deep fakes are a big deal at the moment

What it does

text to speech in anyone's voice with mere seconds of audio

How I built it

pytorch on google cloud

Challenges I ran into

I couldn't get the visual part to work

Accomplishments that I'm proud of

sheer amount of coding

What I learned

how to use google cloud

What's next for Real Time Neural Voice Synthesizer

more alternate history videos

Share this project: