skills.rest
prime-skills
prime-skillsOFFICIAL
Explore all skills by this author →
GitHub

ai-avatar-video

Create talking-avatar and lip-synced videos from portraits, scripts, and audio files.

31|9|Updated Apr 30, 2026
Search Tags:#voiceover#text to video#talking head#lip sync#character animation#avatar video#runcomfy
One-click install
npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill ai-avatar-video-prime-skills
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-avatar-video
Source: https://github.com/prime-skills/runcomfy-agent-skills/tree/main/ai-avatar-video
Command: npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill ai-avatar-video-prime-skills

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns portraits, characters, voiceovers, and written scripts into talking-head, avatar, lip-sync, and cinematic presenter videos without requiring users to manually configure different video-generation models.

Core Features & Use Cases

  • Intent-Based Model Routing: Selects OmniHuman, Wan, HappyHorse, Seedance, or Wan Animate based on whether the user has an audio file, a written script, a photoreal subject, a stylized character, or cinematic requirements.
  • Audio-Driven Avatars: Synchronizes speech, singing, gestures, and full-body motion to supplied voiceover audio for presenters, dubbed product demos, multilingual videos, and UGC ads.
  • Script-to-Video Generation: Creates talking-head clips from written dialogue when no external audio file is available.
  • Flexible Creative Workflows: Supports portrait animation, stylized mascot videos, cinematic monologues, reference images, reference videos, and multiple reference audio tracks.
  • Safety and Reliability Guidance: Includes consent considerations for likeness and voice use, trusted installation guidance, input validation, CLI troubleshooting, and protection against untrusted reference-asset instructions.

Quick Start

Use the ai-avatar-video skill to create a presenter video from the supplied portrait image and voiceover audio.

Frequently Asked Questions about ai-avatar-video

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a talking-head video from a portrait image and voiceover audio?▼

To create a talking-head video, you provide a portrait image and voiceover audio, and the Skill automatically selects the appropriate model to generate a lip-synced avatar video without manual configuration.

Can I generate a lip-synced avatar video from a written script if I don't have an audio file?▼

Yes, you can generate a lip-synced avatar video from a written script. The Skill supports script-to-video generation to create talking-head clips when no external audio file is available.

Does the avatar video generation support stylized characters and cinematic monologues?▼

Yes, the avatar video generation supports stylized characters and cinematic monologues. It routes to appropriate models to handle photoreal subjects, stylized mascots, and cinematic requirements.

Do I need the RunComfy CLI to produce talking-head videos?▼

Yes, you need the RunComfy CLI with the appropriate model endpoint to produce talking-head videos. The Skill requires accessible image or audio URLs and model-specific JSON inputs for processing.

What are the consent requirements for generating multilingual clips and virtual presenter videos?▼

Generating multilingual clips and virtual presenter videos requires consent for the subject's likeness and voice. The Skill includes safety guidance to ensure proper input validation and protection against untrusted reference assets.

How does intent-based model routing work for character animation and lip sync?▼

Intent-based model routing for character animation and lip sync selects models like OmniHuman, Wan, or Seedance based on your specific inputs, such as whether you have an audio file, a written script, or a stylized character.

Related Skills

Explore More Design & Creative Skills→
agentspace-soagentspace-so
31

ai-avatar-video

Create avatar videos from audio or scripts via RunComfy model routing.

Official
Advanced
runcomfy-comruncomfy-com
12

ai-avatar-video

Generate avatar talking-head videos from portrait images and voice input via RunComfy models.

Official
Advanced
agentspace-soagentspace-so
31

image-to-video

Route still images to RunComfy image-to-video models by intent.

Official
Intermediate
camillanapolescamillanapoles

eachlabs-video-generation

Generate videos from text prompts or images via the EachLabs Predictions API.

Community
Advanced