anliyuan/Ultralight-Digital-Human

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2627 stars · 387 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

An ultralight talking-head (digital human) model that animates a person's face from audio input and runs in real time on mobile devices. It uses lightweight audio encoders (wenet/HuBERT) with a UNet-based video generation pipeline, with training and streaming inference scripts in Python.

Use cases

• create a talking avatar from a short training video
• run a real-time digital human on a phone
• generate lip-synced video from audio
• build a lightweight virtual presenter or chatbot avatar
• stream a digital human with low latency on mobile
• train a custom talking-head model from my own footage

When to choose

• you need a very lightweight, real-time talking-head model on mobile or edge devices
• you want an open-source alternative to commercial digital human APIs
• you have clean audio/video training footage and want a custom avatar
• you need streaming inference with low per-frame latency

When to avoid

• you need high-fidelity, full-body or expressive avatars rather than a single talking face
• your source audio is noisy or has echo, which degrades results significantly
• you need a production-ready, well-licensed package (no explicit license file)
• you want a maintained C++ deployment path out of the box (see the successor FeatherTalk instead)

Facets

library · maturity active

machine-learning deep-learning speech-recognition video-processing llm-inference deep-learning computer-vision speech-processing mobile-development artificial-intelligence python cross-platform digital-human talking-head audio-driven-video real-time-inference onnx mobile-deployment wav2lip-alternative streaming-inference android ios gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="anliyuan/Ultralight-Digital-Human")