The Cognitive Services capabilities build on its existing Neural Text to Speech capabilities to offer more flexibility to brands and service providers. The newcast voice, for example, has the cadence you’d expect from a caster, emphasizing days and other vital information. Users may have even heard the voice already in the Bing mobile App’s voice search. Meanwhile, the customer service voice is designed to sound more friendly and engaging. Microsoft says it’s suitable for restaurant reservations, checking into a flight, and more. Digital assistant voices are something we’re all familiar with by now, but Aria’s voice for the task is notably different to Cortana. “Many customers have been using neural TTS voices for their digital assistant solutions. We are introducing two styles in this area: a chat style for more casual, conversational bots, and a more professional style for scenarios such as in-car digital assistants,” explained the company in a blog post. As well as the above, Neural Text to Speech is introducing some new emotional styles, including cheerful and empathetic. None of the examples here are indistinguishable from a human, but it’s clear the technology is getting closer by the day. In these scenarios, non-English languages are often left behind, but Microsoft is offering the same functionality for its Chinese voice assistant, Xiaoxiao, and some of the tones for Francisca, its Brazillian Portuguese personality. You can listen to all of the different options on the TechCommunity blog.
