omnihuman-video
About
This skill uses the OmniHuman v1.5 model to generate lip-synced videos from a character image and audio input. It's ideal for making portraits speak, dubbing content, or creating audio-driven facial animations. Key features include high-quality video output with synchronized lip movements and expressive facial gestures tied to the audio.
Quick Install
Claude Code
Recommendednpx skills add openclaw/skills -a claude-code/plugin add https://github.com/openclaw/skillsgit clone https://github.com/openclaw/skills.git ~/.claude/skills/omnihuman-videoCopy and paste this command in Claude Code to install this skill
GitHub Repository
Related Skills
hailuo-video
OtherThis skill uses MiniMax Hailuo 2.3 models to generate videos from text or images. It offers both Fast and Standard series, with Pro (1080p) and Standard (768p) options for different quality and speed needs. Use it when a user requests text-to-video, image-to-video, or mentions "hailuo" or "海螺视频."
descript
OtherThe Descript skill enables text-based editing of audio and video content through Claude, including transcription and production workflows. It allows developers to manipulate multimedia files by editing their transcribed text directly. Use this skill when you need to automate or streamline audio/video editing tasks within your development pipeline.
youtube
OtherThis skill enables Claude to automate YouTube management tasks through browser automation. Developers can use it to handle subscriptions, playlists, watch history, and engagement features programmatically. It requires Google authentication and integrates with Canifi's environment configuration system.
wistia
OtherThis skill enables Claude to manage Wistia-hosted marketing videos directly from the command line. Developers can use it to handle video libraries, access detailed engagement analytics, and configure lead capture forms. It's ideal for automating video content workflows and tracking performance within marketing campaigns.