# AI Avatar Video — 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 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.

Create talking-head avatar videos from a portrait and a script, with a lip-synced voice.

- **Type:** [Model](https://skills.varg.ai/models.md) · [Talking heads & avatars](https://skills.varg.ai/browse/skills/talking-head.md)
- **Slug:** `inference-sh-ai-avatar-video`
- **Status:** live
- **Publisher:** inference.sh (vendor, verified)
- **License:** MIT
- **Source:** https://github.com/inference-sh/skills/tree/main/tools/video/ai-avatar-video
- **Works in:** Claude Code, Codex, Cursor, Gemini CLI
- **Requires:** inference.sh account, belt CLI (`belt login`)
- **Cost:** Billed by inference.sh
- **Adoption:** 14 installs, 781 GitHub stars (skills.sh, 2026-10-26)

## What it does

Creates AI avatar and talking-head videos through inference.sh, recommending Pruna P-Video-Avatar for speed and cost. It also covers OmniHuman, Fabric and PixVerse, with Inworld TTS-2 and other voices for the audio.

## Use when

- A talking-head video from a photo
- Comparing avatar models

## Install

- Claude Code: `npx skills add inference-sh/skills --skill ai-avatar-video -a claude-code`
- Codex: `npx skills add inference-sh/skills --skill ai-avatar-video -a codex`
- Cursor: `npx skills add inference-sh/skills --skill ai-avatar-video -a cursor`
- Gemini CLI: `npx skills add inference-sh/skills --skill ai-avatar-video -a gemini-cli`

**Models it drives:** p-video-avatar, omnihuman_v1_5, veed_fabric_1_0, pixverse

## Example output

https://skills.varg.ai/previews/inference-sh-ai-avatar-video.mp4 — ByteDance OmniHuman 1.5 (bytedance/omnihuman-1-5, one of the skill's avatar models): a portrait animated into a girl singing with a guitar under cherry blossoms, from inference.sh's avatar-model comparison (credit: inference.sh blog (OmniHuman 1.5 output), https://inference.sh/blog/guides/p-video-avatar-talking-head-generation)

## Used for

- [Talking avatar or presenter](https://skills.varg.ai/use-cases/talking-avatar.md): A person (from a headshot, or generated) speaks your script to camera with lip-sync, in any language.

## More talking heads & avatars skills

- [Character Keynote](https://skills.varg.ai/skills/varg-character-keynote.md): One render call: a Soul character delivers a keynote-style ad line on a generated stage, voiced by Seedance 2.5.
- [Podcast Dialogue Video](https://skills.varg.ai/skills/varg-podcast-video.md): Two-character podcast or debate clips: one studio set, locked camera angles, MiniMax H3 Max with native audio.
- [Talking Head Production](https://skills.varg.ai/skills/inference-sh-talking-head-production.md): Produce talking-head videos with AI avatars, lip-sync and voiceover, from portrait specs to final cut.
- [P-Video Avatar](https://skills.varg.ai/skills/inference-sh-p-video-avatar.md): Turn one portrait into a speaking avatar video with Pruna P-Video-Avatar, its built-in TTS or your audio.
- [AI Podcast Video](https://skills.varg.ai/skills/inference-sh-ai-podcast.md): Generate a multi-person talking-head podcast video from scratch: characters, voices, avatars, stitching.
- [Lanshu AI Presenter Video](https://skills.varg.ai/skills/lanshu-ai-presenter-video.md): Publish-ready explainers led by an AI presenter from an authorized photo, or in one of twelve presenter-free styles.

## 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.

- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP)
- Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a <agent> -y`
- Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp`
- API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt