Ukrainian company to provide AI-generated Darth Vader voice for Disney

27 September, 04:32 PM
Respeecher tool can generate accurate voice models from recorded samples (Photo:techarp.com)

Respeecher tool can generate accurate voice models from recorded samples (Photo:techarp.com)

U.S. mass media and entertainment giant Disney has acquired the right to replicate the voice of veteran Darth Vader voice actor James Earl Jones in future Star Wars productions, using a Ukrainian-made A.I. voice-modeling tool.

Ars Technica, a website covering news and opinions in technology, said in a report on Sept. 26 that the ground-breaking tool is called Respeecher.

Jones, who is 91, has voiced the iconic Star Wars villain for 45 years, starting with “Star Wars: Episode IV – A New Hope” in 1977, and concluding with a brief line of dialog in 2019’s “The Rise of Skywalker.”

Video of day

Now, during the creation of the Obi-Wan Kenobi Star Wars spin-off television series, Jones granted Disney permission to replicate his vocal performance as Darth Vader in future projects, using Respeecher.

Respeecher is a voice cloning product from a company in Ukraine that uses deep learning to model and replicate human voices that produces results practically indistinguishable from the real thing.

Lucasfilm used Respeecher to clone Mark Hamill’s voice for The Mandalorian, and the company thought the same technology would be ideal for a major appearance of Darth Vader that would require dozens of lines of dialog.

Working from archival recordings of Jones, Respeecher created a voice model that could be “performed” vocally by another actor using the company’s speech-to-speech technology.

During production of the Obi-Wan Kenobi show, Russia began its invasion of Ukraine, posing some harrowing challenges for the Respeecher team. However, despite the war, Respeecher is reportedly working on other secret projects – quite possibly for Disney – so expect to hear a lot more from Darth Vader in future.

Vader aside, Respeecher is aware that this kind of technology could pose significant security, social engineering, and even copyright problems if anyone can imitate anyone else’s voice from recorded samples.

In the company’s ethics statement, it says that the firm “does not allow any deceptive uses of our technology” and “does not use voices without permission when this could impact the privacy of the subject or their ability to make a living.”

Follow us on Twitter, Facebook and Google News

poster
Ukraine Today
Fresh daily newsletter covering the top headlines and developments in Ukraine
Daily at 9am EST
Show more news
X