←back to thread

313 points mariano54 | 1 comments | | HN request time: 0s | source

Hey HN, we're Mariano and Anton from ISSEN (https://issen.com), a foreign language voice tutor app that adapts to your interests, goals, and needs.

Demo: https://www.loom.com/share/a78e713d46934857a2dc88aed1bb100d?...

We started this company after struggling to find great tools to practice speaking Japanese and French. Having a tutor can be awesome, but there are downsides: they can be expensive (since you pay by the hour), difficult to schedule, and have a high upfront cost (finding a tutor you like often forces you to cycle through a few that you don’t).

We wanted something that would talk with us — realistically, in full conversations — and actually help us improve. So we built it ourselves. The app relies on a custom voice AI pipeline combining STT (speech-to-text), TTS (text-to-speech), LLMs, long term memory, interruptions, turn-taking, etc. Getting speech-to-text to work well for learners was one of the hardest parts — especially with accents, multi-lingual sentences, and noisy environments. We now combine Gemini Flash, Whisper, Scribe, and GPT-4o-transcribe to minimize errors and keep the conversation flowing.

We didn’t want to focus too much on gamification. In our experience, that leads to users performing well in the app, achieving long streaks and so on, without actually getting fluent in the language you're wanting to learn.

With ISSEN you instantly speak and immerse yourself in the language, which, while not easy, is a much more efficient way to learn.

We combine this with a word bank and SRS flashcards for new words learned in the AI voice chats, which allows very rapid improvement in both vocabulary and speaking skills. We also create custom curriculums for each student based on goals, interests, and preferences, and fully customizable settings like speed, turn taking, formality, etc.

App: https://issen.com (works on web, iOS, Android) Pricing: 20 min free trial, $20–29/month (depending on duration and specific geography)

We’d love your feedback — on the tech, the UX, or what you’d wish from a tool like this. Thanks!

Show context
999900000999 ◴[] No.44388955[source]
It would probably be better to pick one or two languages, actually work with native speakers to make sure it's right.

These "we cover every single language" tools get it like 75% right at best.

replies(1): >>44389217 #
55555 ◴[] No.44389217[source]
I disagree because of how AI is progressing and because there's tons of neglected language markets they can pick up. Obviously your approach can work too, perhaps better. But 95% of language learning tools don't support Thai (my target language) for example so I am an eager user for that reason alone. I think they'll be able to make a generalized curriculum and have the AI use it in all languages.
replies(3): >>44389273 #>>44389492 #>>44390873 #
adastra22 ◴[] No.44390873[source]
Most of the generalized curriculum stuff out there is crap because languages differ from each other in substantial ways. LLMs in principle should help here as they can use their knowledge of the structure of the language to modify, but we're just not there with context windows and thinking capabilities. They will need at least a per-language (ideally per language pair) system prompt that contains a rough outline of the curriculum.
replies(1): >>44394326 #
55555 ◴[] No.44394326[source]
I think the curriculum areas you're referring to are for learners in the beginning and intermediate stages. In which case, fair enough, although I still think you could get pretty far by just prompting an LLM, as the LLM has read hundreds of books teaching how to learn each language. But that's not really my point; my point is that once you're an advanced learner (they claim this is their target market) who knows about 12,000 words, I think you know almost all of the grammar, and the remaining bits will get picked up along the way effortlessly via immersion. What you need help with in this stage is slogging through the next 10,000 vocab words you need to learn to get to extreme fluency or the next 25,000 you need to learn to become plausibly native-level, as well as the speaking and reading practice to make your reading faster (if it's a different character set to your native language) and make your speaking effortless.
replies(1): >>44394687 #
adastra22 ◴[] No.44394687[source]
At that point why engage with an LLM? Just go read a book.
replies(1): >>44395109 #
1. 55555 ◴[] No.44395109[source]
Probably too long of an answer, but: averaged out over the months, I spend 30 minutes every weekday doing flashcards, 45 minutes with a tutor, and spend another 1.25 hours watching TV or reading books in my target language. With 2.5 hours every weekday on average and without life immersion (at your home or office) it's possible to get to reading/writing/speaking/understanding fluency (including in terms of speed) in a difficult language in about 3-4 years and near-native in another 2 years. It's very difficult as an English native to learn a language like Chinese, Japanese, or Thai. It's not like learning Spanish or French (which I have also studied). To answer your question directly, surprisingly, reading a book does very little to help your speaking or understanding abilities. The skills of understanding accents/pronunciations quickly enough and the skill of structuring sentences when speaking quickly enough are completely different skills. Writing/reading/speaking/understanding are four remarkably unrelated skills that must be trained separately. Actually, typing on a keyboard and writing by hand are also different. Because thai actually has a different keyboard on desktop vs phone, since it became good enough, I decided to simply use speech to text for the rest of my life. I'm remarkably fluent in comprehension and have read quite a few adult books and yet if you give me a pencil and paper my brain can't figure out how to spell a word that I can easily say or type. And why use an LLM instead of a tutor? To save $2,700 a year.