Where I could learn check docs about possible performance optimization, voice tweak and speed ups ?

[lukaLLM]

I managed to run it on Windows and look for some more examples or techniques other than this is this existing, possible voices ?

from melo.api import TTS

# Speed is adjustable
speed = 1.0

# CPU is sufficient for real-time inference.
# You can set it manually to 'cpu' or 'cuda' or 'cuda:0' or 'mps'
device = 'auto' # Will automatically use GPU if available

# English 
text = "Did you ever hear a folk tale about a giant turtle?"
model = TTS(language='EN', device=device)