Artificial Intelligence News
Meta announced a development in speech-generative AI by creating Voicebox, a cutting-edge AI model that can execute voice production tasks that it wasn’t specifically trained to accomplish using in-context learning, such editing, sampling, and stylizing. Voicebox can create high-quality audio clips and edit pre-recorded audio while maintaining the style and content of the original recording. For example, it can take out automobile horns or dog barking. The model can speak in six different languages and is bilingual as well.
Credit WION