This page shows which languages are supported by the AssemblyAI API, their language_code values, and the features available for that language.

AssemblyAI offers two different classes of speech-to-text models: Best and Nano.

Below, you’ll find the supported languages for each class of models, as well as instructions on how to change the language for your transcription.

Supported languages for Best

LanguageLanguage CodeStatusSpeaker LabelsCustom VocabularyCustom SpellingMultichannel TranscriptionFiller WordsAutomatic Language DetectionAutomatic Punctuation and CasingExport SRT or VTT Caption FilesExporting Paragraphs and SentencesProfanity FilteringWord SearchPII Text RedactionPII Audio RedactionDetect Important Phrases and WordsContent ModerationTopic DetectionSentiment AnalysisSummarizationAuto ChaptersEntity DetectionReal-Time Streaming Transcription
Global EnglishenLive
Australian Englishen_auLive
British Englishen_ukLive
US Englishen_usLive
SpanishesLive
FrenchfrLive
GermandeLive
ItalianitLive
PortugueseptLive
DutchnlLive
HindihiLive
JapanesejaLive
ChinesezhLive
FinnishfiLive
KoreankoLive
PolishplLive
RussianruLive
TurkishtrLive
UkrainianukLive
VietnameseviLive

Supported languages for Nano

LanguageLanguage CodeStatusSpeaker LabelsCustom VocabularyCustom SpellingMultichannel TranscriptionFiller WordsAutomatic Language DetectionAutomatic Punctuation and CasingExport SRT or VTT Caption FilesExporting Paragraphs and SentencesProfanity FilteringWord SearchPII Text RedactionPII Audio RedactionDetect Important Phrases and WordsContent ModerationTopic DetectionSentiment AnalysisSummarizationAuto ChaptersEntity Detection
Global EnglishenLive
Australian Englishen_auLive
British Englishen_ukLive
American Englishen_usLive
SpanishesLive
FrenchfrLive
GermandeLive
ItalianitLive
PortugueseptLive
DutchnlLive
AfrikaansafLive
AlbaniansqLive
AmharicamLive
ArabicarLive
ArmenianhyLive
AssameseasLive
AzerbaijaniazLive
BashkirbaLive
BasqueeuLive
BelarusianbeLive
BengalibnLive
BosnianbsLive
BretonbrLive
BulgarianbgLive
BurmesemyLive
CatalancaLive
ChinesezhLive
CroatianhrLive
CzechcsLive
DanishdaLive
EstonianetLive
FaroesefoLive
FinnishfiLive
GalicianglLive
GeorgiankaLive
GreekelLive
GujaratiguLive
HaitianhtLive
HausahaLive
HawaiianhawLive
HebrewheLive
HindihiLive
HungarianhuLive
IcelandicisLive
IndonesianidLive
JapanesejaLive
JavanesejwLive
KannadaknLive
KazakhkkLive
KhmerkmLive
KoreankoLive
LaoloLive
LatinlaLive
LatvianlvLive
LingalalnLive
LithuanianltLive
LuxembourgishlbLive
MacedonianmkLive
MalagasymgLive
MalaymsLive
MalayalammlLive
MaltesemtLive
MaorimiLive
MarathimrLive
MongolianmnLive
NepalineLive
NorwegiannoLive
Norwegian NynorsknnLive
OccitanocLive
PanjabipaLive
PashtopsLive
PersianfaLive
PolishplLive
RomanianroLive
RussianruLive
SanskritsaLive
SerbiansrLive
ShonasnLive
SindhisdLive
SinhalasiLive
SlovakskLive
SlovenianslLive
SomalisoLive
SundanesesuLive
SwahiliswLive
SwedishsvLive
TagalogtlLive
TajiktgLive
TamiltaLive
tatarttLive
TeluguteLive
ThaithLive
TibetanboLive
TurkishtrLive
TurkmentkLive
UkrainianukLive
UrduurLive
UzbekuzLive
VietnameseviLive
WelshcyLive
YiddishyiLive
YorubayoLive

Specify the language

You can use the optional language_code parameter to specify the language of the spoken audio in the files that you submit to the API. If you don’t include a language_code parameter in your request, it defaults to en_us.

To learn more about using the language_code parameter, see Set language manually.

If you’re unsure of the spoken language spoken in your audio file, you can use our Automatic Language Detection feature to automatically identify the dominant language in your file

Specify the speech model

You can use the optional speech_model parameter to specify the class of models. To learn more, see Select the speech model.