Meta Releases AI Music Generator AudioCraft

AI is continuing to come for musicians' jobs, as Meta has released the AI music generator AudioCraft. Able to generate high-quality audio and music from text prompts, the open-source framework is Meta's contribution to music in the AI space.

What is it? AudioCraft is a collection of three models: MusicGen, AudioGen and EnCodec. MusicGen, which was trained with Meta-owned and specifically licensed music, generates music from text prompts, while AudioGen, which was trained on public sound effects, generates audio from text prompts. The EnCodec decoder allows higher quality music generation with fewer artifacts. Meta also shared its pre-trained AudioGen models, which allow users to generate environmental sounds and sound effects as well as all of the AudioCraft model weights and code. 

AudioCraft works for music, sound, compression, and generation, all in the same place, helping Meta's goal of making the program accessible and able to quickly help users flesh out their ideas.

What they're saying: Meta is open-sourcing the models, which the company touts as "capable of producing high-quality audio with long-term consistency," which current music AI generation models don't have, and are "easy to use."

"Imagine a professional musician being able to explore new compositions without having to play a single note on an instrument. Or a small business owner adding a soundtrack to their latest video ad on Instagram with ease," Meta shared. "Having a solid open source foundation will foster innovation and complement the way we produce and listen to audio and music in the future. With even more controls, we think MusicGen can turn into a new type of instrument — just like synthesizers when they first appeared."

Meta continued, "We see the AudioCraft family of models as tools for musicians and sound designers to provide inspiration, help people quickly brainstorm and iterate on their compositions in new ways."