Academa
Long-form STEM lecture videos generated by LLMs
Details
- External ID
- 49503421
- Source
- HN
- Company
- —
- Product
- Academa
- Website domain
- academa.ai
- Launched
- Aug. 30, 2026
- Cohort
- —
- Upvotes
- 30
- Upvotes percentile
- 0.8084677419354839
- Tags
- —
- Fetched at
- Sept. 10, 2026, 5:31 a.m.
- Updated at
- Sept. 10, 2026, 5:31 a.m.
Description
Hi HN, we are Sina Atalay and Abdullah Geduk, co-founders of Academa. We are both PhD students.We thought: what if lecture videos were written as code and compiled into video using computer graphics and TTS?Then LLMs could write them, and lectures could be fixed with code edits instead of video production.On correctness: LLMs may make mistakes. But these videos are code sitting in our repository, and we can maintain them. Every report and review becomes a fix in the source, and everyone who watches after that gets the corrected lecture. Every recorded lecture on the internet is stuck with its mistakes. Ours will continuously improve.Each video also comes with an AI chat that understands everything said and shown in the lecture.There is a longer write-up at the bottom of the page.Happy to answer any questions.
Enrichment
- Theme
- video transcription and extraction tools
- Vertical
- Education
- Function
- Content generation
- Audience
- B2C
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- ai-generated stem lecture videos
- Manually corrected
- False
Could you build this?
Partial While prompting an LLM to generate Manim scripts or Remotion code alongside TTS is vibe-codeable, reliably synchronizing complex STEM math animations, pacing, visual clarity, and rendering 25-minute coherent video lectures requires complex custom orchestration pipelines.
What it would actually take: The stack needs an LLM planning agent that decomposes academic topics into scripts and code-based animation descriptions (e.g., Manim or custom WebGL/Canvas renderers), coupled with a programmatic TTS pipeline and an automated video compilation engine (like FFmpeg on worker clusters). The core challenges are dynamic timing synchronization between synthesized speech and animations, handling compilation errors in generated graphics code autonomously, and maintaining visual pedagogical coherence over long multi-chapter videos. This requires a robust distributed rendering worker architecture and fine-tuned code-generation/verification loops for mathematical visualization.
Discussion
20 comments analyzed.
Competitors mentioned: Khan Academy, Coursera, 3Blue1Brown videos, Manim, arXiv
Concerns raised: Flat voice and even word spacing cause listener fatigue and zoning out, Lecture description language kept proprietary, limits transparency and reproducibility, Videos start mid-sentence and end abruptly (technical bugs), Poor narrative setup and problem framing in explanations, Missing interactivity and ability to ask live questions to instructors
Feature requests: Publish the lecture description language and source code, Improve speech synthesis to better match pedagogical emphasis and pacing, Add real-time interactive Q&A with expert instructors, Better problem setup and narrative context before introducing constraints, Implement version control/git history for tracking lecture improvements and errata
Competitors
Other products that read as similar to this one — 37 launches clear the similarity bar, closest 8 shown.
Attention rank: #9 of 38 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 302 days after the earliest competitor.
- How LLMs Work · hn · 2026-04-24 · 245 upvotes · similarity 0.41
- Open Computer-Animated Multivariable Calculus Course in 6 Languages · hn · 2026-01-25 · 5 upvotes · similarity 0.39
- CoursifyYT · ph · 2026-09-30 · 1 upvotes · similarity 0.35
- I built a Free "Masterclass" from YouTube clips · hn · 2025-11-07 · 6 upvotes · similarity 0.35
- Turn any topic into a 3Blue1Brown-style video · hn · 2026-01-10 · 5 upvotes · similarity 0.34
- Fixing LLM memory degradation in long coding sessions · hn · 2025-11-27 · 5 upvotes · similarity 0.34
- I successfully failed at one-shot-ing a video codec like h.264 · hn · 2026-04-04 · 9 upvotes · similarity 0.34
- impol.dev · ph · 2026-09-26 · 2 upvotes · similarity 0.34
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a content generation tool for Government yet.