Files

T

diodiogod 4bd70b6aa2 docs: refactor KugelAudio as VibeVoice variant

- Remove standalone KugelAudio engine entry
- Merge KugelAudio details into VibeVoice engine documentation
- Regenerate comparison tables (ENGINE, FEATURE, LANGUAGE)
- Update README.md to reflect KugelAudio as a model variant

2026-02-11 23:29:12 -03:00

1.4 KiB

Raw Blame History

Feature Comparison Matrix

Feature	F5-TTS	ChatterBox	ChatterBox 23L	VibeVoice	Higgs Audio 2	IndexTTS-2	CosyVoice3	Qwen3-TTS	Step Audio EditX	RVC
Voice Cloning	✅	✅	✅	✅	✅	✅	✅	✅ (Base model)	✅	⚠️ (needs training)
Native Multi-Speaker	❌	❌	❌	✅ (Base only, Kugel uses fallback)	✅	❌	❌	❌	❌	❌
Voice Conversion	❌	✅	✅	❌	❌	❌	✅	❌	❌	✅
ASR (Transcribe)	❌	❌	❌	❌	❌	❌	❌	✅	❌	❌
Emotion Control	❌	❌	⚠️ (v2 tags - doesn't work)	❌	⚠️ (via prompt)	✅ (8 emotions)	⚠️ (via instruct)	⚠️ (via instruct)	✅ (14 emotions)	❌
Native Long-form (90min)	❌	❌	❌	✅	❌	❌	❌	❌	❌	N/A
Community Finetunes	✅	✅	✅	✅ KugelAudio, Hindi	❌	❌	❌	❌	❌	✅
VRAM Efficient	✅	✅	✅	⚠️ (5-18GB)	⚠️ (9GB)	⚠️ (9-12GB)	✅ (5.4GB)	✅ (3-6GB)	⚠️ (7GB)	✅
Speed/Performance	✅ Very Fast	✅ Fast	✅ Fast	⚠️	⚠️	⚠️	✅ Fast	⚠️	⚠️	✅ Fast

1.4 KiB Raw Blame History

Feature Comparison Matrix

Feature Comparison Matrix

1.4 KiB

Raw Blame History