Inspiration
What it does
How we built it
Challenges we ran into
Accomplishments that we're proud of
What we learned
What's next for Kirinuki Subtitle Studio
What I learned
Through this project, I learned to understand the limitations of AI and treat them as design boundaries rather than simply as obstacles. Within those boundaries, I was able to develop freely while deciding which tasks should be automated and which decisions should remain under human control.
I learned step by step how to detect speech, determine where sentences should be divided, combine Whisper results with VAD timing, and keep subtitles synchronized after video cuts. I then organized these capabilities into presets so that users would not need to understand every technical setting.
The application was also designed as a staged workflow. Instead of asking users to complete everything in one large operation, it guides them from video import and transcription through editing, preview, and final export.
What's next
Every time I use the application, I discover another improvement or a new idea. This has become a tool that grows through actual use rather than only through planning.
I want to continue developing Kirinuki Subtitle Studio while creating videos about the games, creators, and other subjects I enjoy. By using it to make videos about the things I care about, I hope to keep improving both the editing experience and the application itself.
Log in or sign up for Devpost to join the conversation.