Description
Link - Trained on exactly 26 minutes of raw audio from Dr. Sbaitso running on DOSBox and captured with built-in audio capture. To match SCP-079, I shifted down the pitch. 20k The low amount of epochs is due to the low complexity of the voice and the large amount of training data. I recommend setting the feature ratio at 1.
Comments
No comments yet. Start the conversation!
Add a comment
Post
Samples
New
Classic
1. Singing
Male
English
2. Singing
Female
English
3. Singing (Dry)
Female
English
4. Singing (High)
Female
English
5. Singing 2
Male
English
6. Singing (Dry)
Male
English
7. Singing (Dry, High)
Male
English
Pitch
0
Weekly Metrics
Users also tried
More to explore
Loading more