Synthetic Steve Jobs Interviewed by Deepfake Joe Rogan for AI-Powered Podcast Scripted by GPT-3
Synthetic voice developer Play.ht published an imaginary conversation (since removed) between Apple founder Steve Jobs, who died 11 years ago, and Joe Rogan this week. AI-generated voice clones of Rogan and Jobs gave deepfake voice to a script composed using OpenAI’s GPT-3 language model for the first episode of the new “Podcast.ai” show that Dubai-based Play.ht will use to demonstrate its synthetic speech services each week.
Synthetic Podcast
Play.ht created the Rogan and Jobs voice models using its Peregrine text-to-speech generator, which is designed to simulate human emotion and other nuances realistically. Rogan is relatively easy to build voice models with, as there is plenty of available samples of his voice. Jobs comes off more stilted and with a voice likely trained from his big speeches rather than more conversational sources. The 20-minute script goes all over the place and is quite obviously the product of a language model from comments like Rogan saying Jobs is “a memory from the past” or Jobs calling Rogan buddy and that “it’s nice to sit back in the car and listen to you rant.” Jobs then starts spouting non-sequiturs combining product ideas, Buddhism, LSD, and why Microsoft is a bad company, so it’s arguably a standard episode of Rogan’s show in some ways.
“The episodes are rendered using Play.ht’s ultra-realistic voices, and transcripts are generated with fine-tuned language models. For example, the Steve Jobs episode was trained on his biography and all recordings of him we could find online so the AI could accurately bring him back to life,” the Podcast.ai introduction explains. “We wanted to push the boundaries of what is possible in current state of the art speech synthesis, we wanted to create content that can inspire others to do the same, and there was no one who inspired and impacted the technology world more than Steve Jobs, that’s why in the first episode we brought his voice back to life. At Play.ht, We believe in a future where all content creation will be generated by AI but guided by humans, and the most creative work will depend on the human’s ability to articulate their desired creation to the machine.”
As deepfake Rogan and Jobs point out, “tech is a double-edged sword” and that “you should never trust a computer they can’t throw out a window.”
Follow @voicebotaiFollow @erichschwartz
