Sumsub supports most of the languages, including Korean, Japanese, Chinese, Cyrillic, and Semitic.
Our OCR engine extracts both local and latin characters from the documents. In addition, we provide a built-in transliteration module that transforms all of the local characters into latin in accordance with the rules stipulated by the country.
- For Amharic, Bengali, Burmese, Dari, Dhivehi, Hindi, Khmer (Cambodian), Kinyarwanda, Lao, Mongolian, Nepali, Sinhalese, we only accept documents with the latin characters. If the document is submitted with the country-specific characters, a notarized translation must be provided.
- Arabic, Farsi, and Urdu are available upon request at an additional cost. For more information, contact your Customer Success Manager.
Updated 5 days ago