New Text-to-Speech endpoints with timestamps

A digital illustration showing a code snippet in a black box and a stylized blue wave graphic in a white box overlapping each other.

We release two new endpoints for text-to-speech, which make it possible to get timestamps on when each character was spoken without using websockets both in a streaming and non-streaming way. You can read more about it

Explore more

ElevenLabs

Create with the highest quality AI Audio

Get started free

Already have an account? Log in