GT4T now supports translations between 309 languages!

GT4T has updated to support all the languages MT engines support, making the total number languages to 309! Yes, 14 MT engines, 309 languages, endless language pairs.

The MT engine that supports most number of languages is probably niutrans.com. It supports 304 languages.

I used to think big companies like Google or Miscrosft are the best and when a Chinese MT provider provides many languages, I immediately think that they might buy or use data from either Google or Microsoft.

But no, translations from niutrans.com are different and neither Google nor Microsoft provides that many languages. And the translation quality is pretty good too. Here are my calculations.

name: Google Neural, Number of languages: 105
name: Microsoft Translator, Number of languages: 77
name: Youdao, Number of languages: 111
name: Yandex, Number of languages: 33
name: Google Phrase Based, Number of languages: 105
name: DeepL Pro, Number of languages: 14
name: Baidu, Number of languages: 26
name: Tencent, Number of languages: 16
name: Sogou, Number of languages: 61
name: CloudTranslation, Number of languages: 15
name: NiuTrans, Number of languages: 304
name: Systran, Number of languages: 46
name: TradooIT, Number of languages: 2
name: Papago, Number of languages: 9

All languages that GT4T supports:

const allSupportedLan= {
knj: ‘Acateco’,
ace: ‘Aceh’,
acr: ‘Achi’,
acu: ‘Achuar’,
adh: ‘Adhola’,
af: ‘Afrikaans’,
any: ‘Agni Sanvi’,
duo: ‘Agta Eastern Cagayan’,
agr: ‘Aguaruna’,
ake: ‘Akawaio’,
sq: ‘Albanian’,
amk: ‘Ambai’,
am: ‘Amharic’,
amu: ‘Amuzgo’,
ar: ‘Arabic’,
hy: ‘Armenian’,
cpb: ‘Ashéninka’,
aym: ‘Aymara’,
az: ‘Azerbaijani’,
azb: ‘Azerbaijani South’,
bdh: ‘Baká’,
ptu: ‘Bambam’,
bam: ‘Bambara’,
bqj: ‘Bandial’,
bno: ‘Bantoanon’,
bsn: ‘Barasana’,
bfa: ‘Bari’,
bch: ‘Bariai’,
bba: ‘Bariba’,
ba: ‘Bashkir’,
eu: ‘Basque’,
be: ‘Belarusian’,
bem: ‘Bemba’,
bn: ‘Bengali’,
ber: ‘Berber’,
bi: ‘Bislama’,
bus: ‘Bokobaru’,
bnp: ‘Bola’,
bs: ‘Bosnian’,
br: ‘Brezhoneg’,
bg: ‘Bulgarian’,
my: ‘Burmese’,
bqp: ‘Busa’,
cjp: ‘Cabecar’,
cak: ‘Cakchiquel’,
cni: ‘Campa’,
kbh: ‘Camsa’,
yue: ‘Cantonese (粵語)’,
ca: ‘Catalan’,
ceb: ‘Cebuano’,
ccp: ‘Chakma’,
cha: ‘Chamorro’,
che: ‘Chechen’,
chr: ‘Cherokee’,
ny: ‘Chewa’,
cbl: ‘Chin Bualkhaw’,
cfm: ‘Chin Falam’,
cnh: ‘Chin Hakha’,
ctd: ‘Chin Tedim’,
czt: ‘Chin Zotung’,
chq: ‘Chinantec’,
‘zh-py’: ‘Chinese Pinyin’,
‘zh-cn’: ‘Chinese Simplified’,
‘zh-tw’: ‘Chinese Traditional’,
cdf: ‘Chiru’,
cv: ‘Chuvash’,
cop: ‘Coptic’,
co: ‘Corsican’,
hwc: ‘Creole English Hawai’i’,
ht: ‘Creole Haitian’,
crs: ‘Creole Seychelles’,
hr: ‘Croatian’,
cs: ‘Czech’,
mps: ‘Dadibi’,
da: ‘Danish’,
dik: ‘Dinka’,
tbz: ‘Ditammari’,
dv: ‘Divehi’,
dtp: ‘Dusun Central’,
nl: ‘Dutch’,
dyu: ‘Dyula’,
dz: ‘Dzongkha’,
en: ‘English’,
enx: ‘Enxet’,
eo: ‘Esperanto’,
et: ‘Estonian’,
ee: ‘Ewe’,
fo: ‘Faroese’,
fj: ‘Fijian’,
fil: ‘Filipino’,
fi: ‘Finnish’,
gur: ‘Frafra’,
fr: ‘French’,
fy: ‘Frisian’,
fuv: ‘Fulfulde Nigerian’,
gd: ‘Gaelic Scottish’,
gbi: ‘Galela’,
gl: ‘Galician’,
krs: ‘Gbaya’,
jy: ‘Georgian’,
de: ‘German’,
gof: ‘Goffa’,
gbo: ‘Grebo Northern’,
el: ‘Greek’,
gub: ‘Guajajára’,
gnw: ‘Guaraní Western Bolivian’,
gu: ‘Gujarati’,
hlb: ‘Halbi’,
ha: ‘Hausa’,
haw: ‘Hawaiian’,
he: ‘Hebrew’,
hi: ‘Hindi’,
hmn: ‘Hmong’,
huv: ‘Huave San Mateo del Mar’,
hui: ‘Huli’,
hu: ‘Hungarian’,
is: ‘Icelandic’,
ify: ‘Ifugao Antipolo’,
ifb: ‘Ifugao Ayangan’,
ifa: ‘Ifugao Central’,
ig: ‘Igbo’,
ikk: ‘Ika’,
id: ‘Indonesian’,
ga: ‘Irish’,
it: ‘Italian’,
izz: ‘Izi’,
jac: ‘Jakalteko’,
ja: ‘Japanese’,
jv: ‘Javanese’,
kac: ‘Jingpho’,
kab: ‘Kabyle’,
keo: ‘Kakwa’,
xal: ‘Kalmyk-Oirat’,
kn: ‘Kannada’,
kpg: ‘Kapingamarangi’,
cki: ‘Kaqchikel’,
xsm: ‘Kasem’,
pss: ‘Kaulong’,
kyu: ‘Kayah Western’,
ka: ‘Kazakh’,
kk: ‘Kazakh(Cyrillic)’,
kbo: ‘Keliko’,
km: ‘Khmer’,
quc: ‘Kiche’,
kg: ‘Kikongo’,
rw: ‘Kinyarwanda’,
gil: ‘Kiribati’,
rn: ‘Kirundi’,
jmc: ‘Kisiha’,
‘tlh-Latn’: ‘Klingon Latin’,
‘tlh-Piqd’: ‘Klingon Piqd’,
ko: ‘Korean’,
ksd: ‘Kuanua’,
kle: ‘Kulung’,
ku: ‘Kurdish’,
kmr: ‘Kurdish Northern’,
ky: ‘Kyrgyz’,
lsi: ‘Lacid’,
lo: ‘Lao’,
la: ‘Latin’,
lv: ‘Latvian’,
lcp: ‘Lawa Western’,
ln: ‘Lingala’,
ond: ‘Lingao’,
lt: ‘Lithuanian’,
ngl: ‘Lomwe’,
lg: ‘Luganda’,
dop: ‘Lukpa’,
lnd: ‘Lun Bawang’,
lb: ‘Luxembourgish’,
mdy: ‘Maale’,
mk: ‘Macedonian’,
mad: ‘Madurese’,
mg: ‘Malagasy’,
ms: ‘Malay’,
ml: ‘Malayalam’,
mt: ‘Maltese’,
mam: ‘Mam’,
map: ‘Mam Northern’,
mni: ‘Manipuri’,
mbb: ‘Manobo Western Bukidnon’,
gv: ‘Manx’,
mi: ‘Maori’,
mrw: ‘Maranao’,
mr: ‘Marathi’,
mhr: ‘Mari’,
mrj: ‘Mari Hill’,
mah: ‘Marshallese’,
yua: ‘Maya Yucatec’,
mo: ‘Mongol’,
mn: ‘Mongolian Cyrillic’,
me: ‘Montenegro’,
mos: ‘Mossi’,
meu: ‘Motu’,
hmo: ‘Motu Hiri’,
tih: ‘Murut Timugon’,
muv: ‘Muthuvan’,
nhg: ‘Nahuatl’,
ntm: ‘Nateni’,
djk: ‘Ndyuka’,
ne: ‘Nepali’,
no: ‘Norwegian’,
nop: ‘Numanggang’,
nyy: ‘Nyakyusa’,
ojb: ‘Ojibwa’,
or: ‘Oriya’,
bdu: ‘Oroko’,
om: ‘Oromoo’,
os: ‘Ossetic’,
otq: ‘Otomi Queretaro’,
pck: ‘Paite’,
pap: ‘Papiamento’,
ps: ‘Pashto’,
ata: ‘Pele-Ata’,
fa: ‘Persian’,
pl: ‘Polish’,
poh: ‘Poqomchi’’,
‘pt-pt’: ‘Portuguese’,
‘pt-br’: ‘Portuguese Brazil’,
pot: ‘Potawatomi’,
pa: ‘Punjabi’,
kek: ‘Qeqchi’,
quz: ‘Quechua Cusco’,
quh: ‘Quechua South Bolivian’,
quw: ‘Quichua’,
qxr: ‘Quichua Cañar Highland’,
rmn: ‘Romani’,
ro: ‘Romanian’,
rug: ‘Roviana’,
ru: ‘Russian’,
spy: ‘Sabaot’,
ssx: ‘Samberigi’,
sm: ‘Samoan’,
sg: ‘Sango’,
‘sr-Cyrl’: ‘Serbian’,
‘sr-Latn’: ‘Serbian Latin’,
st: ‘Sesotho’,
shp: ‘Shipibo’,
sn: ‘Shona’,
jiv: ‘Shuar’,
sid: ‘Sidamo’,
sd: ‘Sindhi’,
si: ‘Sinhalese’,
ssd: ‘Siroi’,
sk: ‘Slovak’,
sl: ‘Slovenian’,
so: ‘Somali’,
es: ‘Spanish’,
swp: ‘Suau’,
su: ‘Sundanese’,
sw: ‘Swahili’,
sv: ‘Swedish’,
syc: ‘Syriac’,
shi: ‘Tachelhit’,
ty: ‘Tahitian’,
tg: ‘Tajik’,
tmh: ‘Tamajaq’,
ta: ‘Tamil’,
tpm: ‘Tampulma’,
tt: ‘Tatar’,
crh: ‘Tatar Crimean’,
te: ‘Telugu’,
tex: ‘Tennet’,
teo: ‘Teso’,
tet: ‘Tetun’,
th: ‘Thai’,
ti: ‘Tibetic (བོད་སྐད།, 藏语)’,
tig: ‘Tigre’,
tpi: ‘Tok Pisin’,
to: ‘Tongan’,
cas: ‘Tsimané’,
tn: ‘Tswana’,
iou: ‘Tuma-Irumu’,
lcm: ‘Tungag’,
tr: ‘Turkish’,
tk: ‘Turkmen’,
tyv: ‘Tuvan’,
tw: ‘Twi’,
udm: ‘Udmurt’,
uk: ‘Ukrainian’,
ppk: ‘Uma’,
ur: ‘Urdu’,
usp: ‘Uspanteco’,
uy: ‘Uyghur’,
uz: ‘Uzbek’,
ve: ‘Venda’,
vi: ‘Vietnamese’,
vun: ‘Vunjo’,
prk: ‘Wa’,
wlx: ‘Wali’,
war: ‘Waray’,
wrs: ‘Waris’,
wsk: ‘Waskia’,
cy: ‘Welsh’,
wal: ‘Wolaytta’,
wol: ‘Wolof’,
xh: ‘Xhosa’,
ts: ‘Xitsonga’,
jae: ‘Yabem’,
ii: ‘Yi (ꆈꌠꉙ, 彝)’,
yi: ‘Yiddish’,
byr: ‘Yipma’,
pil: ‘Yom’,
yon: ‘Yongkom’,
yo: ‘Yoruba’,
dje: ‘Zarma’,
za: ‘Zhuang (壮)’,
zyb: ‘Zhuang Yongbei (邕北壮)’,
zu: ‘Zulu’
};