Our Flash and Turbo models have been specially developed for low-latency applications.
Flash v2 and Flash v2.5 are our ultra-low-latency models, generating audio in less than 75ms. Flash v2 is English only, while Flash v2.5 supports 32 languages. You can see a full list of all supported languages here.
Our Turbo models are also low-latency, but as the Flash models give very similar results, we recommend using the Flash models over Turbo. Turbo v2 is English only, while Turbo v2.5 supports 32 languages, and is 25% faster than Turbo v2, generating audio in around 300ms.
Both Flash and Turbo are highly optimized models, 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.
Both models are discounted when you generate via API. For details, see our API Pricing.
We also offer ElevenAgents, our platform for deploying customized, interactive voice agents. Visit our ElevenAgents documentation to learn more.