#Holly Herndon’s AI Deepfake “Twin” Holly+ Transforms Any Song Into a Holly Herndon Song

Holly Herndon, a prominent voice on the cross-section between AI and the music industry who has prominently used AI in her music, has released a new voice instrument: her AI deepfake “twin,” Holly+. It’s a website where you can upload any polyphonic audio and have it transformed into a download of music sung in Herndon’s voice. Give it a try here and read more details on how it works here.

“Vocal deepfakes are here to stay,” Herndon said in a statement. “A balance needs to be found between protecting artists, and encouraging people to experiment with a new and exciting technology. That is why we are running this experiment in communal voice ownership. The voice is inherently communal, learned through mimesis and language, and interpreted through individuals. In stepping in front of a complicated issue, we think we have found a way to allow people to perform through my voice, reduce confusion by establishing official approval, and invite everyone to benefit from the proceeds generated from its use.”

The Holly+ IP is owned by a DAO (Decentralized Autonomous Organisation) cooperative, and any income generated from the tools’ usage and licensing will go toward the funding of new tool development. The Holly+ DAO will eventually feature an auction site where officially sanctioned artworks will be sold in partnership with the Zora protocol’s Auction House feature. 

Read “The Secret History of Women in Electronic Music Is Just Beginning to Be Told.”