How can I use Universal-2?

AssemblyAI offers state-of-the-art speech recognition models, each optimized for different use cases.

Our Universal-2 model is best for out-of-the-box transcription of pre-recorded audio when you need multi-language support, high accuracy, and fast turnaround times.

You can use Universal-2 by passing "universal-2" in the speech_model parameter. Learn more in this section of our documentation.