Meta日前推出了一款AI声音生成模型Audiobox，这款模型能够同时接收语音及文字输入，用户Meta日前推出了一款AI声音生成模型Audiobox，这款模型能够同时接收语音及文字输入，用户可同时使用语音及文字描述，让这款模型生成所需的音频。据悉，这款模型基于Meta今年6月推出的Voicebox AI模型，据称Audiobox能生成各种环境音、自然对话语音，并整合了音频生成和编辑能力，以便于用户自由生成自己所需的音频。
Meta的这一举措无疑是对AI技术在音频领域的一次重要突破。Audiobox的推出，不仅能够让用户更加便捷地生成所需音频，也为音频制作人提供了更多可能性。此外，Audiobox还支持多层次声音生成，这意味着用户可以根据自己的需求，生成不同层次的声音效果。
据了解，Meta在今年6月推出了Voicebox AI模型，该模型采用了先进的深度学习技术，能够实现高质量的语音合成。而Audiobox则是在这一基础上进行了进一步优化和升级，使其具备了更强的音频生成和编辑能力。
英语如下：
新闻标题：Meta Launches New AI Audio Model Audiobox: Du新闻标题：Meta Launches New AI Audio Model Audiobox: Dual Voice and Text Input, Free to Create Multi-Layered Sounds
Keywords: Meta AI, audio model, voice and text input
News Content: Meta has recently launched an AI sound generation model called Audiobox. This model can receive both voice and text inputs at the same time. Users can use both voice and text descriptions to generate the desired audio with this model. It is reported that this model is based on Meta’s Voicebox AI model launched in June this year. Audiobox is said to be able to generate various environmental sounds and natural dialogue voices, and integrates audio generation and editing capabilities to allow users to freely generate their own audio.
Meta’s move is undoubtedly an important breakthrough in the field of AI technology for audio. The launch of Audiobox not only allows users to more conveniently generate the required audio, but also provides more possibilities for audio producers. In addition, Audiobox supports multi-layered sound generation, which means users can generate different levels of sound effects according to their needs.
It is understood that Meta launched the Voicebox AI model in June this year, which uses advanced deep learning technology to achieve high-quality speech synthesis. Audiobox is further optimized and upgraded on this basis, giving it stronger audio generation and editing capabilities.
【来源】https://www.ithome.com/0/736/876.htm
Views: 1