Deep-learning text-to-speech tool for generating voices of various characters
1–10 of 88 posts
Re: Deep-learning text-to-speech tool for generating voices of various characters
#2Welp, after messing around with a few voices I was completely impressed with Glados's. This is really cool because I have no idea how the character's voice was synthesized, but apparently ML can do it for me so props to that.
Re: Deep-learning text-to-speech tool for generating voices of various characters
#3will this be open source eventually?
Re: Deep-learning text-to-speech tool for generating voices of various characters
#4will this be open source eventually?
https://twitter.com/fifteenai/status/1342304487474606081
found an answer.
"There's no point in releasing a poorly done model, and to do so for the sake of popularity would be despicable. My goal is to achieve indistinguishability, which I certainly know is possible. Anything short of near-perfection is unacceptable. "
Re: Deep-learning text-to-speech tool for generating voices of various characters
#5If it doesn’t work on mobile why bother sharing?
Re: Deep-learning text-to-speech tool for generating voices of various characters
#6From the about section:
> How much does maintaining the servers cost? > It depends on the amount of traffic, but the minimum baseline is around several thousands of US dollars every month. This is expected as inference is very GPU intensive and a sufficient number of instances need to be spun up to handle thousands of requests coming in every minute. Everything is paid out of pocket.
Wow, impressive commitment for something that's free.
Re: Deep-learning text-to-speech tool for generating voices of various characters
#7If it doesn’t work on mobile why bother sharing?
It works on mobile for me. Tried it on both safari and chrome on an iPhone running iOS 14.
Re: Deep-learning text-to-speech tool for generating voices of various characters
#8While you're typing the word the text box don't show it, when you complete the word then it shows on the text box. Brave, Android.
Besides that, amazing results. Congratulations.
Re: Deep-learning text-to-speech tool for generating voices of various characters
#9This was amazing!
Re: Deep-learning text-to-speech tool for generating voices of various characters
#10Welp, after messing around with a few voices I was completely impressed with Glados's. This is really cool because I have no idea how the character's voice was synthesized, but apparently ML can do it for me so props to that.
I'm pretty sure the real Glados voice effect is mostly pitch correction and formant shifting. You can do it with Melodyne at least (which, to be fair, is also computer magic-- just a different kind than this one!)
I just found a video on YT with an example of recreating this in Melodyne: https://youtu.be/1oQn66gvwKA