Emotional and prosody control via TTS and Inversion Editing

TTS SETTINGS

Method ? Resynthesis depth ? RF gamma ? RF eta ? RF inv steps ? RF inject ? RF source ? Steps ? Text CFG ? Speaker CFG ? CFG min t ? CFG max t ? Speaker CFG cutoff ?

Enable cutoff

Fade start t ? Stop t ? Fade slope ? Speaker CFG channels ?

Enable gain

HF ratio ? HF power ? CFG norm clip ? CFG delta log ?

Log norms

Seed ? Speaker KV ?

Enable scaling

KV scale ? KV min t ? Max layers ?

ADAPTERS

Checkpoint ? Weight ? Automate ?

Automate

Text prompt CLSP prompt ? Reference audio CLSP

No checkpoints loaded.

REFERENCE MEAN GUIDANCE

RMG ?

Enable

Strength ? Schedule ? Start t ? End t ?

Emotional and prosody control TTS

INPUT VOICE/PROSODY

RECOGNIZED CAPTIONS

VOICE IDENTITY

TTS CAPTIONS

GENERATE PANEL

TTS SETTINGS

ADAPTERS

REFERENCE MEAN GUIDANCE

GENERATED OUTPUT