Stability AI has launched Stable Audio Open, an open-source model designed to generate short audio samples, sound effects, and songs using text prompts. The model, which can create audio up to 47 seconds long, is trained on audio data from FreeSound and the Free Music Archive. This release marks a significant step in Stability AI's expansion of its generative audio capabilities. The model is optimized for generating sound effects and production elements, making it suitable for applications in video and film production. However, its use is prohibited for commercial purposes. According to TechCrunch, Stable Audio Open achieves the best FD results among competitors in generating sound effects.