cclank/lanshu-create-ai-presenter-video walks an agent through a full talking-presenter video from a topic or script plus one authorized portrait: script, narration, presenter generation, lip-sync, captions, keyword motion graphics, editing and rendering. Each stage has to leave evidence on disk, and nothing ships until the file passes decode and loudness checks. It is provider-neutral and loads as a standard SKILL.md in Claude Code or Codex.
INSTALL LANSHU-CREATE-AI-PRESENTER-VIDEO
git clone https://github.com/cclank/lanshu-create-ai-presenter-video.git \
Copied as written in the repo's README. Check the README for options and requirements.
STACK
PythonFFmpeg
“Provider-neutral Codex Skill for producing verified AI presenter videos from a script and an authorized presenter image.”
ai-videocodexcodex-skilldigital-humanvideo-generation
About Avatars
Digital presenters: talking heads, lip-sync and virtual hosts.