AI videos with Claude Code for beginners: 11 prompts, $0.62

Description and use

Automated creation of a 101‑second narrated video using Claude Code, OpenAI, and Gemini for $0.62 without installing libraries or a video editor.

Problem

Creating AI videos without installing libraries, platforms, or video editors, while keeping costs low.

Outcome

The author built a fully automated AI video pipeline in about an hour, producing a 101‑second narrated space story for $0.62, with no manual library installation or video editor required.

Workflow

• Create an empty folder and start a fresh Claude Code session.
• Generate three API keys (OpenAI, Gemini, and a third if needed).
• Store keys securely (e.g., macOS Keychain).
• Teach Claude Code to generate images with OpenAI GPT‑Image 2.5 by providing API key, docs, and a test prompt.
• Ask Claude Code to create a skill named gpt‑image for future reuse.
• Repeat for a second image model (Nano Banana 2.1) with its API key and docs, creating a nano‑banana skill.
• Generate a test image with each model to compare results.
• Teach Claude Code to generate voices and music using chosen APIs, creating corresponding skills.
• Use FFmpeg skill to edit the generated assets into a 101‑second narrated slideshow.
• Run the full pipeline to produce the final video and record costs in costs.csv.
• Review the output and iterate if needed.

Evidence

I start in an empty folder with a fresh Claude Code and teach it to make images, voices and music, and to edit them with FFmpeg. At the end it makes a 101-second narrated space story.

Source

We build a slideshow. A short story, a voice reading it, and images that change as the story goes.

Source

It took about an hour of work. No libraries to install by hand, no platforms, no video editor.

Source

a costs.csv that says we spent $0.62

Source