Create AI Avatar

Meng ToCommunityCreated by Meng To

Skill
Workflow
Data and AI
MIT
Low risk
Has scripts

From the author

Make an AI avatar of yourself that looks and sounds like you. A HeyGen digital twin trained on a couple of minutes of your own footage says lines you never recorded, in your own ElevenLabs voice, lip-synced from the audio, on the engine whose mouth moves most like yours. Covers picking and joining takes, training, consent, making the voice, rendering the same line on Avatar V, IV and III, and judging them mouth to mouth against your real footage before anything else is made. Use when someone wants a digital twin, an AI avatar or talking head of themselves or a consenting person, a HeyGen avatar from their YouTube videos or recordings, their avatar to speak in their own cloned voice, a lip-synced talking video from a photo and audio, or says their avatar looks wrong, over-acts or its mouth isn't theirs.

— the description by Meng To

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a structured process for creating a digital twin or photo avatar that mimics a person's appearance and voice. It covers the end-to-end procedure, including preparing and uploading footage, training the model, managing consent, generating audio, and rendering video across different engines. The workflow emphasizes a comparative approach, where users render the same line across multiple engines and evaluate the results by comparing mouth movements against original footage to ensure the best match.

What it does

Prepares and joins video takes for digital twin training.
Uploads assets and manages the HeyGen training process.
Handles consent requirements for digital twin creation.
Generates audio using ElevenLabs voice cloning.
Renders video output using different HeyGen engines.
Provides a method to compare and judge mouth movements across renders.

When to use it

When you need to create a digital twin or talking head of yourself or a consenting person.
When you want an avatar to speak using your own cloned voice.
When you need to generate a lip-synced video from a photo and audio.
When you need to troubleshoot or improve the mouth movements of an existing avatar.

Advantages

Uses a systematic, comparative approach to select the best engine for specific facial movements.
Separates face, voice, and lip-sync components to isolate and fix issues.
Provides scripts for consistent asset management and rendering.
Includes a specific method for judging mouth synchronization against real footage.

Usage examples

“Create a digital twin of myself using my YouTube footage.”: The agent will guide you through picking eye-contact takes, joining them, uploading the footage, and initiating the training process.
“My avatar's mouth looks wrong and over-acts.”: The agent will help you render the same line on different engines (Avatar V, IV, and III) to compare mouth movements and select the most natural one.

Install

3 of its files are not mirrored here, so install it from its source:
https://github.com/MengTo/Skills/tree/5ea1661a0e05d82b054553daaa6baf6d0233c33c/agent-skills/media/create-ai-avatar

Documentation by Meng To

Create AI Avatar

HeyGen API · ElevenLabs · ffmpeg. Scripts are plain Node 20 and bash, with no packages to install.

An avatar of you is three things, each from its best source. The face and the way you move come from your own footage (a HeyGen digital twin). The voice is your own clone on ElevenLabs, made into an audio file. One engine lip-syncs the two. You then judge the result where likeness breaks first: the mouth, close up, beside your real one.

Boundary. Use html-explainer-video for a film with no face in it, and html-reel to cut your real phone takes into a reel. Use this skill when the person on screen should be you, saying words you didn't record.

Provenance. Built in November 2026 on a creator's own twin, trained from the eye-contact takes of one YouTube video (2 min 48 s) and voiced in his ElevenLabs clone on v4. The same 8.8-second line was rendered on all three engines, and the creator picked by the mouth. The demo shows four presenters made from single portraits as HeyGen photo avatars, so nobody's real footage is on show.

The mechanism

Keep the face, the voice and the lip-sync apart, and only ever change one of them. The twin is trained once. The voice is a file you listen to before it goes anywhere. A render is the twin plus that file on one engine. When something looks wrong you can then tell which part to change. Use the same line and the same audio for every engine you compare: a new line hides what the engine did.

HeyGen can't use an ElevenLabs voice by its id. Make the line on ElevenLabs (scripts/voice.mjs), then send HeyGen the audio as audio_asset_id or audio_url instead of script and voice_id. The video is as long as the audio, up to 30 minutes.

Judge it by the mouth. In a whole frame every engine looks fine. Crop the nose-to-chin box at six moments of each render and of your real footage, and stack them (scripts/mouths.sh). Then look at how wide the lips stretch, how much of the teeth show, the colour of the lips and the corners of the mouth.

Three ways to an avatar

	Digital twin	Photo avatar	Talking photo
From	15 s to 10 min of footage, about 2 min best	One photo	One photo
Costs first	About $2.13 to train, plus consent	About $1.32	Nothing
Engines	Avatar V, IV, III	Avatar V, IV, III	Avatar IV only
Moves	As you do: your head, your habits	What the engine imagines	What the engine imagines
Use for	Anything that has to pass as you	A presenter from a portrait, on Avatar V	A quick line

All three take your audio. Start on Avatar V: it's HeyGen's newest engine and the default here. Judge it by the mouth, and step down to IV or III if it over-acts the person you know. Fil's Create AI avatar workflow is the photo avatar: your photo and a voice, wired into HeyGen Avatar V.

The workflow

Pick the footage (references/footage.md). Use your best talking takes: you alone, facing the camera with the face in frame throughout, in a quiet room, at 1080p. That's two to three minutes of natural speech. Eye-contact takes are best. Download each once and join them with bash scripts/prep-footage.sh footage.mp4 take-*.mp4.
Upload it. node scripts/upload.mjs footage.mp4 direct-uploads up to 200 MB and keeps the asset id beside the file.
Train it. Say the price ($2.13) and the wallet first. Then run node scripts/train.mjs --footage <asset_id> --name "Ada · March takes", which trains in a few minutes. A new character gets a consent link: the person in the footage opens it within 24 hours and records a short statement. The twin renders only once its look is completed and its consent accepted. To add new footage of the same person, pass --group.
Make the line. Run node scripts/voice.mjs "<one line, about 25 words>" line.mp3 --voice <your clone>. Listen to it, and check its words with node scripts/hear.mjs line.mp3.
Render the line on Avatar V, with no motion prompt: node scripts/render.mjs --look <look_id> --audio line.mp3. To compare, render the same line on --engine avatar_iv and avatar_iii too. Each render prints its price first and the wallet after. A portrait instead of footage: make it a photo avatar with POST /v3/avatars { type: 'photo' } (references/heygen.md) and render its look the same way.
Judge. Run bash scripts/mouths.sh mouths.jpg footage.mp4 twin-avatar_v.mp4 twin-avatar_iv.mp4 twin-avatar_iii.mp4 and put the renders side by side with their sound. Show the person both before saying which is best: it's their face (references/judging.md).
Use the one they pick for the real lines, and write it down with the ids: the look, the group, the voice and the engine.

Rules

Each rule names the failure it prevents.

Check which face goes with which voice before rendering. Two photo avatars' ids were swapped once, and four renders paired each face with the other person's voice. Name every file after its person, and check the look's name before each render.
A new render needs a new Idempotency-Key. One render was sent again with the first render's key, and HeyGen handed back the first video. render.mjs builds the key from the subject and the audio.
Change the engine, not the prompt, when the mouth over-acts. On Avatar V the lips stretched wide and both rows of teeth showed. A motion_prompt and more_blinking changed almost nothing; Avatar IV and III fixed it.
expressiveness is for photo avatars on Avatar IV only. Avatar V rejects it, and a twin doesn't take it.
A calm read beats an acted one. A stability-0 read with [excited] and [laughs] sounded less like the creator than the default. Start calm, and change the voice only after the face is right.
A twin is no sharper than its footage. Takes scaled down to 720p gave a 1280×720 look. Train from 1080p.
Say the price and the wallet before every paid call. The wallet is the account's, so anything else on the same key spends from it too. It once dropped $1.76 more than the twin and one render cost.
Consent belongs to a group and to one person. Never add someone else's footage to a group, and never train anyone who hasn't agreed. HeyGen runs no consent check for a photo, so getting the person's agreement is on you.
Download a source once, then work from the local file. Never loop ffmpeg over a signed link.
Training clones a voice too. HeyGen makes default_voice_id from the footage as its own resource. Use it only if your ElevenLabs clone isn't there. Deleting the twin doesn't delete it.
Hands can come out wrong. Avatar IV gestures, and in one render a thumb looked rubbery. Watch the whole frame once before using a take.

The engines, on one twin and one line

Engine	A second	The mouth	Everything else
Avatar V	$0.12	Lips stretched, both rows of teeth, pinker lips	Smoothed skin; invents the most
Avatar IV	$0.0805	Small and round, top teeth now and then	Hand gestures; the creator's pick for his own face
Avatar III	$0.01	Closest: small openings, natural lip colour	Your real head movement; oldest, so check sync by ear

That's one face in one session, so judge your own: it's why step 6 exists.

Numbers

Footage: 15–600 s (about 2 min best), long edge 640–4096 px, mp4 or webm, one person, up to 200 MB direct.
Training: about $2.13, about 4 minutes for 2 min 48 s. A photo avatar: about $1.32, ready in about 10 seconds.
Consent link: valid 24 hours.
A line: about 25 words, 8–10 s, the same audio for every engine.
One 8.8 s render: Avatar V $1.05, IV $0.71, III $0.09; 2–3 minutes each.
Audio: mp3 or wav, up to 32 MB as an asset, up to 30 minutes a video.
Mouth sheet: 6 moments a row, a 420 × 300 box of a 1920-wide frame, moved to fit the face.

Files

references/footage.md: picking, joining and checking takes
references/heygen.md: every HeyGen call the scripts make, and its answers
references/judging.md: the mouth sheet, what to look for, showing the person
scripts/keys.mjs: keys from the environment or .env.local, and the HeyGen client
scripts/prep-footage.sh, upload.mjs, train.mjs, consent.mjs, voice.mjs, hear.mjs, render.mjs, mouths.sh, balance.mjs
demo/index.html: four presenters from single portraits on Avatar V, one on all three engines, with the mouth sheet

Keys: HEYGEN_API_KEY, ELEVENLABS_API_KEY and ELEVENLABS_VOICE_ID (your clone), from the environment or .env.local. They're never printed.

Files

ATTRIBUTION.mdAdded by AutoGineer849 B
LICENSELicence file added by AutoGineer1.0 KiB
SKILL.md9.3 KiB
agents/openai.yaml398 B
demo/PROMPT.md1.3 KiB
demo/avatar-iii.mp4(opens on GitHub)Not mirrored: opens on GitHub687.0 KiB
demo/avatar-iii.webp14.2 KiB
demo/avatar-iv.mp4(opens on GitHub)Not mirrored: opens on GitHub610.2 KiB
demo/avatar-iv.webp17.7 KiB
demo/avatar-v.mp4(opens on GitHub)Not mirrored: opens on GitHub620.3 KiB
demo/avatar-v.webp17.0 KiB
demo/index.html8.5 KiB
demo/mouths.jpg118.7 KiB
demo/preview.jpg68.2 KiB
references/footage.md2.6 KiB
references/heygen.md3.2 KiB
references/judging.md2.4 KiB
scripts/balance.mjsScript294 B
scripts/consent.mjsScript843 B
scripts/hear.mjsScript1.1 KiB
scripts/keys.mjsScript2.2 KiB
scripts/mouths.shScript1.9 KiB
scripts/prep-footage.shScript1.7 KiB
scripts/render.mjsScript4.0 KiB
scripts/train.mjsScript3.1 KiB
scripts/upload.mjsScript2.0 KiB
scripts/voice.mjsScript1.8 KiB

scripts/consent.mjs

#!/usr/bin/env node
/* A twin's consent: where it stands, and a fresh link (valid 24 hours) for
   the person in the footage to record their statement. A twin renders only
   once its look is completed and its group's consent is accepted.

   node scripts/consent.mjs <group_id> */

import { heygen } from './keys.mjs';

const group = process.argv[2];
if (!group) {
  console.error('Usage: node scripts/consent.mjs <group_id>');
  process.exit(1);
}
const g = await heygen(`v3/avatars/${group}`);
const status = g.consent_status ?? g.avatar_group?.consent_status;
console.log(`${g.name ?? g.avatar_group?.name ?? group}: consent ${status}`);
if (status !== 'accepted') {
  const c = await heygen(`v3/avatars/${group}/consent`, { method: 'POST', body: {} });
  console.log(c.url ? `Open within 24 hours: ${c.url}` : 'Submitted for review.');
}

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs an API key, Needs Node.js

Security

What our scanner noticed· Low risk

Scripts that your agent may run

This skill includes scripts that your agent may run. Read them before you use it.

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by

Meng To

Publisher

Meng To (Community)

Source

MengTo/Skills · agent-skills/media/create-ai-avatar · commit 5ea1661

Licence

MIT License (redistribution allowed)

LICENSE (added by AutoGineer from LICENSE)
ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-09

AutoGineer is not affiliated with or endorsed by Meng To or Meng To.

Get it from the source

3 of this skill’s files are not mirrored here, so there is no ZIP. Get the complete skill from its source: MengTo/Skills

From the author

AutoGineer summary

What it does

When to use it

Advantages

Usage examples

Install

Documentation by Meng To

Create AI Avatar

The mechanism

Three ways to an avatar

The workflow

Rules

The engines, on one twin and one line

Numbers

Files

Files

scripts/consent.mjs

Requirements and compatibility

Security

Attribution and licence

Related skills

Claude API

Transformers

Open Notebook

Vision Sft

LLM Evaluation

Lora Qlora Recipes

Get it from the source