Talking Head Production — 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.

Produce talking-head videos with AI avatars, lip-sync and voiceover, from portrait specs to final cut.

What it does

Talking-head production with AI avatars, lip-sync and voiceover on inference.sh. It recommends P-Video-Avatar (fastest and cheapest, built-in TTS), also covers OmniHuman, PixVerse and Fabric, and spells out portrait requirements and audio preparation.

Use when

Install

Models it drives: p-video-avatar, omnihuman_v1_5, kokoro

Example output

https://skills.varg.ai/previews/inference-sh-talking-head-production.mp4 — Talking-head output of P-Video-Avatar (the guide's recommended model): a presenter in an office speaking to camera, from inference.sh's side-by-side vs HeyGen Avatar 4 (credit: inference.sh blog (P-Video-Avatar comparison), https://inference.sh/blog/guides/p-video-avatar-talking-head-generation)

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.