​
Overview

Blizzard, our default model, is a powerful and expressive text-to-speech model that delivers natural, high-quality voice synthesis with excellent prosody and emotional range.

Note: The Aurora model ID (aurora) is now an alias that routes all requests to Blizzard. As Blizzard has reached production maturity, we’ve consolidated our model offering to provide a single, high-performance solution. This change ensures consistent quality and reliability across all voice synthesis requests.

​
Model Updates & Changes

​
Regular Updates

Models receive regular updates and improvements. Most updates are non-breaking and require no changes to your applications.

​
Breaking Changes

When we need to make breaking changes:

  1. We announce the changes in advance
  2. Provide a deprecation window to update your applications
  3. Document migration steps
  4. Send deprecation notices through the API headers

​
Model Version Tracking

You can find which specific model version handled your request in the API response headers under X-Model-Version. We recommend logging this value for debugging.

​
Support & Updates

We’ll notify you about model updates, breaking changes, and deprecation windows through these channels.