Meta Launches AudioCraft

According to a blog post, Facebook and Instagram’s parent company, Meta, launched a suite of generative artificial intelligence (AI) models dubbed AudioCraft on August 2 to create music from various inputs.

Included in the set of generative AI tools are MusicGen and AudioGen, which use text-based inputs to generate new audio, and EnCodec, which “allows for higher-quality music generation with fewer artifacts.”

In its announcement, Meta noted that its MusicGen model was trained using its own music or music that it had “specifically licensed.”

This occurs amid significant controversy surrounding the training of AI with copyrighted works from various artistic disciplines, including a lawsuit against Meta for copyright infringement during AI training.

Meta has made MusicGen and AudioGen available to the “research community” and developers in multiple sizes.

As it develops more sophisticated controls, the company anticipates that the models will be helpful to both amateurs and professionals in the music industry.

“With even more controls, we think MusicGen can turn into a new type of instrument — just like synthesizers when they first appeared.”

The chief executive officer of the Recording Academy, Harvey Mason Jr., compared the advent of AI-generated music to the introduction of synthesizers.

Meta’s release of its generative AI music tools follows Google’s MusicLM’s introduction of similar devices that convert text to music.

In May, the company announced that its AI Test Kitchen platform was admitting “early testers” of its products.

Meta has actively released new AI tools alongside numerous other tech titans, including Google and Microsoft, in a competition to develop and deploy the most potent models.

On August 1, Meta announced the release of new AI chatbots with personalities, which users of its platforms can employ as search assistants and “fun products to play with.”