Launching a Tech Blog
· 4 min read
Introduction
This blog is the official technical blog of the Solbox Inc. SceneMakerAI project, which repurposes broadcast content using open-source AI technology.
SceneMakerAI Multimodal AI Pipeline Developer
View all authorsProject Introduction and Qwen 3.6 Application in the Broadcasting Domain
· 7 min read
Introduction
At a broadcast station, it takes several days for a professional editor to create a single “Character Roundup” video. To produce these for all five main characters in a 16-episode drama, it would take several weeks.
Sharing My Experience with Optimizing "faster-whisper" for Korean Speech Recognition
· 13 min read
Introduction
If you run faster-whisper large-v3 directly on Korean broadcast content, the subtitles do not appear as intended.
Voice Analysis Process and Results
· 7 min read
Introduction
This article provides a detailed explanation of the speech-to-text conversion process.
Building a RAG Pipeline
· 5 min read
Designing a Langgraph-Based Broadcast Workflow
· 7 min read
Introduction
This article details the LangGraph process for finding segments of broadcast clips using natural language queries.
Explanation of the Short-Form Video Auto-Generation Pipeline_1
· 16 min read
Introduction
This article details the specific process involved in taking a single episode of a drama and breaking it down into material suitable for short-form content.
Explanation of the Short-Form Video Auto-Generation Pipeline_2
· 21 min read
Introduction
In Part 1, I broke down Episode 10 of the SBS drama “Manager Kim” into dialogue and scenes. This article covers the period leading up to the actual release of the short-form version.
Implementation of the "View All" Service
· 10 min read
Introduction
This article outlines the process of creating a “one-line summary” from a compilation of scenes related to a single theme, selected from various episodes of a drama.
09_Best Practices for Optimizing Basic Inference in vLLMs
· One min read