Microsoft announces Text To Speech Avatar AI tool: can create virtual 3D digital people, based on Azure platform

According to news from this site on November 16, Microsoft launched an AI tool called "Azure AI Speech text to speech (TTS) avatar" for Azure AI Speech at the Ignite conference, which claims to be able to generate realistic human avatars. (Digital Man), this tool is currently open to the public for preview and trial.

Microsoft said that users using Azure AI Speech text to speech (TTS) avatar can create virtual avatars based on "entering text to speak content" and Combined with real-person photo training, an "interactive chatbot" based on real people is established, which can be used in corporate marketing, business or customer service scenarios.

It is reported that this Azure AI Speech text to speech (TTS) avatar mainly includes three modules, namely text analyzer, TTS voice synthesizer and TTS virtual avatar synthesizer:

First, the text analyzer will analyze the text content input by the user and generate a phoneme sequence. Then, the TTS speech model in the TTS speech synthesizer will predict the acoustic characteristics of the text input by the user and synthesize the sound. Finally, the neural network sound synthesis model Avatar will predict the lip shape image of the character based on the above acoustic characteristics, and finally form a virtual avatar image

Microsoft explained that traditional virtual character production is time-consuming and laborious, and requires the construction of a dedicated The shooting environment and the post-editing process also cost a lot. Now using Microsoft's latest Azure AI Speech text-to-speech (TTS) role service, once the model is established, users only need to enter text to create various product introductions and interactive videos. Combining the Microsoft Azure OpenAI service and the neural network TTS function can also present a more natural interactive experience

This site found that Microsoft claimed for example , users can use Azure AI Speech TTS avatar to batch produce various video contents, such as corporate culture videos, product introductions, or the CEO's digital avatar at conferences. You can also create virtual live broadcast digital humans, chat robots, business robots, or AI teachers for online teaching, etc.

Microsoft said that Azure AI speech-to-text (TTS) avatars have been rolled out to Azure subscribers and support multiple languages. Users can select the desired character from the preset avatar options, or customize the avatar

If the user wants to customize the avatar, they need to upload a series of characters Video clips. The Azure platform will process these videos online and generate virtual avatars. The character itself is separated from the sound source. Users can choose the official default sound source or upload their own training sound source

The above is the detailed content of Microsoft announces Text To Speech Avatar AI tool: can create virtual 3D digital people, based on Azure platform. For more information, please follow other related articles on the PHP Chinese website!