Multi Voice Selection With Natural Prosody

via “controllable prosody and style transfer from reference audio”

text-to-speech model by undefined. 6,61,227 downloads.

Unique: Separates speaker identity from prosodic style via dual-pathway encoder architecture — prosody encoder operates independently from speaker encoder, allowing style transfer across different speakers without voice blending artifacts

vs others: More granular prosody control than XTTS-v2 (which bundles style with speaker) and faster than Vall-E's iterative refinement approach