Skip to main content
Version: 2.1.0

Supported languages

Speech to Text Model Language Codes

The reference for language codes used by the Phonexia and Whisper Speech to Text models is listed below.

To see, how language tags are created, visit this documentation page, which outlines the international standard utilized to establish consistent guidelines for language tagging.

Language NamePhonexia Model CodeWhisper Enhanced V2 Model CodeWhisper Enhanced V3 Model Code
Afrikaansafaf
Arabicarar
Arabic Gulfar-KW
Arabic Levantinear-XL
Armenianhyhy
Azerbaijaniazaz
Basqueeu
Belarusianbebe
Bengalibnbn
Bosnianbsbs
Bulgarianbgbg
Cantoneseyue
Catalancaca
Chinesezh-CNzhzh
Croatianhr-HRhrhr
Czechcs-CZcscs
Danishdada
Dutchnlnlnl
Englishen-USenen
Estonianetet
Finnishfifi
Frenchfr-FRfrfr
Galicianglgl
Georgianka-GE
Germande-DEdede
Greekelel
Gujaratigu
Hebrewhehe
Hindihihi
Hungarianhu-HUhuhu
Icelandicisis
Indonesianidid
Italianit-ITitit
Japanesejaja
Kannadaknkn
Kazakhkk-KZkkkk
Koreankoko
Latvianlvlv
Lithuanianltlt
Macedonianmkmk
Malaymsms
Marathimrmr
Maorimimi
Nepalinene
Norwegiannono
Nynorsknn
Pashtops
Persianfafafa
Polishpl-PLplpl
Portugueseptpt
Punjabipa
Romanianroro
Russianru-RUruru
Serbiansr-RSsrsr
Slovaksk-SKsksk
Slovenianslsl
Spanisheseses
Swahiliswsw
Swedishsv-SEsvsv
Tagalogtltl
Tamiltata
Telugute
Thaithth
Turkishtr-TRtrtr
Ukrainianuk-UAukuk
Urduurur
Vietnamesevi-VNvivi
Welshcycy