TTS & voice cloning
VocalBrain
What it is
TTS orchestration, 4-D model router, semantic memory (recalls the right track, zero LB import).
The architect's call
2nd consumer of the klody_memory package with zero Library Brain import — empirical proof the abstraction is right. TTS traps solved empirically (EOS never emitted on multi-sentence text → split on \n).
The code
Private repository — walkthrough over a call
Your data cannot leave the building?
That is precisely the problem I solve. A 30-minute call is enough to scope an audit.