A developer used Replit's AI integration to translate the Qubii app into Spanish and Mandarin in about 20 minutes for last-minute sponsors. They added a UI toggle for language switching and ran the translations through Claude to check quality before launch.
What? You've never done this before, right? So we did it in the car. I figured this was one that could be done on the phone and it was partially true. What'd you learn from the localization project to localize it into Chinese and Spanish? We had Repli do both of them, right?
Yeah, we had— I had them do both because, you know, I'm going to pick all the, like, top, like, obviously English is native because I built it in English. Then I was like, okay, I'm going to, I'm going to pick because this is becoming a frustration point because we have last-minute sponsors, we have multiples of them, or, you know, Native Spanish speakers, some of them are native Chinese Mandarin, you know, speakers. And I was like, okay, I wanna make this as seamless as possible for them to get up to speed. I can't do that, but Qubii could, right? So we were vibe coding the waymo and I said to Replit, hey, can you make a toggle so that you can translate everything I've put into Qubii so far into Spanish, Chinese, and then with the toggle they can switch from English to the you know, non-native languages that I don't know. And so it took it maybe 20 minutes 'cause there's, there's a lot of content in Qubi. And so it had to, you know, translate everything. It used, I think it used OpenAI for all the translations. And then after we got outta the car, you know, I, I, I took some screenshots and checked it with Claude to make sure nothing was inappropriate or weird with its translations.
What did Claude say about the translations?
It was pretty good.
Pretty good. Yeah. Yeah. So you, you ate it with Claude, you took screenshots of what, Replit built with OpenAI, and then you took screenshots to QA it into Claude to see if it thought that the translated app was, uh, was, was good enough.
Yeah, actually what I'm running now too in the background is I'm having Cowork just now run through all of it, just spot check, make sure nothing is weird. But now Cowork is doing the full thing. So that's, that's also an interesting learning
