Re:Faux Rogan
by petrochukm on Sunday May 19, 2019 @12:20PM
(#19954037)
Hey!
> I honestly wonder if we are a year or two away from this being possible.
We've launched a service for adding voiceovers 2 months ago... https://wellsaidlabs.com/
Techcrunch: https://techcrunch.com/2019/03/07/wellsaid-aims-to-make-natu...
GeekWire: https://www.geekwire.com/2019/ai2s-incubator-gives-birth-wel...
> How can I do this with my voice?
To prevent abuse of our technology, we need to review your use-case before creating you a custom voice.
> The google WaveNet stuff is pretty good but still not there yet [1].
Google WaveNet is not built for high-quality voice-overs but rather for cheap and fast text-to-speech.
Re:Faux Rogan
by soulofmischief on Sunday May 19, 2019 @05:07AM
(#19952297)
I'd start with recording hundreds of hours of you having typical conversations with a wide variety of context, emotion and intensity.
Once someone gets an implementation of https://sample-efficient-adaptive-tts.github.io/demo/ [0] working that should be good enough (quality-wise).
Wow, the samples on their front page are absolutely awful. Do they have good ones?
Re:Faux Rogan
by james_s_tayler on Sunday May 19, 2019 @08:18PM
(#19956488)
Yeah, I feel like this has to be a joke compared to the level of quality Faux Rogan is pumping out.
I imagine eventually, you could have some type of transcript that's annotated with speech synthesis markup language (SSML). Then, you have a CI/CD pipeline that would run this text-to-speech engine and regenerate the audio. I could then pair this up with the video. I honestly wonder if we are a year or two away from this being possible.
[1] https://cloud.google.com/text-to-speech/