API Reference

style-diff-500 is a speech synthesis model using style diffusion and adversarial training.

Pricing

See our models page for pricing.

Voice IDs

The style-diff-500 model includes a number of generic US male/female voices:

  • us-male-1
  • us-male-2
  • us-male-3
  • us-male-4
  • us-male-5
  • us-female-1
  • us-female-2
  • us-female-3
  • us-female-4
  • us-female-5
  • us-female-6