Suno 推出 v3 音乐生成模型
阅读原文· suno.com音乐生成平台 Suno 发布了 v3 模型,这是其首个能生成广播级质量音乐的模型,支持用户在数秒内创作完整的两分钟歌曲,现已对所有用户开放。v3 在音频质量、风格多样性及提示词遵循性上进行了改进,减少了模型幻觉并提升了歌曲结尾的自然度。该模型专为原创音乐设计,不支持对其他艺术家的参考,并部署了不可听水印技术以检测 AI 生成内容。v4 模型已在开发中。
At Suno, we are building a future where anyone can make music. You can make a song for any moment in any major language with just a few short words. Award-winning artists use Suno, but our core user base consists of everyday people making music — often for the first time.
Today, we are excited to introduce v3, our first model capable of producing radio-quality music. v3 enables you to make full, two-minute songs in seconds and is now available to all users at https://app.suno.ai. Make your own song with v3 today!
Features & Improvements
Thank you to all of our Pro and Premier members, who helped us test and improve v3 Alpha. v3 incorporates your feedback and features a number of improvements, most notably:
◦ Better audio quality
◦ More styles and genres
◦ Improved prompt adherence, including fewer hallucinations and more graceful endings