Turbo v2 numbers pronunciation

Our fastest model now has improved numbers pronunciation

In November we announced our new, fastest model that generates speech at ≈400ms latency and is over twice as fast as our V1 models.

Unfortunately users found that it struggled to pronounce long numbers. Give a listen to this generation of "The current stock price for NVIDIA is $867.49."

Today we just released improved numbers pronunciation for our Turbo v2 model. Here's how it sounds after the upgrade:

Thank you to all of the users who submitted feedback that inspired this fix - and please continue to share areas where our models can be improved.

Explore more

Product
Dubbing API Upgrade Blog Cover (fixed)

Dubbing API Max File Upgrade

We increased the max file size for a single call to our Dubbing API from 45 min -> 2.5 hours and 500MB -> 1GB

ElevenLabs

Create with the highest quality AI Audio

Get started free

Already have an account? Log in