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

..

__init__.py

feat: add OmniVoice Mix Voices node for blended speaker cloning

2026-04-05 19:03:43 +02:00

epub_loader.py

Preserve paragraph breaks in EPUB text extraction

2026-04-05 18:06:41 +02:00

generator.py

Add seed parameter to OmniVoice Generate for consistent voice across chunks

2026-04-05 18:53:58 +02:00

loader.py

Remove local path option from model loader

2026-04-05 18:02:55 +02:00

mix_voices.py

fix: three bugs in OmniVoiceMixVoices

2026-04-05 19:04:54 +02:00

voice_presets.py

Expand voice presets to 8 voices (3 female, 5 male)

2026-04-05 18:51:43 +02:00