VibeVoice Text-to-Speech Demo

Generate single or multi-speaker audio. For single-speaker monologues, the system automatically uses a specialized node with text chunking.

Upload a short audio clip (3-30 seconds, clear audio) for each speaker you want to clone.

0 4294967295
5 100
0.5 3.5

Enable for more varied, less deterministic output.

0.1 2
0.1 1
100 500