What is the difference between Custom Vocabulary and Custom Spelling?

The Custom Vocabulary feature allows you to submit a list of words or phrases to boost the likelihood that the model predicts those words. This is intended to help with words or terms that might be under-represented in the training data.

The Custom Spelling feature allows you to control how words are spelled or formatted in the transcript text. It works like a find and replace feature — anytime you would see X in the API output, it’ll be replaced with Y.

To put it another way, Custom Vocab affects how the model predicts words while Custom Spelling affects words once the transcript text has been created.