​

1. Introducing Waves - [30/09/2024]

Waves is our new unified platform for speech synthesis. It supports various models designed for real-time applications such as voicebots. However, waves will also be supporting various features such as voice cloning, accent cloning, style transfer, speech to speech etc in the near future, making it a ubiquitous platform for anyone who needs AI generated speech.

The voices available on waves platform are available via the Waves API

​

2. Introducing Lightning - World’s Fastest Text to Speech - [30/09/2024]

Lightning is the world’s fastest text to speech model, generating around 10 seconds of hyper-realistic audio in just 100ms, all at once, no streaming.

Read more about lightening in our release post here

You can access lightning via the Waves API

A lot more coming up, very soon