Language hints

Language detection is automatic by default. When you already know the spoken language, pass a hint with the upload language field or realtime transcription.language field.

Common accepted codes are:

Code	Language	Code	Language
ar	Arabic	cs	Czech
da	Danish	de	German
el	Greek	en	English
es	Spanish	fa	Persian
fi	Finnish	fil	Filipino
fr	French	hi	Hindi
hu	Hungarian	id	Indonesian
it	Italian	ja	Japanese
ko	Korean	mk	Macedonian
ms	Malay	nl	Dutch
pl	Polish	pt	Portuguese
ro	Romanian	ru	Russian
sv	Swedish	th	Thai
tr	Turkish	vi	Vietnamese
yue	Cantonese	zh	Chinese

Full language names such as English, Spanish, and Cantonese are also accepted case-insensitively. Chinese regional hints include anhui, dongbei, fujian, gansu, guizhou, hebei, henan, hubei, hunan, jiangxi, ningxia, shaanxi, shandong, shanxi, sichuan, tianjin, yunnan, and zhejiang. The API also recognizes Cantonese (Hong Kong accent), Cantonese (Guangdong accent), Wu language, and Minnan language.

Omit the field or use auto for automatic detection. An unrecognized hint currently falls back to automatic detection rather than returning an error.