Deepgram’s Version feature allows you to specify the version of the model you want to use to process your submitted audio. By default, Deepgram defaults to the latest version of the selected model.
Examples of use cases for Version include:
- Customers who want to make sure they are using the latest version of a given model.
- Customers who want to use an earlier version of Deepgram standard model.
- Customer who want to use a specific version of a custom model associated with their account.
- Customers who would like to receive early access to an updated Deepgram standard model.
To enable Version, when you call Deepgram’s API, add a
version parameter in the query string and set it to the version of the model you want to use to process your submitted audio.
Use the Latest Version
To use the latest version of your selected model, send
latest in the
Use an Earlier Version of a Standard Model
To use an earlier version of a selected Deepgram standard model, send the version number in the
You can locate version numbers of Deepgram standard models in our changelog. Select Speech Model to filter the updates.
Use a Specific Version of a Custom Trained Model
To use a specific version of a custom model associated with your account, send the custom model’s
version_id in the
Get Early Access to an Updated Standard Model
When we release updated versions of Deepgram standard models, you may be able to try them out and provide feedback. To do so, send the version name of the selected model in the
To learn about updated model availability and get relevant version names, contact Support.