Naphat Tangpanitchakorn

My biggest personal project: a Thai-speaking AI VTuber, inspired by Neuro-sama. Karu listens to my voice and reads YouTube live chat, thinks in her own personality, then talks back with a cloned voice and a Live2D avatar. She can co-host with me or run a segment on her own. Her Thai still comes out clunky sometimes, and I improve her a little with every stream.

• ▸Real-time pipeline: speech-to-text (faster-whisper), a persona LLM, Thai voice-clone TTS (F5-TTS) with emotion tags, and Live2D lip-sync, all streamed through OBS
• ▸Memory system: embedding retrieval, pinned facts, and daily self-generated 'thoughts'
• ▸Fine-tuned a local LLM on a dialogue dataset I built by hand (QLoRA to GGUF, served with Ollama)

• Python
• PyTorch
• OpenAI API
• Ollama
• Q+LoRA
• F5-TTS
• faster-whisper
• Node.js

A storefront I built for a wooden furniture shop in Ayutthaya. Customers browse the catalog and pick what they like, and the buy button opens a chat with the shop's page. That's how this shop actually closes sales, so I built the site around their real workflow instead of forcing online payment into it.

• ▸Product catalog with categories, SKU search, and a ready-to-ship filter
• ▸Admin back office for adding products and promotions, with an overview dashboard

• Next.js
• React
• TypeScript
• Tailwind CSS
• PostgreSQL
• Prisma

A platform that runs in production with real paying customers. People register, top up with PromptPay, and buy usage hours for a desktop program I made. Running it taught me things a tutorial never could: when something breaks, a real customer messages me about it.

• ▸PromptPay QR top-up with hour packages, custom amounts, and full history
• ▸Admin console for users, staff, pricing, and online-user stats
• ▸Push program updates and kill-switch clients remotely from the web

• Next.js
• React
• TypeScript
• Tailwind CSS
• PostgreSQL

A desktop app for managing stock in a small shop or warehouse. Staff log in with their own roles, add products, and move stock in and out. Every change gets posted to the team's LINE chat right away, so the owner always knows what happened without opening the app.

• ▸Product and category management with SKU search
• ▸Stock-in / stock-out records for every movement
• ▸Admin and staff roles with full user management
• ▸LINE notification on every stock change

• Python
• Tkinter
• SQLite
• LINE Notify API

A bigger desktop inventory system that covers the whole warehouse side: suppliers, customers, products, storage locations, and staff, with inbound and outbound stock tracking on a local SQLite database.

• ▸CRUD screens for suppliers, customers, employees, products, and storage locations
• ▸Inbound / outbound records with quantity and unit price per line item
• ▸Activity log that keeps a timestamped record of every add, edit, and delete
• ▸Themed desktop UI (ttkbootstrap) in a master-detail layout

• Python
• Tkinter
• ttkbootstrap
• SQLite

IT Empowering Day 2026: In the Era of AI — Bangkok University

Smart Lab Management System — Pitching Round Finalist

May 21, 2026 · BU Diamond Hall ·

Our team was picked as one of the 10 finalists in the Industry-driven Innovation Project category and got to pitch on stage in front of judges from AWS, KBTG, and BorntoDev, competing for the Best AI Prototype for Real-World Impact award. I was the lead developer and built the whole system, then presented how we applied AI in it.

• ▸Face recognition for lab access, with anti-spoofing that tells a real face from a photo or a screen replay
• ▸Built the system end to end as the team's lead developer
• ▸Presented the prototype and our AI approach on stage during the pitching round