Azure Neural Text to Speech(Azure Neural TTS), a powerful speech synthesis capability from Azure Cognitive Services, enables developers to transform text into lifelike speech using AI. Enterprises and government use Azure Neural TTS for video game characters, chatbots, content readers, and more. The Azure Neural TTS product team is constantly working to bring new speech styles and emotions to the US market and beyond.
New language styles and emotional tones
We received feedback from customers that more language options would help them better apply Azure Neural TTS to different user scenarios. In addition, language sentiment and language style support would help provide the most engaging experience to end users. Based on this feedback, we decided to add five new US English neural voices, expanding from 15 to 20. These include two female voices – Jane and Nancy – and three male voices – Davis, Jason and Tony. We’ve also expanded many of our existing and new voices into eight emotional tones, including Happy, Angry, Sad, Excited, Hopeful, Kind, Unkind, and Scared. Finally, to improve spatial experiences, we added shouts and whispers.
Hear how they sound
Project new ways
We encourage you to do so Try out the new voices and emotions . Feedback is welcome to inform which votes will be given for general availability in all regions based on customer satisfaction. “By supporting more speech options and advanced speech styles, Azure Speech continues to address customers’ unmet needs to create a more enjoyable speech experience,” said Binggong Ding, principal group product manager of the Microsoft Speech team.
See the full listof US English voices here.
Three ways customers are using this
reading content is a popular use case for AI customers using Azure Neural TTS. Microsoft has plugins to enable Read Aloud on the web. This use case also supports improved accessibility for customers with vision problems. The new language style, supported by ten different emotional tones, creates endless possibilities to improve the customer experience. scaling character voice production is accelerated by Azure Neural TTS. Video game characters with lifelike voices can be quickly trained to bring your virtual worlds to life and delight players. Emotional tones for fear and kindness add more personality to gaming experiences. The days of frustration are long gone voice assistants and chatbots, because now you can deliver true-to-life conversational experiences. Call centers can scale operations while improving customer satisfaction.
Undead Labs is dedicated to taking gaming in bold new directions. They are the creators of the State of Decay franchise and use Azure Neural TTS during game development. Double Fine, who has produced many popular games including Psychonauts 2, uses our neural TTS to create prototypes for future game projects. Remixd (recently acquired by Global) uses Azure Neural TTS, including Jenny and Davis’ voices, for one of its music radio media clients.
Engage a global audience by using more than 340 neural voices in 129 languages and variants . Bring your scenarios like text readers and voice-controlled assistants to life with expressive and human-like voices.
Neural TTS and responsible AI
We are excited for the future of Azure Neural TTS with human-like, diverse and delightful quality under the high-level architecture of XYZ codeAI framework. Our technological advances are also aligned with those of Microsoft Responsible AI process, and our principles of fairness, inclusivity, reliability and security, transparency, privacy and security, and accountability. We put these ethical standards into practice through the Office of Responsible AI (ORA), which sets our rules and governance processes, the AI Ethics and Effects in Engineering and Research (Aether) Committee, which provides our leadership on the challenges and opportunities advises that result from AI innovations and Responsible AI Strategy in Engineering (RAISE), a team that enables the implementation of Microsoft Responsible AI rules in all engineering groups.