AI-Powered Andy Warhol Voice Reads His Diary in New Netflix Documentary
Netflix’s upcoming documentary, The Andy Warhol Diaries, includes the digitally produced voice of the artist, who passed away in 1987. Voice cloning startup Resemble AI synthesized Warhol’s voice reading excerpts from his memoir for the film. However, it avoids the controversy surrounding a similar move in last year’s Anthony Bourdain documentary Roadrunner by securing the Andy Warhol Foundation’s approval first.
The Andy Warhol Diaries covers the artist’s life through his letters as collected in his memoir titled the same as the new movie. Warhol never recorded himself reading the book, however. Filmmaker Andrew Rossi turned to Resemble AI and its voice synthesis software to recreate Warhol’s Pittsburgh accented voice. The tech startup’s text-to-speech algorithm produced a model for Warhol’s voice capable of reading out the lines from his letters. The digital voice was then blended with a recording of actor Bill Irwin reading out the lines. The alloyed audio is the final version that viewers will hear in the documentary, which premieres on Netflix on March 9. The importance of hearing Warhol’s words from the book is emphasized in the trailer above.
“The diaries are Andy’s thoughts in Andy’s words,” The memoir’s editor, book,’ Pat Hackett, says in the trailer. “No other part of his work shows this.”
The arguments around the Bourdain documentary’s use of his synthetic voice centered around approvals and permissions from his family and estate. The director Morgan Neville claimed at the time to have heard from Bourdain’s widow, Ottavia Bourdain, and Bourdain’s literary executor that they were okay with the artificial voice, but Ottavia Bourdain pushed back publicly to insist she did not. The Warhol documentary includes a statement on the screen citing permission from the Andy Warhol Foundation, just in case the audience wonders about it.
Resemble AI develops speech software to replicate or synthesize voices for a lot of potential purposes. Entertainment is very much a central pillar, however, as the founders told Voicebot in an interview back in 2019. Improved technology has led to better-sounding voices from smaller recording samples, and the company has branched into applying its voice cloning for translation.
“We can capture the essence of how someone speaks,” Resemble AI co-founder Zohaib Ahmed said in the interview. “And it can be shared in brand new ways.”
The trailer closes with an example of Warhol’s voice recreation. “I’m just a freak. I wasn’t very close to anyone. Although, I guess I wanted to be.”