2 Commits

Author	SHA1	Message	Date
Ethanfel	219c74d7ed	fix: three bugs in OmniVoiceMixVoices ... - _resample: squeeze batch dim before torchaudio.Resample (expected 2D) - weight scaling: each clip now trims to natural_length*weight samples, dropping the broken target_per_unit double-multiplication - empty trimmed guard: raise clear error when all weights are 0 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-04-05 19:04:54 +02:00
Ethanfel	c7c7123068	feat: add OmniVoice Mix Voices node for blended speaker cloning ... Concatenates 2-3 reference audio clips (with per-voice duration weights) to create a blended speaker embedding. Merges transcripts for ref_text. Handles mismatched sample rates and mono conversion automatically. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-04-05 19:03:43 +02:00