DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to turn a topic into a narrated explainer video with Anything2 Explainer

Give an agent a topic and get a 1280x720 MP4 with voiceover, subtitles and chapter progress.

  • Top pick
  • Content
  • Intermediate
  • 3 hours
  • From the README
  • Claude Code
  • Codex

Who it is forA content creator or educator who needs a short explainer video on a technical topic and has no motion-graphics tooling.

The problemProducing a narrated explainer video by hand means sourcing facts, writing a script, recording voiceover, timing shots and animating each frame.

The outcomeA rendered H.264 MP4 with synchronized voiceover, subtitles, chapter cards and a bottom progress bar, plus the research doc, narration, storyboard and QC reports.

What you need first

  • Claude Code or Codex installed
  • Node 18 or newer
  • ffmpeg (brew install ffmpeg on macOS)
  • Python 3 with edge-tts 7.2.8, numpy, pillow and scipy (kokoro and espeak-ng only for English narration)
  • Several GB of free disk space (about 2 to 3 GB per the README)

Steps

  1. git clone https://github.com/Vincentwei1021/anything2explainer.git
  2. ln -s "$PWD/anything2explainer" ~/.claude/skills/anything2explainer (or ~/.codex/skills/anything2explainer for Codex)
  3. brew install ffmpeg, then create the Python venv and run pip install 'edge-tts==7.2.8' numpy pillow scipy
  4. In Claude Code or Codex, say: Make me an explainer video about <topic>.
  5. At checkpoint 1 choose the length and language; at checkpoint 2 sign off the narration before voiceover is generated.
  6. At checkpoint 4 review the first 30-second preview before the agents build the remaining shot groups.

Prompt for your agent

Using the anything2explainer skill in this repo, make a narrated explainer video about <topic>, in <language> and about <length> long. Stop at the four checkpoints for my approval. Verify that the final output is a 1280x720 H.264 MP4 with voiceover and subtitles, and that the research doc lists a URL for every number or claim.

Caveat. A full run takes roughly 1 to 3 hours of wall clock, mostly parallel build agents, so plan for it to run unattended for a while.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page