Vocal Synthesis Jay-Z AI voice impersonations
Occurred: April 2020
An pseudonymous music creator named 'Vocal Synthesis' used AI to generate deepfaked tracks of rapper Jay-Z's reciting Shakepeare's 'To be, or not to be' and Billy Joel's Don't Start the Fire. The incident resulted in a DCMA take-down order and a debate about the effectiveness of existing copyright law for deepfakes.
Voice Synethesis’ videos are created by feeding Google’s Tacotron 2 text-to-speech model with Jay-Z's songs and lyrics, and having the synthetic voice read pre-written text. Other videos created by Voice Synthesis include Tucker Carlson reading the Unabomber Manifesto and Bill Clinton reciting 'Baby Got Back'.
Jay-Z's agency entertainment Roc Nation LLC claimed copyright infringment and argued 'This content unlawfully uses an AI to impersonate our client’s voice.' YouTube took down the videos, but later reinstated them on the basis that the DCMA request was 'incomplete'. The videos remained on decentralised, open source platform LBRY.
As Input noted, Vocal Synthesis 'transformed Jay-Z’s discography in a humorous way for no commercial benefit and clearly labels all videos as speech synthesis'. Vocal Synthesis hit back by creating a deepfake video of Barack Obama and Donald Trump explaining that they had no malicious intentions and were 'disappointed' with by Jay-Z and Roc Nation's response.
Operator: Vocal Synthesis; Google/YouTube; LBRY
Developer: Vocal Synthesis
Google (2017). Tacotron 2: Generating Human-like Speech from Text
News, commentary, analysis
Published: July 2023