ElevenLabs has introduced an AI Audio model called Text to Sound, which allows users to generate sound effects, short instrumental tracks, soundscapes, and various character voices from text prompts. This innovation follows their previous success in developing a human-like Text to Speech platform and aims to provide creators, such as those in film, television, video games, and social media, with tools to produce high-quality audio content efficiently and at scale. The development of Text to Sound was made possible through a partnership with Shutterstock, which provided a diverse audio library to enhance the model's capabilities. Aimee Egan from Shutterstock expressed excitement over the collaboration, highlighting the innovation as a market first. Users can access the tool by logging in, describing the desired sound, generating options, and downloading preferred samples, with the platform offering a free sound effects generator for exploration.