Ask HN: Are there AI models for generating sounds based on a text and reference?

A user on Hacker News is seeking AI models that can generate sounds based on both text instructions and a reference sound. They've found existing solutions like elevenlabs SFX only support text-to-audio, making it difficult to accurately recreate sounds without a reference. The user also tried Stable Audio 3, but the results were unsatisfactory, leading them to believe that sound generation AI is still in its early stages, similar to image generation in 2016.