ElevenLabs has introduced "Text to Sound," an AI Audio model that generates sound effects, instrumental tracks, soundscapes, and character voices from text prompts. This new tool aims to assist creators, including those in film, television, video games, and social media, by providing high-quality audio content quickly and affordably. Partnering with Shutterstock, ElevenLabs fine-tuned the model using Shutterstock's extensive audio library, enhancing the tool's versatility.