Microsoft To Do
What will you do with To Do?
Start new thread

VALL-E - AI that can mimic a person's voice with just 3 second sample

by•
VALL-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second sample. VALL-E synthetically preserves speaker's emotion and acoustic environment.

Add a comment

Replies

Best
Hunter
Now anyone can have James Earl Jones (or anyone else for that matter!) voice their radio ads. Also relevant given Apple Books's just-announced audiobooks.
how does one try it? followed links ...nothing
Hunter
it's not publicly available to test yet, but if you follow the links, you'll see a bunch of audio file tests that show what it's capable of.
Impressive … most impressive.
Should give it a try
The product is great and the launch is successful.
Cool...
Congrats on the Launching. We need more tools like these to enhance our creativity. Keep going, guys!
Wow! Only a 3 second sample. I'd rather see some examples in the images rather than how it works though Congrats on your launch
Hunter
did you click thru to any of the links?
Yep. I was mainly referring to the PH post, not the website. My bad, should have specified.
What an innovative idea! Congratulations on a job well done!
How do I try it ?
Frankly terrifying - but incredible none the less 😅 Awesome launch, ?makers!
Nice!
12
Next
Last