I also jumped out of the funnel and had this “I got tricked” feeling after selecting the story parameters. I’m someone who would use this, too. But I’m not giving you my personal information unless I can see what it does.
You don't have to confirm your email address there. Just enter something random.
That's usually what I try on sites like this, when it doesn't work just close the tab and move on.
I know it’s a friction, but we were (maybe still are) a bit paranoid of abuse or bot attacks, as we are using a paid api to roll this thing. One suggestion others gave was to show stories generated by other users, I think that might work. What do you think?
Why not offer a whole library of stories generated by other users that have been reviewed by a human and deemed good?
I'm the target audience for this app, but I don't really want to generate my own stories; I want to read. Generating stories is just additional work for me, and I don't know how good the story is before I generate and read it. If I had access to a library of human-reviewed stories, I'd just read those, knowing that they are at least okay. You wouldn't even have to review them yourself; you could have a system for users to rate stories.
You're selling this as an AI product, but I don't care about AI. I care about learning a new language by reading stories.
Have beginner and intermediate examples (1 page) available. Also helps show what the real UI looks like. Because the current tiny demo UI is probably not the real one, not sure?
Also, pricing is not mentioned anywhere on the start page or before signup
Yes, consider something like letting the user keep track of "minutes reading" or "word points" after generating a story as the point where you log them in.
There has to be user value to login or nobody will do it.
My best friend and I had been trying to learn Dutch for a while. About a month ago, we picked up some Donald Duck books in Dutch, thinking they'd be fun and simple to start with. But soon enough, we found ourselves constantly switching between the book and our phones, struggling to follow the story—definitely not the immersive experience we had hoped for...
That’s when I remembered those books with one language on one page and the translation on the opposite page. Inspired by that concept, I thought, why not use AI to create something similar, but even more interactive?
So, we built DuoBook.
Here's how it works:
1) Start writing your story in your language.
2) Select the language you want to learn.
3) AI helps complete the story, side-by-side with your native language.
It’s still early days, and it might not be perfect, but it's genuinely helping us—and we hope it helps you too!
At least with German Donald Duck the language used there is.. special in a good way. The early translator Erika Fuchs devised a whole new variant of German that:
- uses words and phrases that are either of rare historic origin or completely made up new ones
- verb forms so uncommon that verb form she used frequently (the Infliktiv) has a second inofficial name: the Erikativ
- she frequently borrowed from the biggest writers and poets in the German language in her translations
- for the younger figures there is an entirely made up youth slang that is both appealing and incredibly entertaining to read
The english originals are utterly boring to read in comparison. Her work has a literaric and entertainer quality of the kind that made generations realize there is no real border between serious high brow literature and comics.
Hey! I'm also learning Dutch and trying it out. A couple of things I discovered. For reference, I'm a native English speaker and speak Dutch at a B2~ level but my reading vocabulary is probably closer to B1.
The "long" story is not that long. I was expecting something closer to 1000 words or more. Using your Donald Duck example, I doubt the long story was more than 4 or 5 comic book pages. I started with the magic mushroom example, intermediate difficulty, and long length.
I also generated another story using the "lost puppy" prompt, but this time advanced difficulty and long. The difficulty was ramped up which I appreciate, but the length was even shorter than before!
The speech synthesis is garbage, but I'm sure you already know that. For a free service (for now), I understand why some limitations are in place, but it doesn't look good for your product unless you're targeting beginners. I'm not sure what you're offering is useful to anyone above that level. 3 stories per day for me is about 10-15 minutes on advanced (including the generation waiting time).
I wish you luck with the project! Imo, your time is best spent now optimizing your spend so you can provide higher quality audio to go alongside the text. I'm sure you will have plenty of content generated, but surfacing that to users without it feeling icky might also be a challenge.
Nice job. I'd recommend "publishing" some bilingual books that have already been made on the platform as a better pattern for discovery since content creation requires signing up.
This is such an amazing idea and I would pay for it right now as finding text for A1-A2 is virtually impossible if your language is not incredibly popular
At first I had trouble coming up with an idea for a story. I think it could use more examples. I chose "Ayn Rand gets added to Mt Rushmore" and it made a nice story about it. The next one I might try is "Dingoes permitted as pets around the world". Basically anything you can imagine. I like the vocabulary quiz. I did Spanish and it had a new word and a couple that I'm fuzzy on, and that was useful practice.
Edit: Year of Linux on the Desktop is another.
Edit 2: For Year of Linux on the Desktop it did 2024 as that year. Might want to add the current date to the prompt and say that to have stuff imagined in the future be after that. Another thought is to have the LLM suggest a story prompt for you.
Related is Prismatext, which intermixes the new language into the text of a book in your native language, so you get in-place, contextual learning of the new language:
I built something like this for my own personal language studies about a decade ago called "Kindle Swap". You fed it an ebook in ePub/MOBI format along with a list of known vocabulary and it would sprinkle them into the book so you could read it on your Kindle at your leisure later.
But, please focus on 3 or 4 languages. Do those well.
Asian languages ( apparently Cantonese isn’t on the list ) are very hard to machine translate.
As is this is just Chat GPT + AWS Translate + AWS Text To Speech. Along with Firebase for user management and a very nice UX front end.
To turn this into a product I’d select maybe 3 languages, French , Spanish, German and hire advisors for all 3. Work on creating a few stories edited by your advisors and add basic gamification/quizzes.
Tried this with my native language. Many errors. Probably because the language is only spoken by 20 million people (Sinhala). Suggestion: ability to highlight one word and have its translation highlighted. Could catch errors like the one I encountered: "A robot lives alone on Mars" got translated to "A robot was born alone on Mars"
Sorry to hear that. Do you think we should exclude it then? I think highlighting the word is second most requested feature so far. Thank you for the feedback!
Highlighting the word is extremely cool. Using these examples as feedback into the system ("how did the translation do?"), and letting users provide feedback that you can improve your model on with this feedback loop would be ideal.
Whenever i am in a new country, i hit the first bookstore in the city centre. Child section often has disney books or similar. Sometimes even bilingual versions. I recommend it.
No idea how to order my food, but if i ever need to find my son, who's a clownfish, and was kidnapped, and i need to do it in italian, i am ready.
For Japanese specifically I made an iOS/macOS native app for learning by reading. It curates a library of RSS feeds and some books rather than generating them with AI because there are still issues with the naturalness of LLM-made Japanese writing. I've found many learners are still apprehensive of using generated content.
To calibrate the content to your reading level, rather than generating the content, it tracks your comprehension and shows you how much of a given webpage or book you already understand.
It has optional Anki integration if you don't want to use the built-in ones. I work on this full-time now and am about to launch a manga reading mode, plus Netflix caption lookups.
Readit News
As is, I jumped out of the funnel already.
I'm the target audience for this app, but I don't really want to generate my own stories; I want to read. Generating stories is just additional work for me, and I don't know how good the story is before I generate and read it. If I had access to a library of human-reviewed stories, I'd just read those, knowing that they are at least okay. You wouldn't even have to review them yourself; you could have a system for users to rate stories.
You're selling this as an AI product, but I don't care about AI. I care about learning a new language by reading stories.
Also, pricing is not mentioned anywhere on the start page or before signup
2. Make it available for all (major) languages.
3. Profit!
Also, integrate with captcha + rate limit to prevent abuse. Authentication alone is not strong enough deterrent to a motivated adversary.
- You could look at running a locally hosted model. There are some good story writing ones, albeit unsure for languages.
- Help visitors generate example stories for language pairs on your website ... if a language pair already has one, maybe show a pre-existing one.
.. if it's a new language pair being tested, inform the user it may be shared with others to let them see how the system works?
There has to be user value to login or nobody will do it.
Dead Comment
That’s when I remembered those books with one language on one page and the translation on the opposite page. Inspired by that concept, I thought, why not use AI to create something similar, but even more interactive?
So, we built DuoBook.
Here's how it works:
1) Start writing your story in your language.
2) Select the language you want to learn.
3) AI helps complete the story, side-by-side with your native language.
It’s still early days, and it might not be perfect, but it's genuinely helping us—and we hope it helps you too!
Check it out: duobook.co
- uses words and phrases that are either of rare historic origin or completely made up new ones
- verb forms so uncommon that verb form she used frequently (the Infliktiv) has a second inofficial name: the Erikativ
- she frequently borrowed from the biggest writers and poets in the German language in her translations
- for the younger figures there is an entirely made up youth slang that is both appealing and incredibly entertaining to read
The english originals are utterly boring to read in comparison. Her work has a literaric and entertainer quality of the kind that made generations realize there is no real border between serious high brow literature and comics.
The "long" story is not that long. I was expecting something closer to 1000 words or more. Using your Donald Duck example, I doubt the long story was more than 4 or 5 comic book pages. I started with the magic mushroom example, intermediate difficulty, and long length.
I also generated another story using the "lost puppy" prompt, but this time advanced difficulty and long. The difficulty was ramped up which I appreciate, but the length was even shorter than before!
The speech synthesis is garbage, but I'm sure you already know that. For a free service (for now), I understand why some limitations are in place, but it doesn't look good for your product unless you're targeting beginners. I'm not sure what you're offering is useful to anyone above that level. 3 stories per day for me is about 10-15 minutes on advanced (including the generation waiting time).
I wish you luck with the project! Imo, your time is best spent now optimizing your spend so you can provide higher quality audio to go alongside the text. I'm sure you will have plenty of content generated, but surfacing that to users without it feeling icky might also be a challenge.
One term for this is "Parallel Text" (https://en.wikipedia.org/wiki/Parallel_text).
Cool idea! I've been thinking about learning German - I'll have to give this a try.
Does it highlight the matching words?
And, we don’t have language alignment yet. Still, it highlights some of the “hard” words.
We were thinking about a pricing page with few pro options. For instance, longer text generation, access to better LLMs, or much better TTS etc.
Edit: Year of Linux on the Desktop is another.
Edit 2: For Year of Linux on the Desktop it did 2024 as that year. Might want to add the current date to the prompt and say that to have stuff imagined in the future be after that. Another thought is to have the LLM suggest a story prompt for you.
https://imgur.com/a/nTbBgdJ
https://prismatext.com/
https://specularrealms.com/projects/kindle-swap
But, please focus on 3 or 4 languages. Do those well.
Asian languages ( apparently Cantonese isn’t on the list ) are very hard to machine translate.
As is this is just Chat GPT + AWS Translate + AWS Text To Speech. Along with Firebase for user management and a very nice UX front end.
To turn this into a product I’d select maybe 3 languages, French , Spanish, German and hire advisors for all 3. Work on creating a few stories edited by your advisors and add basic gamification/quizzes.
I like the idea though
No idea how to order my food, but if i ever need to find my son, who's a clownfish, and was kidnapped, and i need to do it in italian, i am ready.
To calibrate the content to your reading level, rather than generating the content, it tracks your comprehension and shows you how much of a given webpage or book you already understand.
It has optional Anki integration if you don't want to use the built-in ones. I work on this full-time now and am about to launch a manga reading mode, plus Netflix caption lookups.
https://reader.manabi.io