106 languages
Kiku Hours works out the language of each video by listening, on your own computer. These are the languages it can name. You never have to say which one you are learning; you only say which ones you already speak, so their time is held out of your total.
- Abkhazian
- Afrikaans
- Albanian
- Amharic
- Arabic
- Armenian
- Assamese
- Azerbaijani
- Bashkir
- Basque
- Belarusian
- Bengali
- Bosnian
- Breton
- Bulgarian
- Burmese
- Catalan
- Cebuano
- Chinese
- Croatian
- Czech
- Danish
- Dutch
- English
- Esperanto
- Estonian
- Faroese
- Finnish
- French
- Galician
- Georgian
- German
- Greek
- Guarani
- Gujarati
- Haitian Creole
- Hausa
- Hawaiian
- Hebrew
- Hindi
- Hungarian
- Icelandic
- Indonesian
- Interlingua
- Italian
- Japanese
- Javanese
- Kannada
- Kazakh
- Khmer
- Korean
- Lao
- Latin
- Latvian
- Lingala
- Lithuanian
- Luxembourgish
- Macedonian
- Malagasy
- Malay
- Malayalam
- Maltese
- Manx
- Maori
- Marathi
- Mongolian
- Nepali
- Norwegian
- Occitan
- Pashto
- Persian
- Polish
- Portuguese
- Punjabi
- Romanian
- Russian
- Sanskrit
- Scots
- Serbian
- Shona
- Sindhi
- Sinhala
- Slovak
- Slovenian
- Somali
- Spanish
- Sundanese
- Swahili
- Swedish
- Tagalog
- Tajik
- Tamil
- Tatar
- Telugu
- Thai
- Tibetan
- Turkish
- Turkmen
- Ukrainian
- Urdu
- Uzbek
- Vietnamese
- Waray
- Welsh
- Yiddish
- Yoruba
How sure is it?
The identifier was measured against real recordings in the 28 languages marked with a dot, and labelled every one correctly on thirty-second windows. It did not confuse the pairs that trip other detectors, such as Italian and Spanish or Korean and Japanese. The rest of the list rests on the model's published results for those languages, and every label, whatever the language, is only shown once two independent checks agree. When the audio is not clear enough to name a language, that video's time is not counted; nothing is guessed.
Notes
- Norwegian covers both Bokmål and Nynorsk; the identifier tells them apart, the product treats them as one language.
- Chinese means Mandarin. Cantonese is not identified separately.
- Serbian, Croatian and Bosnian are listed separately because the identifier reports them separately; expect some overlap between them.
- A language you already speak is declared in the extension's Settings and its time is recorded but not counted. Everything else counts as input.
Missing a language you learn? Tell us; the list follows the model, and the model can be changed.