Google’s MusicLM is Astoundingly Good at Making AI-Generated Music, But They’re Not Releasing it Due to Copyright Concerns

MusicLM by Google AI music generator

Google have trained an Artificial Intelligence model on 280,000 hours of music to be able to generate impressive songs based upon text prompts. 

According to the MusicLM github, 

    “Our experiments show that MusicLM outperforms previous systems both in audio quality and adherence to the text description. Moreover, we demonstrate that MusicLM can be conditioned on both text and a melody in that it can transform whistled and hummed melodies according to the style described in a text caption.”

Some examples include: 

Listen to all of the examples they’ve created here.

Why aren't Google Releasing MusicLM

The main reason Google are hesitant and have no immediate plans to release MusicLM for public use is copyright issues. 

In an internal experiement, they discovered that around 1% of the music generated was a direct replica of a piece of music is was trained on. 

      “We acknowledge the risk of potential misappropriation of creative content associated to the use case,” the co-authors of the paper wrote. “We strongly emphasize the need for more future work in tackling these risks associated to music generation.” 

The 1% is enough for them to be hesitant. But even if the music never replicated the music it was trained on, the issues around copyright are still only just being considered. 

Music, or any content for that matter that any AI model is trained on generally took countless hours to create. And now an AI comes along, uses someone else’s work to produce content of it’s own, is that really fair? It’s a fascinating new dilemma these researchers are going to have to deal with. 

Recent News