How can I use Universal-2?

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

There are no default models for transcription. You must specify which model or models to use via the speech_models parameter when making a request to the /v2/transcript endpoint. You can provide multiple models in priority order, and the system will automatically route to the best available model based on your request.

To learn how to select and configure speech models, see Select the speech model.

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.