Introducing Voicebox: The first generative AI model for speech to generalize across tasks with state-of-the-art performance
ai.facebook.com
Voicebox is a state-of-the-art speech generative model based on a new method proposed by Meta AI called Flow Matching. By learning to solve a text-guided speech infilling task with a large scale of data, Voicebox outperforms single-purpose AI models across speech tasks through in-context learning.
  • socialjusticewizard
    1·
    2 years ago

    Well, that was inevitable. With generative face video pretty much ready now, we’re just an integration away from creating a fully featured video conversationalist.