What languages do you support?

Last updated: October 23, 2025

This page shows which languages are supported by the AssemblyAI Async API, their language_code values, and the features available for that language.

AssemblyAI offers two different speech-to-text models for prerecorded audio: Slam-1 and Universal.

Slam-1 currently only supports English, whereas Universal supports 99 languages.

Supported languages for Slam-1

  • English

Supported languages for Universal

  • Global English

  • Australian English

  • British English

  • US English

  • Spanish

  • French

  • German

  • Italian

  • Portuguese

  • Dutch

  • Hindi

  • Japanese

  • Chinese

  • Finnish

  • Korean

  • Polish

  • Russian

  • Turkish

  • Ukrainian

  • Vietnamese

  • Afrikaans

  • Albanian

  • Amharic

  • Arabic

  • Armenian

  • Assamese

  • Azerbaijani

  • Bashkir

  • Basque

  • Belarusian

  • Bengali

  • Bosnian

  • Breton

  • Bulgarian

  • Burmese

  • Catalan

  • Croatian

  • Czech

  • Danish

  • Estonian

  • Faroese

  • Galician

  • Georgian

  • Greek

  • Gujarati

  • Haitian

  • Hausa

  • Hawaiian

  • Hebrew

  • Hungarian

  • Icelandic

  • Indonesian

  • Javanese

  • Kannada

  • Kazakh

  • Khmer

  • Lao

  • Latin

  • Latvian

  • Lingala

  • Lithuanian

  • Luxembourgish

  • Macedonian

  • Malagasy

  • Malay

  • Malayalam

  • Maltese

  • Maori

  • Marathi

  • Mongolian

  • Nepali

  • Norwegian

  • Norwegian Nynorsk

  • Occitan

  • Panjabi

  • Pashto

  • Persian

  • Romanian

  • Sanskrit

  • Serbian

  • Shona

  • Sindhi

  • Sinhala

  • Slovak

  • Slovenian

  • Somali

  • Sundanese

  • Swahili

  • Swedish

  • Tagalog

  • Tajik

  • Tamil

  • Tatar

  • Telugu

  • Thai

  • Tibetan

  • Turkmen

  • Urdu

  • Uzbek

  • Welsh

  • Yiddish

  • Yoruba

Specify the language​

You can use the optional language_code parameter to specify the language of the spoken audio in the files that you submit to the API. If you don't include a language_code parameter in your request, it defaults to en_us.

To learn more about using the language_code parameter, see this section of our documentation.

If you're unsure of the language spoken in your audio file, you can use our Automatic Language Detection feature to identify the dominant language in your file automatically.

Specify the speech model​

You can use the optional speech_model parameter to specify the class of models. To learn more, see Select the speech model.

Note: The information on this page is specific to our Async Speech-to-Text feature for pre-recorded audio.

See this page to learn more about supported languages for our Streaming STT feature.