YouTube, in collaboration with Google’s DeepMind Artificial Intelligence lab, has launched an experimental AI music tool currently in beta called “Dream Track“. This tool allows users to generate original song snippets up to 30 seconds long, featuring the AI-generated voice of a selected artist. The tool is currently available to a small group of artists and creators, and YouTube is encouraging feedback to inform future products and tools.
The Dream Track tool works by having a user type an idea into the creation prompt and select a participating artist. The tool then produces an original song snippet featuring the AI-generated voice of that artist. The AI technology behind Dream Track is powered by Lyria, which is Google DeepMind’s most advanced music-generation model to date.
Nine popular artists have co-signed to be a part of this project. These artists include Charlie Puth, Demi Lovato, John Legend, Sia, T-Pain, Troye Sivan, Charli XCX, Alec Benjamin, and Papoose. These artists have expressed their interest and openness to this experiment, viewing it as a test for what AI music creation can do.
In addition to Dream Track, YouTube has also showcased other Music AI Tools designed to let users build out music tracks, often without playing a traditional instrument. For instance, these tools can create a saxophone track by combining a hummed melody with the text prompt “saxophone solo”. Other demonstrations include beatboxing being turned into a drum loop, singing becoming an orchestral score, or chords from a MIDI keyboard creating a vocal choir.
However, the introduction of these AI tools has raised concerns about potential misuse and copyright issues. To address these concerns, YouTube has announced new policies requiring creators to indicate when they’ve uploaded AI-generated content. The platform has also developed a feature called SynthID, which watermarks any of the AI-generated audio it produces so it can be identified as such. In terms of copyright, YouTube has announced new policies requiring creators to indicate when they’ve uploaded AI-generated content. The AI content produced on YouTube’s features will also be watermarked for disclosure. This is a response to the potential risks that the use of such AI tools could constitute copyright infringement. If an AI tool copied specific melodies or lyrics, for example, that would likely constitute copyright infringement. However, well-built AI tools are generally designed to copy the general sound and feel of music, in part to avoid allegations of copyright infringement.
YouTube’s AI-generated music tool in currently in beta, Dream Track, represents a significant step forward in the integration of AI technology in music creation. With the participation of renowned artists, this tool not only offers a new way of creating music but also opens up a discussion about the future of AI in the music industry. As history has proved time and time again, artists shouldn’t be ignorant and/or have their head buried to the changing environment of how music is created and distributed or be left behind.
