You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
To make the experience more seamless, a hesitation noise could be used to mask the latency inherently introduced by the LLM. These would be multiple samples extracted from all the original voice actor datasets, unless the TTS is able replicate them.
It would be noises such as:
breathes in
lipsmack
sighs
ahem
ugh
hmm
gasp
aah
yawn
sniff
The text was updated successfully, but these errors were encountered:
To make the experience more seamless, a hesitation noise could be used to mask the latency inherently introduced by the LLM. These would be multiple samples extracted from all the original voice actor datasets, unless the TTS is able replicate them.
It would be noises such as:
The text was updated successfully, but these errors were encountered: