Exciting news from Azure AI Speech!

Jiadong Chen
3 min readNov 17, 2023

Microsoft’s Azure AI Speech has launched ‘Personal Voice’ and is now previewing ‘text to speech avatar’. These updates make digital interactions more engaging and personalized than ever. It’s bringing us one step closer to a personalized and intuitive user experience. Let’s delve into how these new features can enhance your digital interactions. Read on to learn more.

Personal Voice

🎙️ As technology advances, the need for personalization is paramount. The ‘Personal Voice’ feature allows users to create their own AI voice. This opens the door to a fully personalized voice experience. Imagine creating a voice that sounds just like you with just a 60-second voice sample!

🌐 With ‘Personal Voice’, you can create a voice in seconds, in any of the 100 languages supported. This global reach is a game-changer for personalized and intelligent voice experiences.

  • 🎮 From creating a unique voice assistant experience, to enabling immersive gaming experiences, to breaking down language barriers in speech translation — ‘Personal Voice’ opens up endless possibilities.
  • 🎧 Media & entertainment can greatly benefit from ‘Personal Voice’. It enables the creation of personal voices for stories, audio books, podcasts, videos, making content more relatable and immersive.
  • 🔍 Azure AI Speech ensures every voice created with ‘Personal Voice’ has explicit user consent, protecting the rights of individuals and fostering transparent human-computer interaction.

Text to Speech Avatar

🎭 Azure AI Speech also announces the public preview of ‘text to speech avatar’, a feature that enables users to create talking avatar videos with text input, making digital interactions more engaging.

👀 With ‘text to speech avatar’, you can create engaging videos and applications enriched with an interactive avatar, such as training videos, product introductions, customer testimonials, and more.

  • 🎬 Traditional video content creation can be time-consuming and costly. With ‘text to speech avatar’, users can efficiently create video content simply with text input.
  • 💬 ‘Text to speech avatar’ can be used to build conversational agents, virtual assistants, chatbots, and more, providing more natural and engaging digital interactions.
  • 🌟 This release includes prebuilt text to speech avatars as out of box products, and a custom text to speech avatar feature that enables customers to create a personalized avatar for their product or brand.

https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/azure-ai-speech-announces-public-preview-of-text-to-speech/ba-p/3981448?WT.mc_id=DT-MVP-5001664

https://github.com/Azure/gen-cv/blob/main/avatar/video/README.md?WT.mc_id=DT-MVP-5001664

🎯 As we wrap up this thread, it’s clear that Azure AI Speech’s ‘Personal Voice’ and ‘text to speech avatar’ are not just innovative, they’re transformative. They are redefining how we communicate and engage in the digital world!

--

--

Jiadong Chen
Jiadong Chen

Written by Jiadong Chen

Microsoft MVP, MCT | Azure Certified Solutions Architect & Cybersecurity Architect Expert | Member of .NET Foundation | Packt Author