Apps & Tools
talking-portrait.cpp
Animate portrait photos with your voice using high-performance C++ and GGML
Float cloneOpen source
talking-portrait.cpp media is blocked
Allow external media to connect to the provider and play this content.
Description
A C++/GGML+CUDA implementation of the FLOAT audio-driven talking portrait model, generating 25 fps talking-head video from a single image and speech audio. It features a zero-allocation GPU inference pipeline and includes a WebGL gallery demo that renders generated portraits inside a virtual PBR picture frame environment.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.