Lanshu AI Presenter Video — workflow skill for talking heads & avatars

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

Publish-ready explainers led by an AI presenter from an authorized photo, or in one of twelve presenter-free styles.

What it does

Turns a topic or a finished script into a complete explainer video, either led by an AI presenter generated from an authorized adult presenter image or performed without a presenter in one of twelve explainer styles (nine visual, such as paper pop-up, clay town, blueprint and chalkboard, plus three narrative ones). It runs a resumable job state machine (lock content and audio, plan and generate the presenter, edit, verify and deliver), supports revising, captioning, lip-sync repair and re-exporting an existing job, and records the actual model and provider chosen for each job instead of hard-coding one. Published by Lanshu (cclank), with Chinese and English READMEs.

Use when

Not for

Install

Example output

https://skills.varg.ai/previews/lanshu-ai-presenter-video.mp4 — Creator's explainer on Hugging Face Storage: an AI presenter generated and embedded by this skill beside code-drawn explainer panels (graphics via the creator's companion html2video skill). First 8 s of 30 s. (credit: 岚叔 Lanshu (@LufzzLiz), https://x.com/LufzzLiz/status/2094018562046271682)

Used for

More talking heads & avatars skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.