You can generate captions automatically by referencing the audio clips used in your edit within your caption asset. Shotstack will detect the language of the audio and transcribe it accordingly.

Shotstack will automatically try to detect the language used.

First add a clip holding the audio you wish to have transcribed:

Assign an alias in the properties panel of this clip:

Add an automated caption clip:

Reference the alias of that clip:

Once the alias is referenced, Shotstack will generate captions for the audio in that clip.