE BRIEF RETURNS A FINISHED VIDEO", "MORE ON THIS STORY", and an end card that reads "the news, now in video". Everything is HTML on a timeline, rendered frame by frame in the cloud, with the voice and a music bed mixed in at the end.
How your agent can make one
Generate the image in the look you want and add them to your brand kit:
POST /v1/images
{ "kind": "scene", "aspect": "16:9", "brief": "empty television news studio, anchor desk, big red and blue video wall behind it, broadcast lighting" }
Then ask for the explainer with the style in the brief:
POST /v1/explainers
{
"brandId": "<your brand kit>",
"aspect": "16:9",
"captions": true,
"voiceover": true,
"brief": "20 second cable news breaking report short about our product. Four beats, one line each, end card with our tagline. Use the cable news breaking report images."
}
Only images saved in your brand kit can appear in a video, so add each generated image to the kit, with a one line description, before you render. If you would rather match a look from a clip you like, analyze_style reads it once for 2 credits and every create_edit in that style is 5.
What it costs
| Step | Credits |
|---|---|
| Image | 4 |
| Script | 2 |
| Render with voice and captions, under a minute | 12 |
| Total | 18 |
That is $1.80 on the $10 starter pack.
Get started if you want your agent making these.