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 three-second audio sample, Ars Technica has reported. The ...

Drawing upon the potential of Meta‘s open-source MusicGen, an AI-based sound generation suite, TextToSample was developed using the data fed by this advanced algorithm. Adding to its capabilities, the ...

Nvidia has released a new generative audio AI model that is capable of creating myriad sounds, music, and even voices, based on the user’s simple text and audio prompts. Dubbed Fugatto (aka ...