Soft Subtitles vs Burned-In: Why Our AI Dubs Now Ship a Separate SRT FileGenerating captions and dubbed audio from one reviewed script, and why that matters more than the export format. This week I shipped three updates to AI Video Translator: line-by-line review of translOct 21 · 6 min readpeters-tech-lab.hashnode.dev
Slicing a 30,000px Webtoon Without Cutting Speech Bubbles in HalfKorean webtoons are published as a single vertical strip. One episode can easily be 700 to 800 pixels wide and tens of thousands of pixels tall. That's a problem the moment you want to run it through Oct 7 · 6 min readpeters-tech-lab.hashnode.dev
The Indie Tech Stack 2026: How I Ship High-Traffic AI and Privacy SaaS Solo with Next.js 14 and Edge CachingFrom handling heavy AI computer vision pipelines to scaling global edge requests without a massive backend team: Here is the exact architecture I use to ship production-ready micro-SaaS apps solo. Whe1Sep 16 · 3 min readpeters-tech-lab.hashnode.dev
Engineering a Seamless 2D-to-3D Mesh Pipeline: Overcoming the Geometry BottleneckGenerative AI has evolved rapidly beyond text and 2D images, moving straight into spatial geometry. However, engineering a production-ready pipeline that transforms a flat 2D image into a structured, 1Jul 9 · 3 min readpeters-tech-lab.hashnode.dev
Under the Hood: Engineering a High-Throughput AI Video Translation & Voice Cloning PipelineMoving beyond basic API wrappers to solve context-aware video localization and native vocal fingerprint replication at scale. Hey developers, Video localization in 2026 is still fundamentally broken. 1Jun 22 · 3 min readpeters-tech-lab.hashnode.dev