Network Security Internet Technology Development Database Servers Mobile Phone Android Software Apple Software Computer Software News IT Information

In addition to Weibo, there is also WeChat

Please pay attention

WeChat public account

Shulou

YouTube launches AI tools that can imitate famous singers and can compose songs using words or humming.

2025-01-15 Update From: SLTechnology News&Howtos shulou NAV: SLTechnology News&Howtos > IT Information >

Share

Shulou(Shulou.com)11/24 Report--

CTOnews.com YouTube is testing new generative AI features that allow users to compose music by typing text or humming a melody. One feature called Dream Track, already available to some creators on the platform, automatically generates 30-second music clips based on the style of famous artists. The feature mimics nine different artists, all of whom were YouTube's partners in developing the feature. YouTube also showcases some new tools that can generate music by humming.

YouTube said it is currently testing Dream Track with "a small selection of American creators" to create music in the style of nine artists; Alec Benjamin, Charlie Puth, Charli XCX, Demi Lovato, John Legend, Papoose, Sia, T-Pain and Troye Sivan. Official video demos show how to create Charlie Puth-style music with prompts such as "a ballad about opposites attracting, upbeat soundtrack" or "sunny morning in Florida, R&B." The software can generate lyrics, accompaniment, and AI synthesized sounds in artist style.

CTOnews.com notes that in addition to Dream Track, YouTube also showcases other music AI tools designed to allow users to create music without traditional instruments. In a demo video, YouTube shows how to compose saxophone music by combining humming melodies with textual cues like "saxophone solo." There are also videos showing how to turn rhythm ventriloquism into drum loops, singing into orchestral music, or MIDI keyboard chords into vocal choruses.

YouTube says participants in its music AI incubator will be able to test the tools later this year.

These new AI tools are powered by Lyria, a music generation model developed by Google's DeepMind. In a blog post for DeepMind, the company said music generated using Lyria will carry a SynthID watermark that cannot be heard by the human ear and can be retained when the music is modified. So even if someone adds more noise to the music, compresses it into MP3 files, or speeds it up, it can still theoretically be determined that it contains AI-generated audio from Lyria.

It's worth mentioning that just a few days ago YouTube announced that it would remove AI music covers and AI-generated content imitating characters in the coming months.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.

Views: 0

*The comments in the above article only represent the author's personal views and do not represent the views and positions of this website. If you have more insights, please feel free to contribute and share.

Share To

IT Information

Wechat

© 2024 shulou.com SLNews company. All rights reserved.

12
Report