Voices ​

The voice defines which engine and which voice within the engine to use for synthesis. All values are case-insensitive and the internal list is fetched from the providers directly. Any voice that a provider offers can be utilized by the audio server. A full list of voices can be acquired from the voices endpoint.

type Engine = 'speechify-1'

type Voice = {
  name: string
  engine: Engine
  language: string // e.g. en-US, fr-FR, arb, etc.
}

speechify-1 ​

The speechify-1 model represents our in-house state of the art model which is actively receiving improvements to latency, voice cloning capability and pronunciation. It is currently the only model available for synthesis but many more will be available in the future, likely before the end of the beta.