Deepgram is continuing to expand our selection of Enhanced Models to bring you the highest accuracy across many languages and use-cases. 

To better support these models, we have deployed a new `tier` parameter to be used in our API calls. 

Accepted options are:

  • tier=base 

  • tier=enhanced

Default value if not passed is tier=base. 

For example, to call the General English Enhanced Model, the URL query might look like

To learn more about the tier parameter, please see the tier page in our documentation

To learn more about the various parameters you can use to customize your transcriptions with Deepgram, check out the list of Deepgram’s features in our documentation

Please note that model=general-enhanced will continue to be accepted as a way of calling the General Enhanced model for English, but all other Enhanced Models will need to be called by specifying tier=enhanced in your API call. 

All beta names for enhanced models have been deprecated. If you were involved in beta testing our Enhanced models, please update your API calls to reflect one of the above methods of calling the model, and thank you for your valuable feedback! 

Stop building work-arounds for STT systems that don't work.

Start FreeTalk to an expert