OmniHuman 1.5 via dLazy — model 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 how-to page 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 how-to page.

Turn a portrait photo and an audio track into a talking digital-human video with OmniHuman 1.5, via the dLazy CLI.

What it does

Runs Jimeng OmniHuman 1.5 through the dLazy hosted service with the dlazy jimeng-omnihuman-1.5 CLI command. You pass one portrait image, one audio file and an optional prompt; it returns a presenter-style video of that person speaking. Options are 720p (audio up to 60 s) or 1080p (audio up to 30 s) and a fast mode. The description mentions text input, but the documented flags only take audio, so you need a voice track first.

Use when

Not for

Install

Models it drives: omnihuman_1_5

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.