**Stability AI 推出 Stable Audio 3.0,支持长达六分钟的音轨并开源权重**

_Stability AI launches Stable Audio 3.0 with up to six-minute tracks and open weights_

> Stability AI 发布了新一代音频模型 Stable Audio 3.0,其中三个模型开源了权重。该模型能生成最长六分钟的音乐音轨,并声称完全基于授权数据训练。

**来源信息**
- **来源**:The Decoder:AI News(RSS)
- **分类**:ai-models
- **发布时间**:2026-05-20 22:59(北京时间)
- **原文**:[打开原文](https://the-decoder.com/stability-ai-launches-stable-audio-3-0-with-up-to-six-minute-tracks-and-open-weights)