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



About | Details |
---|---|
Name: | VALL-E |
Submited By: | Derick Koelpin |
Release Date | 2 years ago |
Website | Visit Website |
Category | Audio |
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.
Super cool idea! Discovered it a few days ago on Twitter, and was stoked by how good the results were!
11 months ago
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
1 year ago
Congrats on the Launching. We need more tools like these to enhance our creativity. Keep going, guys!
1 year ago
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 <a href="https://www.producthunt.com/posts/apple-books-digital-narration" target="_blank" rel="nofollow noopener noreferrer">Digital Narration</a> audiobooks.
1 year ago