OCR Language Codes

The ocrRecognitionLang parameter specifies the OCR recognition language using standard language codes. Defaults to auto (automatic detection).

Common Languages

Code	Language
auto	Auto Detect
zh-Hans	Simplified Chinese
zh-Hant	Traditional Chinese
en	English
ko	Korean
ja	Japanese

Latin Script

You can pass a specific language code or use latin for general Latin script recognition.

Code	Language
latin	Latin (General)
fr	French
de	German
es	Spanish
pt	Portuguese
it	Italian
nl	Dutch
sv	Swedish
pl	Polish
cs	Czech
ro	Romanian
hu	Hungarian
fi	Finnish
da	Danish
no	Norwegian
tr	Turkish
vi	Vietnamese
id	Indonesian
ms	Malay
hr	Croatian
sk	Slovak
sl	Slovenian
af	Afrikaans
sq	Albanian
ca	Catalan
et	Estonian
lv	Latvian
lt	Lithuanian
is	Icelandic
fil	Filipino

Devanagari

Code	Language
devanagari	Devanagari (General)
hi	Hindi
mr	Marathi
ne	Nepali
sa	Sanskrit

Cyrillic

Code	Language
cyrillic	Cyrillic (General)
kk	Kazakh
ky	Kyrgyz
mn	Mongolian

East Slavic

Code	Language
eslav	East Slavic (General)
ru	Russian
uk	Ukrainian
be	Belarusian
bg	Bulgarian

Arabic Script

Code	Language
arabic	Arabic (General)
ar	Arabic
fa	Persian
ur	Urdu

Other Languages

Code	Language
tamil / ta	Tamil
telugu / te	Telugu
kannada / kn	Kannada
thai / th	Thai
greek / el	Greek

Legacy Format Compatibility

The following legacy format codes are still supported but we recommend migrating to standard codes:

Legacy	Standard Code
AUTO	auto
CHINESE	zh-Hans
CHINESE_TRAD	zh-Hant
ENGLISH	en
KOREAN	ko
JAPANESE	ja
LATIN	latin
DEVANAGARI	devanagari
CYRILLIC	cyrillic
ARABIC	arabic
TAMIL	tamil
TELUGU	telugu
KANNADA	kannada
THAI	thai
GREEK	greek
ESLAV	eslav