Microsoft's Custom Neural Voice feature will allow you to create a highly realistic, humanlike voice

Microsoft today announced the general availability of Custom Neural Voice, a Text-to-Speech feature, part of Speech Service in Azure Cognitive Services. This feature will allow you to create a highly realistic, humanlike custom voice for your application using Microsoft’s groundbreaking neural text-to-speech models. Since the voices created are so lifelike, Microsoft is limiting the access so that users will make use of this technology responsibly.

As part of Microsoft’s commitment to responsible AI, we are designing and releasing Custom Neural Voice with the intention of protecting the rights of individuals and society, fostering transparent human-computer interaction and counteract the proliferation of harmful deepfakes and misleading content. For this reason, we have limited the access and use of Custom Neural Voice.

To create a custom voice, you can just record audio and upload it as training data. The Azure Speech Service will create a unique voice tuned for your recording. The realistic and natural sounding voice of Custom Neural Voice can represent brands, and allow users to interact with apps conversationally in a natural way. Microsoft highlighted that following customers are already using this latest TTS feature.

• AT&T/Warner Bros. They recently launched a first-of-its-kind creative and interactive experience at the AT&T Experience Store in Dallas, TX where customers can talk directly to Bugs Bunny.
• Progressive. Using the voice of Flo, the iconic Progressive Insurance spokesperson, Progressive created the Flo chatbot to streamline the customer inquiry process and deliver personalized experiences.
• Duolingo. To help make learning a new language feel attainable and applicable with quirky characters and quality content, Duolingo created a diverse cast of stylized voices using the Duolingo curriculum.

You can learn more about Custom Neural Voice here.

Source: Microsoft