Creating music on YouTube with AI-powered Dream Track

By: Prof. Ts. Dr. Manjit Singh Sidhu

Google is currently at the forefront of testing groundbreaking artificial intelligence (AI) capabilities for YouTube, with the aim of revolutionizing music composition for users. This pioneering feature, known as Dream Track, has been discreetly rolled out to a select group of content creators based in the United States. Dream Track is meticulously designed to effortlessly generate 30-second audio clips that emulate the distinctive styles of renowned musical artists who have collaborated with YouTube.

Presently, Dream Track supports the musical styles of nine prominent musicians, namely Alec Benjamin, Charlie Puth, Charli XCX, Demi Lovato, John Legend, Papoose, Sia, T-Pain, and Troye Sivan. The unveiling of this cutting-edge technology was showcased in a demo video, demonstrating how a simple text prompt such as “A ballad about how opposites attract, upbeat acoustic” can seamlessly produce a short track echoing Charlie Puth’s signature style.

Google’s exploration into the realm of AI has reached new heights with its latest venture on YouTube, where they are testing cutting-edge capabilities that could redefine how music is created and consumed. Beyond the remarkable capabilities of Dream Track, YouTube is also introducing Music AI tools that empower creators to craft 30-second musical pieces without the need for traditional instruments. In a captivating demonstration, humming a melody while inputting “saxophone solo” as text can magically transform the input into a captivating saxophone tune. The marquee feature, Dream Track, has already been quietly introduced to a selected group of content creators in the United States.

Expected to be available later this year, participants in YouTube’s Music AI incubator program will gain exclusive access to these revolutionary creation tools. The driving force behind these features is Lyria, a generative music model developed by Google’s DeepMind division. Lyria ensures that tracks created with its technology contain an indiscernible SynthID watermark, persisting even if the audio undergoes modifications. This watermark is a crucial component, facilitating the identification of AI-generated content.

The incorporation of AI into music composition is part of a larger trend toward the spread of AI-enabled generative content production. While these breakthroughs promise exciting possibilities, they also raise concerns about how such technology may disrupt established musical traditions and challenge traditional views of creative merit. The full degree of their influence has yet to be determined as these technologies grow and change the landscape of creative expression.

This endeavour into AI-generated music not only demonstrates Google’s technological expertise, but also emphasizes the growing integration of AI into numerous facets of our daily life. As people anxiously anticipate more access to these elements, the convergence of technology and creativity takes centre stage, setting the path for a future in which artistic expression’s boundaries are constantly stretched and redefined.

The integration of AI into music composition is just one aspect of a larger trend in AI-enabled generative content production. While these breakthroughs offer exciting possibilities and new

creative expressions, they also raise concerns about the possible change of traditional musical traditions and the changing nature of artistic ability.

As we look more into the implications of AI in music composition, it becomes clear that the relationship between technology and creativity is experiencing dramatic change. The combination of AI with creative expression not only demonstrates Google’s technological power, but also foreshadows a future in which the limits of creativity are constantly stretched and redefined. This view into a musical world demonstrates that technology not only complements, but actively influences, the way we produce and enjoy art.

Dream Track’s integration into YouTube is part of a broader initiative to explore the capabilities of AI in the realm of creative expression. Beyond its utility in music composition, YouTube is actively showcasing Music AI tools that liberate creators from the constraints of traditional instruments. In an engaging display, a video demonstration reveals how humming a melody and inputting “saxophone solo” as text can seamlessly transform the hummed tune into a delightful saxophone piece. This versatility in musical creation is poised to empower a new wave of artists and creators, providing them with tools to bring their musical visions to life without the need for extensive instrumental training.

Scheduled to be available later this year, these groundbreaking creation tools will initially be offered to participants in YouTube’s Music AI incubator program. The driving force behind these revolutionary features, Lyria, is a generative music model developed by Google’s DeepMind division. What sets Lyria apart is its ability to embed an indiscernible SynthID watermark into the tracks it generates. This watermark, designed to persist even through modifications to the audio, serves as a unique fingerprint, allowing for the identification of content that has been AI-generated. It’s a measure aimed at maintaining transparency and authenticity in a landscape where technology and creativity converge.

As the implications of AI in music composition continue to unfold, there is a broader trend emerging in the realm of AI-enabled generative content creation. These advancements hold the promise of not only exciting possibilities and novel creative expressions but also raise questions about the potential transformation of established musical traditions and the evolving nature of artistic talent.

While the excitement builds for wider accessibility to these features, the ongoing integration of AI in various aspects of our daily lives takes centre stage. The synthesis of technology and creativity, exemplified by Google’s foray into AI-generated music, underlines the transformative moment we are witnessing in the evolution of music and artistic expression.

This journey into uncharted territory not only showcases the technical capabilities of AI but also prompts a re-evaluation of how we perceive and engage with creativity in the digital age.

……

The author is a Professor at the College of Computing and Informatics, Universiti Tenaga Nasional (UNITEN), Fellow of the British Computer Society, Chartered IT Professional, Fellow of the Malaysian Scientific Association, Senior IEEE member and Professional Technologist MBOT Malaysia. He may be reached at manjit@uniten.edu.my