Stability AI Launches Stability Audio 3.0 for Songs Up to 6 Minutes
Stability AI 推出音频模型 Stability Audio 3.0,可生成最长 6 分钟专业级歌曲
Stability AI launched the Stability Audio 3.0 audio generation model family with four sizes ranging from 459 million to 2.7 billion parameters; the small model targets on-device use and generates audio under 2 minutes locally, while medium and large models support full music creation beyond 6 minutes and 20 seconds.
Why it matters: Stability AI released four audio models, the two smallest run locally, the mid and large models push generation to 6 minutes 20 seconds, double the previous generation, and the small and mid models are open-sourced.