Microsoft has revealed its latest research in text-to-speech AI with VALL-E, as reported by Engadget. VALL-E can simulate someone's voice from only a three-second audio sample.

At Microsoft Ignite 2023, the company launched AI-powered tools to create photorealistic avatars and voices that mimic a person's speech.

Microsoft has shown off its latest research in text-to-speech AI with a model called VALL-E that can simulate someone's voice from just a 3-second audio sample.

Microsoft’s new AI can simulate anyone’s voice with 3 seconds of audio Text-to-speech model can preserve speaker's emotional tone and acoustic environment.

Copilot gets high-speed voice generation while foundation model debuts on LMArena Software King of the World, Microsoft has trundled out two new in-house AI efforts, one already talking inside Copilot ...

The new small language model can help developers build multimodal AI applications for lightweight computing devices, Microsoft says.