Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

YouTube Logo

YouTube is stepping up its AI music capabilities, now allowing select creators in the U.S. to remix popular songs using new features in its Dream Track toolset. Originally launched last year, Dream Track enables creators to generate AI-driven songs using vocal likenesses of stars like Charlie Puth, Charli XCX, Demi Lovato, John Legend, Sia, T-Pain, and Troye Sivan. Today, the platform is adding a new remixing feature that lets creators modify these songs’ styles based on custom descriptions.

Creators selected for this experimental feature can use the “Restyle a Track” option to describe their desired remix style. The AI then produces a 30-second snippet aligned with their creative vision, ready for use in YouTube Shorts.

According to YouTube, if creators want to adjust the genre or mood of a song, they can simply input their vision into the “Restyle a Track” prompt. This will then generate a fresh, unique sound while preserving the original song’s vocals and lyrics.

To ensure proper credit, remixed audio clips are attributed to the original track within the Short and on the Shorts audio page. AI-modified snippets will also display a label to clarify that the music was transformed by AI tools.

Dream Track, powered by DeepMind’s Lyria music generation model, originally launched in November last year, and also includes a tool allowing users to create tracks by simply humming a melody.

Addressing music industry concerns, YouTube preemptively announced in August that it would compensate artists and rights holders for AI-generated uses of their work. In partnership with Universal Music Group (UMG), YouTube has outlined a framework to ensure fair compensation for rights holders whenever their material is used in AI-driven creations.