Show HN: Get conversational practice in over 20 languages by talking to an AI

How do we send you money? I saw it mentioned on the site, but didn't really see a way to do so, or I either missed it.

Duolingo, Mango, Babbel, blah blah other language learning apps / software runs anywhere from $2.99 to $14.99 a month.

Live tutors / lessons vary greatly, but Babbel Live is $75 to $150 a month depending on what length of time you're willing to pre-pay. For in-person one-on-one lessons, I've seen a price of $10 an hour on iTalki for a Spanish professor in Medellín, Colombia to instruct you. If you figure 1-2 hours per week, that's $40 - $80 per month, and that'd be considered a "light" load.

While writing this, it did occur to me that your app / AI / ML model / whatever label you want to put on it will put a lot of tutors out of business (as how you do compete with a natural language model that's available 24/7?), but I think the overall good to humanity is worth it, and as always, the cream of the crop will rise to the top anyway.

What's your long-term plan with Quazel? There's no wrong answer here, insofar as I'm personally concerned. "I want to make enough money to quit my day job by leveraging this into a SaaS offering.", "I want to sell out for $50 million ASAP and go live on a small yacht in the Caribbean.", "I want to hit a billion dollar valuation in 6 months and totally reinvent language learning.", "I just wanted to improve the way we learn languages online, bro..." They're all good goals to me, I'm just curious what sparked this.

Hahah I have a super silly response for this one: It's simply because we have not gotten around to translate the UI and everything into other languages besides english. That's why we simple assume people know english, since they need to be able to know at least some english to use it. But it's high on our to-do list.

the AI giving you paid ads as part of normal conversation has a taste of dystopia to it, but I don't think it's creepy IFF the user is made aware of it beforehand. Definitely include an option to pay and remove ads if you go this route.

Also possibly concerning, is the financial incentive to push conversations into areas where the ads are discussed. People dont always talk about consumer goods, but with the ad model you might have the situation where AI keeps bringing them up anytime it is remotely relevant. turning conversations into commercials, and missing opportunities for learning generic words by replacing them with named brands.

You: "Hi how are you?"

AI: "Thanks to my Frosted Flakes and cup of Folgers that I bought from ShopRite this morning, I am feeling great! Have you tried Frosted Flakes?"

Reality: "I'm good, you?"

that said, there could be some value in seeing brands you recognize around the words they represent (like saying "frosted flakes cereal" above instead of just "frosted flakes") since the context will help you remember what the generic words mean.

Also dont underestimate the issues you might have getting Brands on board with this. you are asking them to give you permission to use their brand name in conversations that they cannot approve of in advance. that's very tricky too

I tried using it in Portuguese and it's cool but it seems very off, just a huge number of things that don't sound even remotely natural or idiomatic. But when I click the translate button, the English translation is a perfectly reasonable thing to say.

SO... I'm highly suspecting that, behind the scenes, the "real" conversation is happening in English, and it's translating in both directions. Which is always going to be fairly disastrous, particularly with short snippets of conversational text. (In contrast, machine translation does best with long sentences of highly technical writing.)

So the concept is very intriguing, but the problem is that it needs to rely on native language models per-language. (Or if it already is, then those models need a vastly better or larger training corpus.)

So A+ for proof of concept, but I'd never recommend anybody practice with this in order to learn/practice a language, because with the quality where it is, it will make you a worse speaker -- not better. The things it says are just too weird.

Yes, there are also millions of lonely elderly who would love to speak to someone.