Make Shorts, Reels and TikToks with those big word-by-word captions - from your own PC.

In this hands-on project you build a Python tool that takes a voice file and its word timings and renders a 1080x1920 vertical video: big captions with the current word highlighted, a title card, and your own background. No video editor, no subscription.

What you’ll build

• make_video.py: voice + word timings in, ready-to-post MP4 out
• A settings file for colours, font size and background
• Works with the AI Voice Maker’s output, or any audio plus an .srt subtitle file

What you’ll learn

• Installing ffmpeg, the free tool behind almost every video app
• How a video is really just many pictures shown quickly
• Keeping captions perfectly in sync with the voice
• Fixing the usual problems (ffmpeg missing, timings longer than the audio, file errors)

What you get

• A 12-lesson step-by-step course with real screenshots and frames
• The finished tool, a sample voice with word timings, a background image and a README

You need: Windows or Mac, about 200 MB of free space, and the free lessons What is the terminal?, What is Python? and What is a virtual environment? (links inside).

Time: about 30 minutes.