Make a narrated 3D explainer video with a team of coding agents

A creator had Claude Code agents on Fable 5.2 write every scene of a 55-second 3D explainer as Remotion code, with voice and captions, in 2 hours 25 minutes of unattended work.

Done withClaude Code· Nov 18, 2026

What they did

The author wanted a short vertical video on why cola tastes different from glass, cans and plastic bottles. They wrote notes first: the script, a shot-by-shot order, the voice style and the look they wanted. Then they sent one short paragraph to a single Claude Code session, with every agent on Fable 5.2, and told it to run to the end without stopping. The session split the shots with one agent per scene, fact-checked the script, generated the voice, wrote word-by-word captions, reviewed the plan, built each scene in 3D as code and rendered it to MP4 with Remotion. It all ran inside a folder of format instructions the author had written ahead of time.

How it went

The run took 2 hours 25 minutes from the first log line and produced a finished 55-second video with 3D bottles, condensation, foam, molecule animations, narration and captions. The fact check found no false claims, the render check found no empty or frozen frames, and the run ended with a list of what it still doubted. It used 167.8M tokens, 95 percent of them cache reads, which would be about $158 at API prices but was covered by a Max plan. The author still wants a watch-through with sound, sound effects and tighter timing in one scene.

Worth knowing

The time spent writing the notes and the instruction folder is not in the 2 h 25 min, and the author sells that folder as a product. Since most tokens are the project re-read each turn, lock the script before scenes are built. All checks were made on stills, not on the moving video. The voice was billed separately by an unnamed provider.

Try it

With Claude Code· 4 parts to fill in

Make a [length]-second vertical explainer video about [topic] from my notes in [folder]. Plan the shots first and check the plan against the script before building anything. Fact-check every claim in the script and list any you doubt. Generate the narration with [my voice tool], then write captions timed to each word. Assign one subagent per scene to build it as Remotion code, matching the look described in the notes and timing each change to the word that names it. Render the opening first and check its frames for blank or frozen moments, then render the full video. Stop and show me the MP4 and a list of anything you are unsure about.

Square brackets are the parts to fill in. The prompt is ours; the story is theirs.

Where they said it

Related