Skip to main content
Expressive text to speech with measured character billing.

Model ID

Pass this exact public ID in the top-level model field.

Supported modes

  • text_to_speech

Inputs

  • Text

Outputs

  • Audio

Capabilities

  • text_to_speech

Additional capabilities

  • Speech generation
  • HTTP audio streaming
  • Complete-turn WebSocket

Technical details

Availability and final customer prices can change. Check the Dashboard model catalog before production use.
See the Audio API guide for voice selection, formats, metering, callbacks and WebSocket sessions. Maximum 2,000 characters per generation. Try Eleven v4 Turbo in API Explorer. See the API reference overview for authentication, request conventions, and response schemas.