Introducing Play 3.0 Mini: a fast and efficient text-to-speech model

The new Play 3.0 Mini Text-To-Speech model has been launched, offering users improved speed, accuracy, and cost-efficiency. This updated version is the fastest in the industry with a time to first audio of 189ms and supports diverse data recognition, including phone numbers and acronyms, with a 40% lower character error rate than its predecessor. Additionally, a new pricing tier is introduced, allowing more cost-effective access for users.