skills.rest
shengshu-ai
shengshu-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

vidu-skills

Generate AI videos and images via the Vidu API.

68|27|Updated Apr 2, 2026
Search Tags:#text-to-speech#text-to-image#text-to-video#image-to-video#ai video generation#lip sync
One-click install
npx skills add https://github.com/shengshu-ai/vidu-skills --skill vidu-skills
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vidu-skills
Source: https://github.com/shengshu-ai/vidu-skills/tree/main
Command: npx skills add https://github.com/shengshu-ai/vidu-skills --skill vidu-skills

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires vidu-cli, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the generation of AI videos and images using the Vidu API, simplifying the process for users and saving time.

Core Features & Use Cases

  • Text-to-Image: Generate images from text descriptions.
  • Text-to-Video: Create videos from text input.
  • Image-to-Video: Transform images into videos with text overlay.
  • Lip Sync: Match text or audio to video for lip syncing.
  • Text-to-Speech: Convert text to speech with various voices and languages.
  • Video Composition: Combine multiple videos, audio, and subtitles into a single output.
  • Use Case: Imagine you want to create a promotional video for your product. Use this Skill to generate the video, add text, and even create a voiceover with text-to-speech.

Quick Start

To generate a video from text, run: vidu-cli task submit --type text2video --prompt "A cat walking through a park" --model-version 3.2 --duration 5 --resolution 1080p

Frequently Asked Questions about vidu-skills

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

FAQPage Schema
How do I generate AI video from text using Vidu API?▼

To generate AI video from text using Vidu API, run the vidu-cli task submit command with the text2video type, specifying your prompt, model version, duration, and resolution parameters.

Can I convert an image to video with text overlay?▼

Yes, you can convert an image to video with text overlay. The image-to-video feature transforms static images into dynamic videos by processing your image input and applying text descriptions via the Vidu API.

Does Vidu API support lip sync and text-to-speech?▼

Vidu API supports both lip sync and text-to-speech. You can match text or audio to video for lip syncing, and convert text to speech using various voices and languages.

What do I need to set up before using vidu-cli for video generation?▼

Before using vidu-cli for video generation, you need a Vidu API token. You can also optionally configure a Vidu base URL if you are connecting to regional services.

Can I combine multiple videos, audio, and subtitles into one output?▼

Yes, you can combine multiple videos, audio, and subtitles into one output. The video composition feature merges these elements into a single cohesive video file through the Vidu API.

What is the best way to automate AI image and video creation in my workflow?▼

The best way to automate AI image and video creation is using this Skill to script the Vidu API. It automates text-to-image and text-to-video tasks, saving time by simplifying the generation process.

Related Skills

Explore More Design & Creative Skills→
CaneproCanepro

sentry

Fetch and inspect Sentry issues and events via a read-only API.

Community
Advanced
shige1014-devshige1014-dev

video-download

Download videos, audio, subtitles, and metadata from online URLs using yt-dlp.

Community
Intermediate
agentspace-soagentspace-so
31

lipsync

Generate lip-synced videos from audio or scripts via RunComfy CLI.

Official
Intermediate
sayasaya8039sayasaya8039
2

fal-ai-media

Generate images, videos, and audio through a unified fal.ai interface.

Community
Intermediate