Supported languages
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 three different levels of speech-to-text models: Slam-1, Universal, and Nano. Check out the Models page of our documentation to learn more about our different models and how to choose the best one for your use case.
Below, you’ll find the supported languages for each class of models, as well as instructions on how to change the language for your transcription.
Supported languages for Slam-1
Supported languages for Universal
Supported languages for Nano
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 Set language manually.
If you’re unsure of the spoken language spoken in your audio file, you can use our Automatic Language Detection feature to automatically identify the dominant language in your file.
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.