Vibe Coding

This is another tab in my daughter’s media player. The last two posts were about an English song tab. This one is about English stories. The Need: The Stories Only Live on the Device We have a set of eight English picture books about a cartoon pig family. It comes with a small talking reader. The device has eight book icons down the left and right edges. You press a book icon, then press one of ten buttons in the middle, and it reads that page out loud. ...

This is part two. In the first post I turned 19 free English board books into a tab in my daughter’s media player. The tab worked. Then I used it with her for one evening and found three things that bothered me. The Need: Three Small Annoyances Every video started with a roughly 10-second channel intro and ended with a promo card for other videos. In a song tab, that is a jolt every time. My wife and I had agreed she shouldn’t watch video yet, but the tab played video by default. The lyrics and translation were below the picture. To read them I had to scroll. And my daughter doesn’t like it when “her” picture shrinks or disappears off the top of her phone. None of these is a big problem. All three would have stopped us using the tab. ...

I bought some picture books for my three-year-old on a Korean secondhand marketplace app. The seller added 19 English board books for free, as a bonus. I said thank you, took them home, and put them on a shelf. I had no idea how to use them, and she was too young for English anyway. That was a few months ago. This post is about how those books went from a shelf to a tab in her media player, and about the one thing that made it possible: I let the AI look at the books before I decided anything. ...

A transcript is a record of what a person said. If an AI “fixes” it into what the person should have said, it is no longer a record. I learned this on my own archive of Korean sermon recordings. The Need: Fix the Mistakes, Keep the Speaker Speech-to-text gets Bible words wrong. It writes a hardship word for a different hardship word, a town name as nonsense, a book of the Bible as another book. For a searchable archive, that matters, because people search for those names. ...

I like the idea of running my own AI. No bill, no data leaving my house. So when I needed to clean up a long transcript, I tried the local way first. The result changed my mind about when “free and local” is worth it. The Need: Speech-to-Text Gets Names Wrong Whisper turns a Korean sermon into text very well, but it makes a certain kind of mistake. It hears Bible words as ordinary words. A town name becomes a nonsense word. A book of the Bible becomes a different book. And one example I like: the Korean word for Psalms, sipyeon (시편), sounds almost like “ten pyeon” (10편). Whisper wrote “10” where the speaker said “Psalms”. ...

A transcript without speaker names is hard to use. If an audio file has two people talking, I need to know which words came from which person. My pipeline can label speakers automatically. The question was whether I could trust the labels. I did not want to trust them just because the output looked clean. So I made an answer key by hand, and I let the computer grade itself against it. ...

Most weeks, the work on my daughter’s media player is not coding. It is adding things she asked for. This is a small post about two such additions, because each one hit a snag, and the snags are the useful part. The Need: She Asks for a Song, and It Isn’t There Yet My daughter is three. She decides what she wants to hear, and the answer changes every week. If the player doesn’t have it, I need to add it in a few minutes, or the moment is gone. So adding content has to be boring and fast. ...

The Need: Every Verse Cost Me My Place I prepare short talks for a Bible study. My routine is simple. I read a passage in my Bible app, add the verses I want to my notes, and write a few lines under them. Then I go back to read the next verse. That last step was the problem. The app has one screen at a time. To read the next verse, I left the notes, opened the viewer, and found my place again. Sometimes the next verse was in a completely different book, so there was no place to go back to. Finding it again took longer than writing the note. ...

In the last Kids Player post, I made the matched song’s cover fill the whole screen after a voice search. It looked good. Then I used it for a week and found what it was missing. The Need: The Picture Stayed the Same While the Song Changed When a song ends, my daughter’s player moves to the next one. With normal tapping, the big cover changes with it. After a voice search, it did not. The new song played under the old picture. ...

This is a small bug with a nice reason behind it. I speak Korean, so I will explain the Korean part first. In a Korean Bible, most books are divided into 장 (jang, “chapters”). The Book of Psalms is the exception. Its sections are called 편 (pyeon), and people say “Psalms 23 pyeon”, not “Psalms chapter 23”. Both words are in normal use. A person might say either one, depending on habit. ...