We have made some major updates to our voice design model. The additional parameters loudness, quality, guidance_scale, and seed allow you to achieve even better results now. Have a listen and easily share your voice design prompts via URL.

will someone try this with my character and animation AI and share it please. 😊

Announcing: Our most advanced speech-to-text model goes beyond accuracy to capture the real-world complexity of human conversation and deliver reliable, source-of-truth audio data. Explore Universal-2 updates 👇

Can we please get more voice spots in the Creator tier? I never even use all my minutes, have hundreds of thousands left unused because all I want is to make new voices for project uses that don’t say a lot but need to be unique. The amount of voice designs granted feels way too low and to get more means upgrading and that would result in even more unused minutes.

👀👀

wow!! amazing. Just to know, is there some kind of SSML available!

@elevenlabsio I cancelled and just use Zonos now. it runs for free on my machine with 11labs quality. the moat is almost dried up!

is the latency going to get even better?