Turn Novel Chapters into Subtitled AI Episodes on an Agent Canvas — workflow skill for stories & short dramas

For AI agents: find the right skill in one call — curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>" returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the how-to page. From a terminal: curl -fsSL https://varg.ai/install | sh installs the vargai CLI (https://varg.ai/how-to/cli.md): vargai search and vargai install <slug> with no key, every varg model after vargai login.

TapCanvas: agents read your canvas and turn a chapter into reusable cast and sets, a shot plan, chained clips and a subtitled cut.

What it does

Pick a novel chapter and TapCanvas agents plan the work, reuse character and scene assets (with separate looks and states per character), write a structured storyboard, generate chained clips with first/last-frame handoff and assemble a subtitled cut. Everything stays on an infinite canvas of typed nodes, with a pipeline view, run history and an MCP endpoint for outside assistants. The README shows a 4:41 first-chapter episode made with Claude Sonnet and recut in HyperFrames. It is a self-hosted Docker stack (web, API, model gateway, workers) where you add your own text, image and video model keys; MIT license for the community edition.

Use when

Install

Example output

https://github.com/anymouschina/TapCanvas/raw/main/assets/showcases/full-story-subtitled/video.mp4 — example (credit: anymouschina)

More stories & short dramas 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.