I wonder if Kal'stit heard about this recording before ? I pretty sure Doctor knew about this , more than anyone . Even Kal'stit and Amiya dont even know about this
EVERYONE’S TALKING ABOUT THE GLITCH BUT NO ONE TALKING ABOUT HOW HANDSOME CHILDE IS LIKE ❤❤❤ (i’m a 100000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000% childe simp)
Can you try doing the same thing with Gilgamesh or rasputin from fate/grand order? I'm highly curious what it sounds like and might try this if its similar enough,
My guy. I need to know some things. How big were the clips you fed to her? 1 minute ones? 5 minute ones? Whats the stability and similarity sliders? You inspired me to turn some waifus into proper bilinguals too!
The entire voice lines. I only play around with stability. I dont touch clarity that much but it depends on audio quality. I put it high clarity if the audio is high quality
@@yaek7311 I used the Japanese voice samples I got from RU-vid. I try finding the whole voice lines without any background music. For clarity, is either 75% or more. For this W one, I don't remember what clarity I used but it's constant. Depending on the audio file, if the quality is good I put it on high, and its stays there for the rest of the voice lines. Stability, really depends on your character's personality. For W I put it on lower than 50%, although it goes weird and crazy sometimes, I play around with it until I find what I think is perfect.
@@Kulgia Thank you! It sounds to me like you used one Japanese voice sample per one English line output. Is that correct? Or did you combine all samples you found into one file to clone a universal voice for all English lines?
@@yaek7311 It's the latter. I combine all the samples. I find that easier than doing one by one Japanese sample per English voice output, which I doubt it'll come out any better if doing that.
My god, she have a voice tone just like as JP va, but in English. Exactly what I have been imagined about EN skadi Edit: wait bruh, I heard that this is AI generated is this true lul
Yeah it's AI generated. AI generation has become something that can replicate a human's voice VERY closely. Unfortunately, the voice doesn't go very far in terms of emotion, but the model has really good, and can go places if it has more time to develop.
Skadi and Kal'tsit both have an "emotionless" tone of voice so they're easy for AI to replicate. There's a lot of characters in Arknights who have that tone of voice, the hardened "strong woman" type such as Texas, Gladiia, Saria, Mudrock, etc.