How the AI-made Transformer video works: EdgeTTS for voice, Remotion + KaTeX for visuals
dotey · x · 2026-09-26
dotey details the stack behind the AI-generated Transformer video: the model picked the open-source edge-tts (a reverse-engineered API for Microsoft Edge's TTS service, 12k stars on GitHub) for narration, Remotion (React/JS video framework) for rendering, and KaTeX for math formulas.
Related event: One Prompt, Claude Code Builds a 'What Is a Transformer' Video(3 posts)→
More from coding & agent
- A weekend vehicular combat game coded entirely by Claude with 25+ prompts — DamageHelpful9364 · 2026-09-26
- Claude Opus 5.5 renders a whole Mumbai heritage sunrise scene purely in code, no 3D models — CurieuxExplorer · 2026-09-26
- Fabric-RLM: Open-source Recursive Language Model harness brings MIT's RLM to Microsoft Fabric notebooks — PawarBI · 2026-09-26
- ChatGPT Pro user regrets switching from Claude: 'output never what I asked' — Honest_Abroad_5846 · 2026-09-26
- Experiment: feeding thoughts to a NousResearch agent all day, no laptop needed — CurieuxExplorer · 2026-09-26
- Claude optimizes 30+ biomolecular models in under 4 weeks; ScienceIDE opens agent-learnable science code — jiqizhixin · 2026-09-26