Cleft officially supports US English and is optimized for US English voice recognition using the Whisper model. While the underlying Whisper model has the capability to work with other languages, we only officially support and test with US English at this time.
While the underlying model was trained on 98 languages, we only list the languages that exceeded <50% word error rate (WER), which is an industry standard benchmark for speech to text model accuracy. The following 57 languages meet this quality threshold:
Afrikaans
Arabic
Armenian
Azerbaijani
Belarusian
Bosnian
Bulgarian
Catalan
Chinese
Croatian
Czech
Danish
Dutch
English
Estonian
Finnish
French
Galician
German
Greek
Hebrew
Hindi
Hungarian
Icelandic
Indonesian
Italian
Japanese
Kannada
Kazakh
Korean
Latvian
Lithuanian
Macedonian
Malay
Marathi
Maori
Nepali
Norwegian
Persian
Polish
Portuguese
Romanian
Russian
Serbian
Slovak
Slovenian
Spanish
Swahili
Swedish
Tagalog
Tamil
Thai
Turkish
Ukrainian
Urdu
Vietnamese
Welsh
Note: The model will return results for languages not listed above, but the quality will be low.