AudioCraft, now available for experimentation, allows users to create new music based on text prompts alone. This means musicians can “explore new compositions without having to play a single note on an instrument”, according to Meta.
This means users can simply enter a prompt, such as ‘Sirens and car engines approaching and passing while it rains’, and AudioCraft will generate an audio sample that can be used for business or personal ventures. This means content creators and influencers can create specific and unique audio and music for campaigns easily.
While other companies such as Google have also created large language models that can generate sounds and audio, it is not as accessible as AudioCraft will be.
According to Meta, “The AudioCraft family of models are capable of producing high-quality audio with long-term consistency, and they’re easy to use. With AudioCraft, we simplify the overall design of generative models for audio compared to prior work in the field — giving people the full recipe to play with the existing models that Meta has been developing over the past several years while also empowering them to push the limits and develop their own models.”
Artificial Intelligence is also being utilized by TikTok users to create music covers. Recently, an AI-generated cover of The Weeknd’s Starboy sung by Taylor Swift went viral on the video-sharing application, getting over 870 thousand views.
Already, AI-generated audio is taking the social media world by storm. With AudioCraft, the creation of content and new, unique audio will become easier.