LAION's Humaneness Voice Converter: full Chatterbox-based checkpoint on Hugging Face
lmoroney · x · 2026-10-13
The author re-shares his earlier tweet with the Hugging Face link. The model card confirms: Humaneness Voice Converter is LAION's recommended default Chatterbox-based voice-conversion checkpoint, a complete audio-to-audio inference package (S3 token extractor, CAMPPlus speaker encoder, score-conditioned flow decoder, HiFT vocoder, Ears Medium scorer) — not a TTS model. English/German supported; CC BY 4.0; an official demo compares it against untouched Chatterbox, best-of-N selections, and external converters.
Related event: LAION Open-Sources Humaneness Voice Converter(2 posts)→
More from Multimodal
- Krea 3 image model is 'very very close' as fal.ai posts prompting guide — Oren_Lester · 2026-10-13
- Kandinsky 6.0 Video goes open source: 3B/29B models generate clips with synced audio — lmoroney · 2026-10-13
- promptpilot MCP server pipes 20+ image, video and audio models into Claude Code — modelcontextprotocol · 2026-10-13
- Midjourney v8.2 style code sref 1582397130 delivers painterly water-light photography looks — azed_ai · 2026-10-13
- GPT-6 Astra builds 100% 3D hotel website via Blender MCP with 10.7M triangles — ravisparikh · 2026-10-13
- Midjourney V7 ultraviolet gradient snake eye macro via --sref 1632499533 — michaelrabone · 2026-10-13