Transcribe AI

Transcribe audio in 99+ languages

Every language in the app runs on the same offline AI model, from Afrikaans to Yoruba. Choose the spoken language before you record.

All 99 languages in the app

  • Afrikaans
  • Albanian
  • Amharic
  • Arabic
  • Armenian
  • Assamese
  • Azerbaijani
  • Bashkir
  • Basque
  • Belarusian
  • Bengali
  • Bosnian
  • Breton
  • Bulgarian
  • Cantonese
  • Catalan
  • Chinese
  • Croatian
  • Czech
  • Danish
  • Dutch
  • English
  • Estonian
  • Faroese
  • Finnish
  • French
  • Galician
  • Georgian
  • German
  • Greek
  • Gujarati
  • Haitian Creole
  • Hausa
  • Hawaiian
  • Hindi
  • Hungarian
  • Icelandic
  • Indonesian
  • Italian
  • Japanese
  • Javanese
  • Kannada
  • Kazakh
  • Khmer
  • Korean
  • Lao
  • Latin
  • Latvian
  • Lingala
  • Lithuanian
  • Luxembourgish
  • Macedonian
  • Malagasy
  • Malay
  • Malayalam
  • Maltese
  • Maori
  • Marathi
  • Mongolian
  • Myanmar
  • Nepali
  • Norwegian
  • Nynorsk
  • Occitan
  • Pashto
  • Persian
  • Polish
  • Portuguese
  • Punjabi
  • Romanian
  • Russian
  • Sanskrit
  • Serbian
  • Shona
  • Sindhi
  • Sinhala
  • Slovak
  • Slovenian
  • Somali
  • Spanish
  • Sundanese
  • Swahili
  • Swedish
  • Tagalog
  • Tajik
  • Tamil
  • Tatar
  • Telugu
  • Thai
  • Tibetan
  • Turkish
  • Turkmen
  • Ukrainian
  • Urdu
  • Uzbek
  • Vietnamese
  • Welsh
  • Yiddish
  • Yoruba

How accuracy varies by language

The offline AI model inside the app learned from far more audio in some languages than others. English, Spanish, French, German, Italian, Portuguese and Japanese tend to give the cleanest drafts. Languages with less training audio still work, but depend more on a clear, close recording. The model is small enough to run on the phone, which makes recording quality matter more than it would on a large server model.