Fish Audio's Drama 3 is claimed to be the top open TTS model
A user says transcript meta tags can control emotion, direction and sound effects in Drama 3.
TLDR
A user describes Fish Audio's Drama 3 as the top open text-to-speech model. They say meta tags within a transcript can control emotion, direction and sound effects, and call its voice cloning “pretty good.”
Combined views
—
1 Source, first seen ago
