seedance

Generate AI videos from prompts, images, or audio via the Seedance API.

1|Updated May 13, 2026
One-click install
npx skills add https://github.com/wtgoku-create/PopiStudio --skill seedance-wtgoku-create
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: seedance
Source: https://github.com/wtgoku-create/PopiStudio/tree/main/SKILLs/seedance
Command: npx skills add https://github.com/wtgoku-create/PopiStudio --skill seedance-wtgoku-create

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill removes the manual, trial-and-error process of creating AI videos by handling task submission, progress polling, and downloading finished MP4 files for you.

Core Features & Use Cases

  • Text-to-Video (T2V): Turn a natural-language prompt into a short video concept for pitches, demos, and content ideation.
  • Image-to-Video (I2V): Animate a first frame (or multiple reference images) by attaching local images, network URLs, or file:// URIs.
  • Audio-synced video generation: Produce a video with generated audio (available on specific 1.5 pro models) for richer storytelling and presentations.
  • Use case: You need a 9:16 vertical short for social media: describe the scene, optionally provide a reference image, generate the video, and download the MP4 automatically.

Quick Start

Use the seedance skill to generate a 5-second text-to-video by running the command: bash "$SKILLS_ROOT/seedance/scripts/generate-video.sh" --prompt "A cinematic shot of a small cat playing in a sunny meadow, camera slowly pushes in" --ratio "9:16" --duration 5 --output generated_video.mp4.

Frequently Asked Questions about seedance

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

FAQPage Schema
How do I generate an MP4 video from text prompts?

You can generate an MP4 video from text prompts by submitting a natural-language description to the Seedance API, which handles async task creation and polls for progress before downloading the finished file. This text-to-video process requires an ARK_API_KEY to access the Volcengine Ark API endpoints.

Can I animate an existing image into a video?

Yes, you can animate an existing image into a video using the image-to-video feature by attaching local images, network URLs, or file:// URIs as reference frames. The Seedance model API processes these reference frames to generate the animated video output.

How does audio-synced video generation work?

Audio-synced video generation produces a video with generated audio for richer storytelling and is available specifically on the 1.5 pro model family. You configure audio-enabled generation settings through the Seedance model API to get the final MP4 output.

Do I need an API key to create AI videos?

Yes, you need an ARK_API_KEY to create AI videos because the generation process uses Volcengine Ark API endpoints for task submission. This key is required for the asynchronous task creation, progress polling, and downloading the resulting MP4 via video_url.

What are the limitations when generating AI videos?

Limitations when generating AI videos include model-specific duration constraints and enforced polling and timeout limits during the generation process. The audio-synced feature is also restricted exclusively to the 1.5 pro model family.

Can I generate vertical short videos for social media?

Yes, you can generate vertical short videos for social media by specifying a 9:16 ratio and a short duration like 5 seconds in your command. The Skill automatically downloads the resulting MP4 file formatted for your specified aspect ratio.