Meta released the speech generation AI model "Voicebox", which supports speech generation from text, can match audio styles based on samples that are only two seconds long, and convert text samples to another language, given individual speech samples , and can read the translated text content in the speaker's original voice, currently supporting six languages: English, French, German, Spanish, Polish and Portuguese. Meta said that Voicebox can also make virtual assistants and non-player characters in the metaverse make natural voices, and can allow the visually impaired to hear written messages from friends read by AI in their voices, providing creators with new tools to easily create And edit the audio track of the video and so on.