Tag
Openspline 是一个开源的实时数字人头像层，可通过 5 行代码接入现有语音 AI 智能体，在本地 GPU 上生成口型同步的实时视频，RTX4090 上可达 90+ FPS。
Un laboratorio chino ha lanzado LongCat-Avatar, una herramienta open source que genera un avatar sincronizado con audio a partir de una foto y un audio, revolucionando la producción de video.
This post describes how to use Hugging Face's ZeroGPU and a coding agent to autonomously deploy AI models, specifically the LongCat talking-avatar model, on a budget.
LongCat released an open-source talking-avatar model (likely state-of-the-art) under MIT license, with a Hugging Face demo, enabling various applications like AI tutors, dubbing, and coding agents.