How can I use Universal-2?

At AssemblyAI, we use a combination of models to produce your results. Our Best tier will house our most powerful and accurate models, including Universal-2. This tier is best suited for use cases where accuracy is paramount, and end-users will interact directly with the results generated from our models.

Our Best tier is used by default if no speech model tier is specified. Universal 2 part of our Best tier. There is no need to do anything special to use this new model. Just submit requests as normal and they will always be routed to our latest models.