AT&T and Warner Bros. used the tech to create an interactive version of Bugs Bunny.
Microsoft is opening limited access to a text-to-speech AI called Custom Neural Voice, which allows developers to create customized synthetic voices. The technology is part of an Azure AI service called Speech. Companies can use technology for things like voice-activated devices and smart assistants, chatbots, online learning and reading audiobooks or news. They will have to sign up for access and obtain Microsoft approval before they can take advantage of Custom Neural Voice.
The technology can offer more natural voices than many other text-to-speech services, according to Microsoft. Custom voices use a bank of sounds, or phonemes, to create voice sources. The personalized neural voice uses several neural networks in an attempt to ensure that the prosody (the tone and duration of each phoneme) and the pronunciation are accurate. This helps AI to mimic an actor’s voice correctly or use a synthetic voice that sounds realistic.
Several companies are already using the technology, including AT&T and Warner Bros. They recently installed a system at the AT&T Experience Store in Dallas, where people can interact with Bugs Bunny. Using a combination of Personalized Neural Voice, augmented reality and 5G, Bugs can chat with customers in real time and move around the store to help them find a hidden golden carrot.
Eric Bauza, the actor who currently voices Bugs, has recorded more than 2,000 lines and phrases with the help of Microsoft to create a voice source. Warner Bros. and Microsoft worked together to create a personalized voice that explores the character’s personality and inflections. Duolingo also used Personalized Neural Voice to create quirky characters to help people learn new languages, while Progressive created the technology for its chatbot Flo.