Google is making strides in the field of artificial intelligence with its latest updates to YouTube, which will enable users to create music tracks using just a text prompt or a simple hummed tune. The tech giant is testing new generative AI features on YouTube, with the first one known as Dream Track, which has been rolled out to a few creators on the platform. This feature is designed to auto-generate short 30-second music tracks in the style of famous artists. Moreover, YouTube is also showcasing new tools that can generate music tracks from a hum.
The Dream Track feature is currently being tested with a select group of US creators and has the ability to produce tracks in the style of nine renowned artists, including Alec Benjamin, Charlie Puth, Charli XCX, Demi Lovato, John Legend, Papoose, Sia, T-Pain, and Troye Sivan. The software can generate lyrics, a backing track, and an AI-generated voice in the style of the chosen artist. To demonstrate the capabilities of this feature, YouTube provided video demonstrations showing how a prompt such as “A ballad about how opposites attract, upbeat acoustic” can create a track in the style of Charlie Puth, or “A sunny morning in Florida, R&B” can be used to make a T-Pain song.
The objective of these tracks is to be used with YouTube’s TikTok-style Shorts service. In line with this, YouTube also unveiled a new AI feature called Dream Screen in September, which can generate videos and photos to use as backgrounds.
Participants in YouTube’s Music AI incubator will have the opportunity to test these innovative tools later this year. These new AI tools are powered by a music generation model called Lyria from Google’s DeepMind. According to an accompanying blog post from DeepMind, tracks created using Lyria will carry a SynthID watermark that is inaudible to the naked ear and can be preserved even when a track is modified. This means that even if someone adds more noise to a track, compresses it into an MP3 file, or speeds it up, it should theoretically still be possible to tell that it contains AI-generated audio from Lyria.
It is evident that Google is at the forefront of AI development with its new generative AI features for YouTube. By allowing users to create music tracks from a simple text prompt or hummed tune, Google is revolutionizing the way music is generated and produced. The ability to imitate the style of famous artists and generate music tracks from a hum opens up new possibilities for creators and musicians. Additionally, the incorporation of a watermark in AI-generated tracks adds a layer of authenticity and traceability to the music, ensuring that the origin of the track can be identified even after modifications are made.
The implications of these new AI tools are far-reaching and have the potential to reshape the music industry. With the ability to produce music tracks in the style of renowned artists, creators and musicians can leverage these tools to expand their artistic capabilities and reach new heights in music production. Furthermore, the integration of AI-generated music tracks with YouTube’s Shorts service will offer users a new way to engage with music and create compelling content.
Overall, Google’s new generative AI features for YouTube represent a significant advancement in the field of artificial intelligence and demonstrate the potential for AI to transform the music industry. As these tools continue to be tested and refined, it will be exciting to see how they impact music creation and production, and how they are utilized by creators and musicians to innovate and inspire. The future of music creation and production is on the cusp of a revolution, and Google is leading the charge with its groundbreaking AI features for YouTube.