Tesseract engine
With the Tesseract OCR engine, only the searchable pdf format is supported.
Supported languages: Afrikaans (South Africa), Albanian (Albania), Azerbaijani (Azerbaijan), Belarusian (Belarus), Bosnian (Bosnia & Herzegovina), Bulgarian (Bulgaria), Catalan (Spain), Croatian (Croatia), Czech (Czech Republic), Danish (Denmark), English, Esperanto, Estonian (Estonia), Finnish (Finland), French (France), German (Germany), Hungarian (Hungary), Icelandic (Iceland), Indonesian (Indonesia), Irish (Ireland), Italian (Italy), Japanese (Japan), Javanese (Java), Kyrgyz (Kyrgyzstan), Latin, Latvian (Latvia), Lithuanian (Lithuania), Macedonian (Macedonia), Malay (Malaysia), Maltese (Malta), Norwegian (Norway), Polish (Poland), Portuguese (Brazil), Portuguese (Portugal), Romanian (Romania), Russian (Russia), Serbian (Serbia), Slovak (Slovakia), Slovenian (Slovenia), Spanish, Swedish (Sweden), Turkish (Turkey), Ukrainian (Ukraine), Uzbek (Uzbekistan), Vietnamese (Vietnam), Welsh (Wales), Yiddish.
Selecting multiple languages will take much more time to process the files.
For further information about the engine, see the dedicated documentation from its developer.