All you wanted to suggest

Sync books between devices of a single account

At the moment all dictionary words are exported to a single 'Smart Book' deck, regardless of language. This makes practicing the words harder as the different languages are mixed together. It would be nicer to export each language to its own deck.

Sync saved words between devices of a single account

I'd like to save some phrases or paragraphs to re-read in the future, further investigate about it, etc. This is a basic feature that almost every other book reading app has and I think I'd benefit greatly its overall user experience

Sometimes I also want to improve the original text, e.g. I download subtitles from YouTube that are not broken into sentences, there are only words but no punctuation marks. I would correct this while reading.

Function: -pause -back -forward -repeat original text significantly improves narrator, making use more comfortable, useful and enjoyable

Is it a way to redesign as to translate an entire paragraph not with a button, but with a gesture. For example, swiping across the text to the right - translating this paragraph, swiping to the left - pronouncing the paragraph.

I just have concerns as to whether or not the pricing model could be kept indefinitely without a raise of price in the future. In short how does the app limit and overusage of the AI tokens since everyone use case is different? Wouldn't it be a better approach to allow users to attach their own API token so even in the future case of an inevitable price increase on all generative AI services, users of this app wouldn't be affected by such and be double charged in the economy? I personally wouldn't mind paying a one time option to unlock the ability to attach own API key. Please take this into serious consideration!

Currently, Smart Book isn’t optimal for any language that lacks spaces. The problem is, without spaces the pop-up dictionary has no way to tell where words begin and end. There are tons of great tools out now for parsing these languages—but they would need to be implemented. I’ll discuss Japanese since that’s the language I know more about, but I’m happy for anyone who knows more about another spaceless language to chime in. Japanese is made of kanji (elaborate symbols that look like this, borrowed from Chinese: 蒜肥留) which are used for nouns and verbs, but we don’t know how they sound by looking at them. They’re read depending on what word they appear in. In addition to kanji, Japanese has two different syllabaries that look like this ひいよ and this ケムラ which are used for foreign loan words, for conjugations of verbs, as particles to mark grammatical functions, and more. These don’t represent ideas like kanji do, they represent sounds: usually a pairing of one consonant with one vowel sound. So ひ is the sound or syllable “hee” and の is “no.” の can be a particle indicating possession, so if 私 means me and 本 means book, 私の本 is “my book.” But at the end of a sentence it only adds an emotional tone to the sentence. And it can appear in words spelled fully in hiragana as well. Without a parser, the dictionary has no clue if it is or isn’t part of a word, conjugation, etc. If it appears in a word, the pop-up dictionary will treat it as if it were by itself and say it indicates possession. The dictionary isn’t so bad with kanji. So I suspect it might not be so bad for Chinese, where everything consist of hanzi and only hanzi. I’d love for a Chinese reader to chime in on this. But it’s almost useless with the hiragana (ひいよ) and katakana (ケムラ), and this makes it impossible to meaningfully parse sentences in Japanese. You can’t learn conjugations on the fly by reading Japanese like you can with Spanish, for example, because you can’t tell where the conjugation actually begins or ends. This is not a problem for an advanced reader of Japanese, but it’s an impossible hurdle for the beginner. Japanese readers mostly rely on other tools to read, but there isn’t any one particular reader that dominates, and I believe Smart Book could take over the market without much effort. If Kurs is interested in promoting Smart Book to Japanese learners, I would especially recommend talking to the owner of JPBD, another one man passion project and possibly the best single resource for Japanese. JPBD is an online dictionary that shows word frequency information and allows the user to create flashcard decks directly from the dictionary entry page. If Smart Book were to be implemented together with JPBD, this could make it the most powerful tool for reading in Japanese by far.

Problem 1: In addition to the fields already available in the dictionary (translations, context, type of speech etc) many users have long been requesting additional fields for a more complete description of the words and expressions (definitions, synonyms, conjugation, user comments etc). Solution: Implement regular text fields without auto-filling from external sources (translators). See pic 1. Problem 2: Due to the different formats for presenting the translations by different translators, as well as the variety of requests for META-data from individual users, it is absolutely impossible to fill in additional fields automatically. (For example, compare Google and Reverso translations). Solution: Using the standard clipboard of Gboard the user can copy those texts from the translator built into the dictionary that he/she considers necessary while switching to various translators (array in the bottom of the translator window) and then can distribute these saved texts from the clipboard into those fields in which it considers necessary. See pics 3 and 4. This is not an ideal solution, but it can be implemented by developers in the foreseeable time.

When we enter a word into the dictionary, mark it as unknown, choose option with showing unknown words further down the text - if the word is in a different form, or used in another part of speech - its translation and word are not displayed, as if we have not dealt with it before. If word could be added to the dictionary with all its (as far as possible) forms, it would be more useful for learning process and building up associations.

Currently in chinese/japanese you cant select to translate the last character of a row. Instead you need to select the first one of the next row. Thanks

Add the ability to read RSS news feeds just like books

Ability to specify gender and article when saving words to the dictionary

When user reads detailed answer from LLM, e.g. about definition of word with examples it would be useful to save it into Anki. The LLM's answer might be more clear than vocabulary article. But now we can only read and close this page.