Metas open-source MusicGen AI uses text to create song genre mashups

Now Both Google and Meta have AI Music Generators. Google released MusicLM last month and Meta’s MusicGen just released.

MusicGen can take prompts and samples to create a new(ish) tune.

How will this affect music moving forward? Will these tools help push artists to new heights or will we be awash in heartless melodies?

Via Engadget:

Meta’s Audiocraft research team has just released MusicGen, an open source deep learning language model that can generate new music based on text prompts and even be aligned to an existing song, The Decoder reported. It’s much like ChatGPT for audio, letting you describe the style of music you want, drop in an existing tune (optionally) and then clicking “Generate.” After a good chunk of time (around 160 seconds in my case), it spits out a short piece of all-new music based on your text prompts and melody.

Learn more!

from Adafruit Industries – Makers, hackers, artists, designers and engineers! https://ift.tt/GHjfyFx
via IFTTT