volcengine-video-studio

Use this skill to actually submit, poll, inspect, and download Volcengine / ARK video generation jobs instead of only drafting prompts.

中文说明

这是一个面向 火山引擎 / ARK 兼容视频生成接口 的生产可用型 skill，重点不是只写视频提示词，而是把整条生成链路真正跑通，从提交任务、轮询状态，到拿回结果、下载成片，都能一把做完。

它特别适合下面这些对外场景：

• - 文生视频
• 图生视频
• 草稿视频二次优化
• 提交生成任务并持续轮询状态
• 检查任务返回内容与原始 payload
• 将生成好的视频自动下载到本地

如果你想要的是一个能真实发起任务、能追踪任务进度、能拿到最终视频文件、适合实战交付的火山视频 skill，这个版本就是为这种需求准备的。

Treat the prompt and optional reference media as runtime input for each task. Do not reuse documentation example prompts or example media in a real generation request unless the user explicitly asks for that exact example.

What this skill is good at

• - text-to-video from a task-specific prompt
• image-to-video using a local file, data URL, or remote image URL
• draft-video refinement with a guiding prompt
• polling existing tasks and downloading finished outputs
• switching between a faster default model and a stronger alternate model

Default path

Run the bundled script with the actual prompt for the current task:

CODEBLOCK0

To switch to the alternate model for one run:

CODEBLOCK1

By default the script:

• - submits the task
• polls until the task finishes
• extracts returned video URLs from the task payload
• downloads generated files into INLINECODE0

Required config

The script reads config from env vars:

• - VOLCENGINE_API_KEY or INLINECODE2
• INLINECODE3 (recommended)
• INLINECODE4 or VOLCENGINE_ENDPOINT or INLINECODE6

Recommended video models:

• - doubao-seedance-1-0-pro-fast-251015 — default, faster iteration
• INLINECODE8 — alternate higher-tier option

Default behavior:

• - if VOLCENGINE_VIDEO_MODEL is unset, the script defaults to INLINECODE10
• avoid relying on VOLCENGINE_MODEL for video runs when that env var is also used for image generation

Typical endpoint:

• - INLINECODE12

The script calls:

• - INLINECODE13
• INLINECODE14

Common workflows

1. Text to video

CODEBLOCK2

2. Image to video

CODEBLOCK3

3. Draft/sample video to final video

CODEBLOCK4

4. Inspect an existing task only

CODEBLOCK5

5. Submit only, do not wait

CODEBLOCK6

6. Use raw content JSON when the target model needs a custom body

CODEBLOCK7

Local media support

For --image and --video:

• - local file path → converted to data: URL automatically
• INLINECODE18 URL → sent as-is
• INLINECODE19 URL → sent as-is

This makes local reference media usable without manual upload steps.

Key options

• - INLINECODE20
• INLINECODE21
• INLINECODE22
• INLINECODE23
• INLINECODE24
• INLINECODE25
• INLINECODE26
• INLINECODE27
• INLINECODE28
• INLINECODE29
• INLINECODE30
• INLINECODE31
• INLINECODE32

Execution checklist

1. 1. Confirm whether the user wants text-to-video, image-to-video, or draft-video refinement.
2. Treat the prompt as task-specific runtime input; never carry over example prompt text or example media into a real run unless explicitly requested.
3. Choose prompt-first mode by default; use --content-json only when the API shape must be customized.
4. Pass local reference media directly with --image or --video.
5. Prefer --duration for whole-second clips and --frames only when finer control is required.
6. Poll by default so the final answer includes actual output URLs or downloaded files.
7. Mention the saved file paths when downloads are enabled.
8. If the API returns an unexpected structure, surface the raw JSON instead of guessing.

Troubleshooting

• - Missing key → set INLINECODE38
• Missing or wrong model → set INLINECODE39
• If a video run accidentally picks an image model (for example doubao-seedream-4-5) → explicitly set VOLCENGINE_VIDEO_MODEL instead of reusing INLINECODE42
• Missing endpoint → set INLINECODE43
• 401/403 → key invalid or missing permission
• 404 → endpoint wrong or region mismatch
• 400 → unsupported model/parameter combination
• Task remains queued too long → check quota, rate limit, or model availability
• No obvious video URL in response → inspect INLINECODE44

References

• - INLINECODE45
• INLINECODE46

• - Missing endpoint → set INLINECODE48
• 401/403 → key invalid or missing permission
• 404 → endpoint wrong or region mismatch
• 400 → unsupported model/parameter combination
• Task remains queued too long → check quota, rate limit, or model availability
• No obvious video URL in response → inspect INLINECODE49

References

• - INLINECODE50
• INLINECODE51