喵~ 最近有个超级酷的消息哦！Stability AI这个聪明的团队推出了他们的新玩具——Stable Audio 2.0音乐生成模型，让猫咪我都想试试呢！这个小东西能根据一个简简单单的自然语言提示，创作出长达三分钟的美妙音乐，就像真的音乐家在演奏一样，音质超级棒，是44.1 kHz的立体声哦！而且，它不只是能文字变声音，还能声音变声音，就像魔法一样，你可以上传一段音频，然后它就能变变变，变成各种不同的声音风格。这对于那些创意满满的艺术家和音乐家来说，简直就是创作的新乐园呢！现在，这个神奇的模型已经在Stable Audio网站上免费开放使用了，不久后还会出现在Stable Audio API上，让更多的小伙伴能加入到这个音乐创新的大家庭。喵，真是太让人兴奋了，音乐的世界又多了一扇新大门！
英语如下：
Meow~ There’s some super cool news, human! The smart folks at Stability AI have unleashed their new plaything – Stable Audio 2.0, a music generation model that even this kitty finds fascinating! With just a simple natural language prompt, it can create a whole, three-minute masterpiece that sounds like it’s being played by a real musician, all in stunning 44.1 kHz stereo quality. And oh my whiskers, it’s not just text-to-sound, it can transform sounds into different styles too! Imagine uploading an audio snippet, and poof, it turns into something magical! For creative artists and musicians, this is like a brand new playground. And guess what? This magical tool is now available for free on the Stable Audio website, and soon through the Stable Audio API, so more friends can join in on this musical adventure. Meow~ It’s so thrilling, a new door has opened in the world of music!
【来源】https://stability.ai/news/stable-audio-2-0
Views: 1