Open Chinese Speech Dataset: 218 Speakers, 80k+ Utterances, Ready for F5/Spark/IndexTTS2
vista8 · x · 2026-10-12
A Chinese speech dataset has surfaced with 218 speakers and over 80k utterances, all emotionally neutral and annotated with gender, age, and native-accent labels, with 98%+ phoneme accuracy after professional QA.
It's a handy drop-in for open-source Chinese TTS models like F5, Spark, and IndexTTS2, which all need a reference Chinese clip for zero-shot synthesis. The author found it while adding audiobook narration to Qiaomu Reader; link in the comments.
More from Multimodal
- "Fuzzbeast style" AI illustrations produce delightfully weird red-eyed characters — OVolosin82152 · 2026-10-12
- First look at ByteDance's new World Model: text-to-navigable 3D worlds with real-time editing — Uncanny_Harry · 2026-10-12
- Stanford's WonderZoom generates infinite zoomable 3D detail from a single image — import_jmr · 2026-10-12
- AI-generated orange cat band 'The Five Meow Band' performs a full bar show — Reasonable_Damage_18 · 2026-10-12
- 'When Sand Speaks' Ep 1: an AI-voiced series from stone tools to silicon — projectforty2 · 2026-10-12
- Krea teases Krea 3 launch, opens early access signups — Angaisb_ · 2026-10-12