Get the latest tech news

Tencent’s EzAudio AI transforms text to lifelike sound, sparking innovation and debate


Tencent's EzAudio revolutionizes AI-generated sound, offering unprecedented audio quality from text while raising ethical concerns about deepfakes and the future of voice technology.

Researchers from Johns Hopkins University and Tencent AI Lab have introduced EzAudio, a new text-to-audio (T2A) generation model that promises to deliver high-quality sound effects from text prompts with unprecedented efficiency. In comparative tests, EzAudio demonstrated superior performance across multiple metrics, including (FD), Kullback-Leibler(KL) divergence, and Inception Score(IS). ElevenLabs, a prominent player in the field, recently launched an iOS app for text-to-speech conversion, signaling growing consumer interest in AI audio tools.

Get the Android app

Or read this on Venture Beat

Read more on:

Photo of Text

Text

Photo of innovation

innovation

Photo of Tencent

Tencent

Related news:

News photo

LG Nova launches partner alliance program to catalyze innovation

News photo

Tencent’s new AI can create open-world video games from text

News photo

Periphery Synthetic is playable by sound alone - is it the next step in accessibility for the blind and visually impaired?