Higgsfield Video Explainer — workflow skill for explainers

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.

Turn a topic or document into a narrated, stylized explainer assembled from 10-second voiced blocks.

What it does

Builds a complete non-photoreal explainer or story video: research, one style key, narration split into 10-second blocks, one Seed Audio voice take and one Gemini Omni Flash clip per block, then server-side assembly into a finished MP4. It supports Higgsfield's live style presets or custom references, mascot and faceless modes, two aspect ratios and optional burned-in subtitles.

Use when

Not for

Install

Models it drives: omni_flash_1_1, seed_audio, nano_banana_pro, nano_banana_2

Example output

https://skills.varg.ai/previews/higgsfield-video-explainer.mp4 — Higgsfield Faceless Video showcase: 2D animated captioned explainer on how early humans discovered fire; first 8 s (credit: Higgsfield, https://higgsfield.ai/skills)

Used for

More explainers 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.