Our latest model, Turbo v2.5, is a highly optimized model, specifically tailored for low-latency applications without sacrificing vocal performance and keeping inline with the quality standard that people have come to expect from our models.
We’ve measured latency of around 300ms consistently (+ network).
It’s 25% faster than Turbo v2. It’s 300% faster than Multilingual v2 and adds Vietnamese, Hungarian and Swedish to our existing 29 languages.
You can read more about it here.