Holly Herndon Announces "Digital Twin" Holly+
The AI deepfake tool will allow users to convert existing audio into sounds produced by Herndon's voice
Developed in collaboration with machine-learning music innovators Never Before Heard Sounds, Holly+ will allow "for anyone to upload polyphonic audio and receive a download of that music sung back in [Herndon's] distinctive processed voice."
Read Herndon's statement about the new tool:
Vocal deepfakes are here to stay. 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.
Hear samples of the Holly+ tool in action — including an AI rework of the X-Files theme song — below, and learn more about Herndon's "twin" here.
I'm working with @ourZORA to create a place where people can own artworks made with my voice 🦾— Holly Herndon (@hollyherndon) July 14, 2021
and will be using the @OpenLawOfficial Tribute DAO framework so friends and family can vote on official usage, and how to use the proceeds to fund new tools to share with everyone 🛠 pic.twitter.com/7NFqdHxqcJ