I played with transliteration, which practically means that entering moskva will make the sounds-like feature suggest москва and vise versa (a source's response and possible transliteration is still up to just it, of course; I could augment queries with OR'd alternatives, but I'm wary of doing so since there are always some sources that respond badly).

I've played a little with other alphabets: Latin variants should already have started working, Greek can be and is already is half added, Chinese is fairly impossible, the Japanese kana would be doable but the kanji less so, abjads like Hebrew and Arabic won't work well unless I can find a way to even just roughly phonetically add the implied vowels on the fly (though since it makes the sounds-like server a little slower I won't add the features unless there is demand) and abugidas are a little more hopeless yet.

I could potentially add features like using literal-enough transliterations to make purely greek or purely cyrillic entries vaguely readable to non-natives/non-experts, but then again, if you have specific interest in the record you probably know either both the language and the script, or neither, in which case it won't help. Again, it's a possibile on user request.

Also, Andre Keyzer suggested a virtual keyboard to be able to mouse-click characters into input text fields and thereby not requiring users to have a specific keyboard or going through the trouble of configuring a keyboard mapping. I'll be looking into that later; there's some more basal work to be done right now, and another new feature I'm playing with I'll report on in a few days. Er, not that it isn't public yet:P (well, demo-login public)