AI Video Generation Workflow is an open-source, modular pipeline for reliable short explainer production. It turns a topic into a final MP4 through script generation, slide prep, TTS voiceover, subtitle timing from real audio durations, and FFmpeg rendering. Built for batch creation, stage-by-stage reruns, and consistent style across multi-video series.

Anima - OnBrand Vibe Coding — Design-aware AI for modern product teams.

Design-aware AI for modern product teams.

Hey Product Hunt! I’m Haolin, maker of AI Video Generation Workflow. I built this because pure text-to-video tools were hard to control for real production: output quality fluctuated, reruns were expensive, and voice/subtitle/scene sync was often off. So I designed a modular workflow that turns a topic into a final MP4: 1) script generation 2) slide preparation 3) TTS voiceover 4) subtitle alignment from real audio durations 5) FFmpeg rendering What makes it practical: - stable and repeatable output for multi-video series - rerun only failed stages instead of restarting everything - easier team handoff with clear artifacts and docs It’s fully open-source: https://github.com/haolinwang819... I’d love feedback on what to prioritize next: - Docker one-command setup - more TTS backends - local model adapters for lower cost Thanks for checking it out. I’ll be here all day to answer questions.