Meta (formerly Facebook) has released ‘MusicGen,’ an AI-powered music generator that converts text description and melody into audio.

The code and models for open research, reproducibility, and the music community were also released by the company.

“We present MusicGen, a simple and controllable model for music generation.” Text and melody can both be used to trigger MusicGen. “We release code (MIT) and models (CC-BY NC) for open research, reproducibility, and the music community,” said Felix Kreuk, Research Engineer at Meta AI research, on Twitter.

“MusicGen is based on the EnCodec audio tokenizer.” MusicGen, in contrast to previous work, is a single-stage transformerLM that employs efficient token interleaving patterns, eliminating the need for cascading several models (e.g., hierarchically or upsampling),” he added.

Furthermore, MusicGen was trained on 20,000 hours of music, including 10,000 “high-quality” licensed music tracks and 3,90,000 instrument-only tracks from the Shutterstock and Pond5 stock media libraries, IANS reported from SanFrancisco.

However, Meta isn’t the first company to provide an AI-powered music generator.

Google launched ‘MusicLM’ in May, a new experimental AI tool that can generate high-fidelity music in any genre given a text description.

The tool, which was first announced in January of this year, is now available to the general public.

The text-to-music AI tool is available in the AI Test Kitchen app, which is available on the web, Android, and iOS