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 articles by the ElevenLabs team

Customer stories
eagr_case study

Eagr.ai Supercharges Sales Training with ElevenLabs' Conversational AI Agents

Eagr.ai transformed sales coaching by integrating ElevenLabs' conversational AI, replacing outdated role-playing with lifelike simulations. This led to a significant 18% average increase in win-rates and a 30% performance boost for top users, proving the power of realistic AI in corporate training.

ElevenLabs

Create with the highest quality AI Audio

Get started free

Already have an account? Log in