Bosun Posted April 3, 2023 Posted April 3, 2023 Posited this in another response, but thought I'd start a thread on it. Currently, the AI tech exists to 'deepfake' voices. That means you could type out a phrase and have an AI interpret it into the voice with tonal inflection and pacing that resembles the sample data. So Does anyone think it would be possible to create a plug-in for the Jester AI, that would allow the plug-in to use an AI algorithm to read and listen to Jester AI as a sample, and then choose from a bank of other sample audio that it could 'swap voices' with? Essentially, being able to 'Hot Swap' in different voices for Jester, after running all those files through a processor AI to 'deepfake' a new voice from the example audio file. I'm imagining being able to take famous characters from movies, your best friend, etc, and after a small sample of maybe 40-50 lines, being able to have the AI deepfake the rest of the 10,500 samples. Possible? Or pipe dream?
IronMike Posted April 3, 2023 Posted April 3, 2023 Here, this might interest you. 1 Heatblur Simulations Please feel free to contact me anytime, either via PM here, on the forums, or via email through the contact form on our homepage. http://www.heatblur.com/ https://www.facebook.com/heatblur/
Bosun Posted April 4, 2023 Author Posted April 4, 2023 Mike, Thanks! Saw that mod, and it just sparked the idea - "what if it didn't take recording 10,500 samples individually to change the voice?" This wasn't so much a feature request as a more academic ponder on what would be possible given current AI tech.
_BringTheReign_ Posted April 4, 2023 Posted April 4, 2023 On 4/3/2023 at 4:58 PM, IronMike said: Here, this might interest you. 8 hours ago, Bosun said: academic ponder on what would be possible given current AI tech. I am working on a plugin that takes the file names, a script, and a few macros to spit out a voice of your choosing. It's not dynamic, but it would be fairly easy to swap between voices with OVGME. It's a learning experience for me so it is taking some time, but I cannot wait to share it open-source when it is ready! 2 .
Temetre Posted April 9, 2023 Posted April 9, 2023 I dont think this is really about AI, its is just text to speech. And yup, there has been quite convincing TTS engines for quite a while now. 1
Bozon Posted April 16, 2023 Posted April 16, 2023 Ooohh I want Jester with Arnold Schwartzenegger’s voice, or even better Darth Vedar’s voice! “I find your lack of flares, disturbing…” 1 “Mosquitoes fly, but flies don’t Mosquito” :pilotfly: - Geoffrey de Havilland. ... well, he could have said it!
Recommended Posts