tts-1-hd

Name in the API

tts-1-hd

Base model

coqui/XTTS-v2, served by openedai-speech

Type

Text to speech

Input → output

text → audio

Availability

Dedicated

Hardware

A 12 GB slice of a GPU per instance

Voices

alloy, echo, fable, nova, onyx, shimmer

Endpoint

/v1/audio/speech

Notes

• The name and the voices follow the OpenAI API, but the voices do not sound like OpenAI's.