VoiceCraft is simply the future of voice editing and voice synthesis. We’re practically in science fiction territory here because with just a few seconds of your voice audio, this AI can understand your timbre, your intonation… your flow, basically. And then, off you go, you can make it say whatever you want, and it will sound exactly like you’re the one speaking! It’s both eerie and awesome at the same time.
I invite you to listen to the demo sounds here to form your own opinion. It allows you to do a lot of things like changing a word in a recorded sentence, extending or shortening a passage… etc. It’s truly an essential tool for all audio content creators, podcasters, voice actors, and everyone else.
Here’s an original voice saying this:
“that schedule is one per week and it will probably be like a Wednesday night thing because I plan on doing one to two videos per week.”
And here’s the version processed by the AI, which retains the original voice but also makes small modifications to the text as desired. It lets you make anyone say anything.
“that schedule is one per week and you will start to see a lot more content arriving because I plan on doing one to two videos per week.”
Try voice editing
Try TTS inference
Yes, if malicious people use this to make anyone say anything, that’s concerning. But rest assured, the creators of VoiceCraft have thought of everything. There are ethical safeguards and audio watermarking systems to prevent misuse. We’ll see if it holds up.
I really encourage you to check out VoiceCraft’s GitHub page; it has all the information and links to demos. And if you want to delve deeper, dive into their research paper, it’s fascinating.
