Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
bytedance avatar

Video Generate

  • 31 installs
  • 411 repo stars
  • Updated August 4, 2026
  • bytedance/agentkit-samples

video-generate is a Claude skill that generates a video from a text prompt via the Volcengine Ark model API, with an optional first-frame image.

About

video-generate is a Claude skill that produces a video from a text prompt using the Volcengine Ark model API. A developer runs video_generate.py with a filename and prompt, and can optionally pass a first-frame image (URL or local path) to control the starting frame. The script prints the resulting video URL and downloads the file. It reads an Ark or Volcengine API key from environment variables.

  • Generates a video from a text prompt via Volcengine Ark model API
  • Optional first-frame image (URL or local path) controls the opening shot
  • Outputs a TOS video URL and downloads the file to a given filename

Video Generate by the numbers

  • 31 all-time installs (skills.sh)
  • Ranked #964 of 1,335 Generative Media skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

video-generate capabilities & compatibility

Needs a Volcengine Ark or MODEL_VIDEO_API_KEY; model calls are billed by Volcengine

Capabilities
video generation · text to video
Use cases
video generation · image generation
Runs
Runs locally
Pricing
Bring your own API key
From the docs

What video-generate says it does

当需要根据文本描述生成视频时,使用该技能。支持通过首帧图片控制视频起始画面,首帧可以是 URL 或本地文件路径。
SKILL.md
优先读取 `MODEL_VIDEO_API_KEY` 或 `ARK_API_KEY` 环境变量。
SKILL.md
npx skills add https://github.com/bytedance/agentkit-samples --skill video-generate

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs31
repo stars411
Last updatedAugust 4, 2026
Repositorybytedance/agentkit-samples

What it does

Generate a video from a text prompt, optionally seeded by a first-frame image, and download it.

Who is it for?

Generating a short video from a text description, optionally controlling the opening frame.

Skip if: Breaking an existing video into shots, or running offline without an Ark or Volcengine API key.

When should I use this skill?

You need to create a video from a text prompt.

What you get

You get a generated video URL and the downloaded file at your chosen filename.

  • generated video TOS URL printed to console
  • downloaded video file

By the numbers

  • supports three invocation forms: text-only, first-frame URL, and first-frame local file

Files

SKILL.mdMarkdownGitHub ↗

Video Generate

适用场景

当需要根据文本描述生成视频时,使用该技能。支持通过首帧图片控制视频起始画面,首帧可以是 URL 或本地文件路径。

使用步骤

1. 准备目标文件名(如 output.mp4)和清晰具体的 prompt。 2. (可选) 准备首帧图片,可以是 HTTP URL,也可以是本地文件路径(脚本会自动转为 Base64)。 3. 运行脚本 python scripts/video_generate.py <filename> "<prompt>" [first_frame]。运行之前cd到对应的目录。 4. 脚本将输出视频的 TOS URL 并自动下载到指定文件。

认证与凭据来源

  • 优先读取 MODEL_VIDEO_API_KEYARK_API_KEY 环境变量。
  • 若未配置,将尝试使用 VOLCENGINE_ACCESS_KEYVOLCENGINE_SECRET_KEY 获取 Ark API Key。

输出格式

  • 控制台输出生成的视频 URL。
  • 视频文件将被下载到指定路径。

示例

纯文本生成:

python scripts/video_generate.py "cat.mp4" "一只可爱的猫"

带首帧图片生成(URL):

python scripts/video_generate.py "dog_run.mp4" "一只小狗在草地上奔跑" "https://example.com/dog_start.png"

带首帧图片生成(本地文件):

python scripts/video_generate.py "my_video.mp4" "图片中的人物动起来" "/path/to/local/image.jpg"

Related skills

Generative Mediallmautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.