http://whatlanguageisthis.com/
Since the language analyzer is becoming one of the most used web services that I run, the other day I was thinking that it would be cool get it its own domain (and a .com domain costs just 50 SEK (around 850 yen in normal times) anyway). So I was thinking about what domain name to get – that isn’t already taken – and well, one of the most common search phrases people use to find the language analyzer is “what language is this webpage/blog/text/whatever” and luckily whatlanguageisthis.com was available, so there it is! I think it’s quite easy to remember and very easy to tell people. 4 stars out of 5, perhaps? Pretty good.
Setting up the new site was pretty easy; it’s essentially just a php script that chdirs into the language analyzer directory and continues from there as before.
I also did another nice update: the data file that the app uses to identify the language is now downloaded after the page and all the application javascript files have loaded. That means the page should load much faster, and the user can start reading the instructions or entering text while the data is being downloaded in the background. If the user clicks “Go” before the data file is downloaded, it will stop and wait, while displaying a typical web 2.0-ish loading indicator.
I’m planning to add support for more languages soon, and improve identification of similar-looking languages even further. Anyway, here’s the url for the new site again:
http://whatlanguageisthis.com/
hi
loved the website and its results. How about sharing code.
Gabiing malinaw
madulom ang tanan
gawas lang sa Batang Hesus
nga gibantayan man nila
sa langitnong kalinaw
nia'ng Mesiyas karon.
this is silent night in cebuano, Philopino language.
The Program suggest tagalo, Philipino language, i.e. very near, but not exactly. ???
Hi, Cebuano is currently not supported, but I'll add it in the next update (some time after New Year). Thanks for providing the sample text!
Tried entering simple Bangla phrases transliterated in English.
I LOVE YOU = Ami tomate bhalobashi.
I DON'T SPEAK BANGALI = Ami Bangla janna na.
The system said it was Bosnian… Does it only pick up Bengali when written in the native characters?
Jc
Jc,
Yes, unfortunately transliterated texts are not supported (as mentioned on the about page). If writing Bangla using latin script is common then I'll certainly add support for it, but I cannot find a reasonably large source of Bangla texts written in latin characters…
Thank you – Thank you!! Wonderful tool, very easy to use.
It seems a hard work for this widget to tell Chinese character. I tried to paste some Chinese character, and the result is always "unknown".
add on to firefox see lot of people using that but still very good site /software
is there an email address where i can send mr. falck a picture to see if he can identify the language in it? It's a small piece of writing, but so far i have had absolutely no luck identifying it. Thank you.
a. nahnemus,
Please send it to f [at] lck . nu (i.e. my last name falck with the a replaced by @ and add .nu)
If I can't recognize it (which is quite probable) I'll put it on whatlanguageisthis.com and ask the visitors for help. I'm sure someone will know!
USEFUL WEBSITE.THANK YOU
great site ! thanks
Thanks!
天下邮,个人邮件,企业邮件,免费邮件,收费邮件,G邮局,超大附件,863智能反垃圾,个性化邮箱.
Can anyone tell me what language this is?
That's Chinese. I don't know why the identifier doesn't recognize that sentense… it should be easy. I'll look into it.
A spell check would make this site awesome!
Nice tool. Tried to see if it can identify Chinese and Arabic togeather. And it returned Arabic. I think would be more intresting if it can recognise mixed languages. Do you offer any APIs.?
Anonymous,
Thanks! There is support for identifying mixed texts, but in this case I suspect the amount of Arabic outweighed the Chinese by too much.
I am currently working on offering different APIs, so please stay tuned…
how can i translate Malay to English? specifically "ngiyazi ukuthi keng le oyingwetseng mo"
can you provide a RESTful API to this? lots of developers could use it – including me
Francis, sorry I don't know of any Malay-English translation tool…
eddotnet5000,
The resulting app should follow the REST principles since there's not really any state to represent anyway, I think.
thnx Henrick, ecco un bel sito di recente ho scoperto che mi è stato utilizzato per tutto il resto. http://www.nicetranslator.com/ un altro sono i problemi con l'Esperanto, che è affascinante per me. (la lingua, non il problema!)
This is a great tool! Thanks for putitng it together. It has been extremely useful to me!
Thanks a lot for your encouraging words!
It was really great !
well done !
Hi, Very nice and it does a great job every time. Do you have a API for using this from a web service or is the code available from you. It would be nice if many people can use this in their applications.
Hi
Can anyone translate this for me?
como stas muchachito? ya me operaron do pie todo bien….stoy estudiando el lunes empiezo la escuela besitos..claro k me acuerdo! todo bien, ya stoy operada…todo bien
Thank you! This site is excellent! =]
wow this was really helpful thx so much
Thank you very much. Have Stefan Zweig biography of Balzac written in this language.
Henrik, Thanks so much for this web app. It's great. Keep up the good work buddy
Thanks a lot, Serge, pigeon toes, and everyone!
i posted "La 18 ani e cam devremw sÃ-pi faci griji pentru vÃrsta ta"
and it tranlated as Bosnian, or possibly croatian or serbian. My hunch is that it could be Aramanian. I would like to learn it but there is not much support around for it. your thoughts? i can post more if you like. my keyboard does not support all the letters and such so it's tough.
commoncents,
Thanks for your comment. I agree that the language is Romanian. However, it's a bit garbled (encoding problems?) and misspelled ("devremw" should be "devreme", I think).
Romainian is supported by whatlanguageisthis.com… could you try again with the text correctly encoded and spelled? If that doesn't work, then please do let me know, so that I can improve the support for Romanian.
this is so helpful! thank you!
really cool program, im going to bookmark it
language name not showing properly
Anonymous, could you please tell me what web browser software (name and version) you're using? I've heard this before but I can't reproduce it. I test the site in various versions of IE, Firefox, Chrome, and Opera…
It rocked!
Karl …Thank you so much man…I was able to impress some friends of mine who challenged me to find which language a piece of text belonged to…..
Hi, Henrik. This app is just fantastic. I've needed it for my entire virtual life (which is what? Like 14 years-old now) and I'm glad I finally found it. I'm sure you'll have conditions to improve it and I wish you the very best!
Thanks for your website it helped identify a hacker. good health to you.
hi,
i am doing research on languages as part of my degree, i stumbled across this website and love it!!! but i have only one query….how does the program identify what language has been used? does it use some sort of algorithm or does it just compare sections against a database of languages?? thanks
Hi Phil, I’m glad to hear you like the site. It’s a combination of analyzed and refined data and algorithms. Since the program runs in the browser the data needs to be very small, since it’s downloaded (otherwise the site would be slow). If it ran on the server, a large database could be used and I believe that in that case it would be much simpler to develop the algorithms, similar to how google’s language identification works; by just comparing the input to a huge database. So my software uses small, refined data with only the statistically significant (not meant in a scientific way; I’m an engineer and do things by intuition) data about each language. I’ve then hand-written a lot of algorithms to improve the results from the statistical analysis. Well that’s about it… it’s the result of years of trying out what works best, essentially.
hi, me again
This seems very complex. first of all, what do you mean by statistically significant data? And also… In what way do your algorithms improve the results obtained?
Only reason i am so curious is due to the fact that i am hoping to use some of the results gained from this website in a presentation and need to provide details upon how it all works???
Thanks!!!
Phil, by “statistically significant” I mean that I have refined the data on each language down to only the bits that sets it apart from other languages. For example, “-ing” is a common word ending in English, but it’s also common in the other northern European languages, so while it’s a good indicator that the language might be English, it’s not very useful when trying to identify for certain. I have written algorithms to improve the results when identifying very similar languages (such as the Scandinavian ones, Bosnian/Serbian/Croatian/Slovak, Dutch/Afrikaans, etc, still no luck with Indonesian/Malay tho). Feel free to email me if you have further questions, I would also be interested in your presentation. My email address is on the upper right at http://henrikfalck.com/ (to avoid spam, it’s not a link and it’ll be backwards if you copy-paste it).
Phil, by “statistically significant” I mean that I have refined the data on each language down to only the bits that sets it apart from other languages. For example, “-ing” is a common word ending in English, but it’s also common in the other northern European languages, so while it’s a good indicator that the language might be English, it’s not very useful when trying to identify for certain. I have written algorithms to improve the results when identifying very similar languages (such as the Scandinavian ones, Bosnian/Serbian/Croatian/Slovak, Dutch/Afrikaans, etc, still no luck with Indonesian/Malay tho). Feel free to email me if you have further questions, I would also be interested in your presentation. My email address is on the upper right at http://henrikfalck.com/ (to avoid spam, it’s not a link and it’ll be backwards if you copy-paste it).
Thankyou very much!!!!
I will be sure to email you a copy of it as soon as I am finished!!
Once again thankyou, you’ve been very helpful!
Thanks
… it’s not working for me…
Nadia, what web browser and version are you using?
The last few times I’ve tried to use the What Language Is This website when I paste my entry into the box I get the following message:
LOADING DATA, PLEASE WAIT…
I’ve let it run for over 10 minutes but it does not go to the next step.
Hi Shelly, it should definitely not take more than a couple of seconds to load the data. What web browser (and version) are you using?
hi, nice tool, why it cant identify korean?
this string : 네이버 :: 세상의 모든 지식, 네이버
taken from website title of Naver.com
“Etiam non eros at nisi euismod dignissim vel malesuada elit”
Which is found from more searching is actually mostly Latin resolved to Tagalog in this search. It doesn’t seem close at all. Does your site support Latin? Also, could you show a relevancy list rather than a single result. Anyway, nice site tho.
Joshua, yeah Latin isn’t currently supported as it’s not often found on the net. I’d like to add it some time though. For some reason, unknown languages often end up being classified as Tagalog. I guess Tagalog just looks like an average language.
It would be good to show the encoding as well.
Your language detection tool seems to be good. Have we the chance to be able to create a .net library ?????
this fuckin sucked gave me the wrong language and i failed my test
Apparently, images are not supported, which doesn’t help me, since most of the language characters I need to identify are in image format. Google Chrome doesn’t support all characters encoded in different languages and Windows doesn’t support Chinese at all, so in order to see them, they have to be image files.
It would be useful if a person could simply type in a URL, the way you can with Tin Eye or What the Font.
Awesome! Thank you…
hello! thanks for letting me know the language… btw, can’t translate it to english
Hi,
do you have an API for your service? I loved this and I really needed something like that for a project I’m about to start.
“Tere, vana sôber! Kuidas käsi käib?” – Your website announces: This language iss Slovenia (possibly Croatian or Serbian”. WRONG!!! It’s in Estonian that is not even close to those suggested Slavic languages! (Estonian belongs to Finno-Ugric languages)
I tried again: “Tere, inimene! Mis tuju sul täna on?” – your website: “The language is Bosnian”. WRONG! It’s ESTONIAN!
Thank you for providing example sentences. I will improve the recognition of Estonian.
Frickin’ amazing!!!
I think you should be able to just put a single word or small phrase in. That would be very helpful.
hey dear thanks….i badly needed it…
Hi,
I’m using IE 9 on a Windows 7 system. The site is not working for me. When i copy pasted the “Etiam non eros at nisi euismod dignissim vel malesuada elit” from one of the comments here itself, a “Loading” message keeps rotating. I’m not getting result.
If i use firefox, i get results almost in couple of seconds.
I want to ,noew what nlanuage this messade was written
———- Forwarded message ———-
From: Linda Scott
Date: Wed, Jun 22, 2011 at 10:30 AM
Subject: Really Happy and very excited
To: Anas Elattar
what language was used for message;
from:linda scott
Date: Wen, jun 22,2011 at 10:30 AM
identify thje lanhuage
http://whatlanguageisthis.com/
חיר עיוני? שו אלסירה? אבל כל שי יעטיקי אלעאפייה
I recenly tried to use this site to find out what language my friend speaks but everytime I type in something like “dostora vacation to shesh hoye ashlo… vacation ta jotil katse…ak hon sudhu clg e ferar chinta…k harap lagtese… bohut moja korsi” I get either tagalog or something else then whatever languges it told me I went to googletranslate,that laungauge….then the sentence to english it did not work:( tryed it many times diff sentence and diff language……and nothing…….if any1 knows this language do no hesitate to reply: ) Ty!!!
òîâà òè a̎ í a̎îáõî a̎èìî
I recently tried to translate in google and your page the preceeding caption (from a movie I am downloading).
The nearest translation available was Afrikaans (the symbol a̎ is a translator’s blip, it is a with ” on top), that translated the untouched portion of the sentence as “your eyes” in english and spanish.
If any luck, please e-mail me the correct answer.
Sincerely yours
Gonzalo
Հարավային Կորեա, պաշտոնապես հայտնի որպես Կորեայի Հանրապետություն (կորեերեն՝ 대한민국) — պետություն Արևելյան Ասիայում, որը զբաղեցնում է Կորեական թերակղզու հարավային մասը։
I put this paragraph in and it said Korean, which it’s not.
This is an awesome website i it.
Henrik: Tried several times to have a short sentence identify the language so I can then have it translated but your program was either too busy or isn’t currently available for users.
Hi!
I’m doing a touch of research on the page http://hmar.in/hmar/gospel-centenary-lawm
to get an online translation but I can’t even get the language recognised yet. Your page tells me it is cebuano, but I doubt it.
Take care! And above all relax and have fun!
thanks for tool you’re a great man!
can you apply in your tool the all languages in the world?
Look at this its 2012 and your still getting comments, Id like to say Thank You for a job well done and helping others,
Even though I couldnt workout what my bit of text was Im still grateful to you. x
1.Îòêëþ÷èòüñÿ îò èíòåðíåòà è ó ñòàíîâèòü ïðîãðàììó.
como stas muchachito? ya me operaron do pie todo bien….stoy estudiando el lunes empiezo la escuela besitos..claro k me acuerdo! todo bien, ya stoy operada…todo bien
SHOULD ACTUALLY BE:
¿Cómo estás muchacha? Ya me operaron dos pies todo bien…. Estoy estudiando lunes empiezo a la escuela besicos…. ¡claro que me acuerdo! Todo bien, ya mi operada…todo bien.
IS: Spanish, TRANSLATION:
How are you girl? Since I had surgery of my two feet, everything’s been all good…. I am studying Monday starting at the basic school…. Of course I remember! It’s all good, since my operation…all good.
—
Now that I got that tick out of the way, I’m not so happy with the translator. It decides EVERYTHING is Filipino/Tagalog, or Cebuano, whereas it is actually Spanish, German, Italian, English, etc. It’s a novel idea but it’s just horrendously inaccurate.
Example:
“Yo fui al mercado ayer con mi mejor amiga.” – Spanish
Translation:
“I went to the market yesterday with my best friend.”
What it decided:
Tagalog (Filipino)
What it would actually be in Tagalog:
“Nagpunta ako sa merkado kahapon sa aking pinakamatalik na kaibigan.”
Spanish looks NOTHING like Filipino…I suggest you fix this bug!
If you had a “like” I would have shared this on FB.
Thank you! We had narrowed the possibilities down to German or Dutch through Swedish and Norweigan friends. It is German.
If you had a “like” I would put this over Google Plus.
Doesn’t recognise Welsh or Gaelic.
I noticed, I can’t get a result using Internet Explorer, but when I use FireFox, I get a result instantly and the result is always right.
I think most people think the Top Results Right Now
is where the answer is. I notice many people say the site said the language they entered was Tagalog, but I think they are looking at that list. I initially thought that was a list of possible languages as I think many other do. It’d be good to clear that up.
Try this article in detector: http://www.cnn.com/2012/06/08/tech/blind-spot-mirror-patent/index.html
It says the language is: Tagalog (Filipino).
I too have I.E. for my browser with Windows 7. I typed in Jesus est codamne a mort and the translator is still spinning around “loading.” Tentative top picks were Tagalog (Filipino), Bosnian, Spanish, Croation, or German. Way wrong, except for Spanish also being a romance language. It’s simple French, as you probably know. Translation: Jesus is condemned to death (Title of First Station of the Cross). Why does it not translate with I.E.?
yo me voy pa mi casa esto pinta muy mal
Mr Falck, I found that this is Spanish, but wlit.com was giving filipino. HOPE IT HELPS !
I loved it. . . this is the one good and helpful tool for me
You need Tibetan.
can anyone help me? i can’t write the characters because i don’t know how to write them i have a photo of the piece of paper and i wonder if somebody can help me to find out what kind of language is this? thanks
මහණෙනි, පරීක්ෂා කිරීමේ බලය කවරේද? මහණෙනි, මෙලොව ඇතැමෙක් මෙසේ පරීක්ෂා කරයි. (කෙසේද?) කාය දුශ්චරිතයාගේ ලාමකවූ විපාකය වනාහි මේ ආත්ම භාවයෙහිද, පරලොවෙහිද වේ. වාග් දුශ්චරිතයාගේ ලාමකවූ විපාකය වනාහි මේ ආත්ම භාවයෙහිද, පරලොවෙහිද වේ. මනො දුශ්චරිතයාගේ ලාමකවූ විපාකය වනාහි මේ ආත්ම භාවයෙහිද, පරලොවෙහිද වේය කියායි. හෙතෙම මෙසේ නුවණින් සලකා බලා කාය දුශ්චරිතය හැර කාය සුචරිතය වඩයි. වාග් දුශ්චරිතය හැර වාග් සුචරිතය වඩයි
please add this language too. This is called Sinhalease, using in Sri Lanka
የመድሓንት ሽያጭ (identify)
Takes Bashkir language for Bulgarian.
i wrote something in dutch and it said it was african!!!!
So excited to know of this site. Most helpful and interesting. Thank you!
Very interesting site, but it often gets languages wrong. Last example: “Rrëmben 4 persona: Dua një picë dhe një” (it’s supposedly Albanian but whatlanguageisthis.com concludes it’s Italian)