Following the development of generative AI technology for images and code generation, Stability AI has now ventured into text-to-audio generation. Stability AI, recognized for its Stable Diffusion text-to-image generation AI technology, is now set to publicly release its Stable Audio technology. This debut allows anyone to generate brief audio snippets using basic text inputs. Last July, the company rolled out an upgrade for Stable Diffusion, introducing the SDXL base model for enhanced image composition. Following this, they widened their service offerings beyond imagery to coding with the introduction of StableCode in August.