ElevenLabs just released their  improved Text to Sound Model for all users. 

It can generate sound effects, short instrumental tracks, soundscapes, and a wide variety of character voices from a text prompt.

All you have to do is describe the sound you need, click generate, and check out the samples.

Sound effect clip libraries are already available in the market for creators, filmmakers, and video game developers. However, these libraries can sometimes be costly or make it challenging to find the exact sound needed.

ElevenLabs partnered with the stock media platform Shutterstock to develop a library and train its model using Shutterstock's audio clips. 

Shutterstock has licensed its content libraries to numerous AI companies, including OpenAI, Meta, and Google.