← 返回 Skills 市场
hljwwyy123

dy-video-to-text

作者 Aiden · GitHub ↗ · v1.0.0 · MIT-0
linuxdarwinwin32 ✓ 安全检测通过
312
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install dy-video-to-text
功能描述
Extract speech-to-text from Douyin (TikTok China) videos, get watermark-free download links, and download videos. Use when user shares a Douyin link, asks to...
使用说明 (SKILL.md)

Douyin Video Processor

Process Douyin (TikTok China) share links: extract video speech to text, get watermark-free download URLs, and download videos locally.

First-Time Setup

Before using any script, install the Python dependencies:

bash scripts/install_deps.sh

This installs requests and dashscope. Only needed once.

Environment Variable

The text extraction feature requires DASHSCOPE_API_KEY from Alibaba Cloud Bailian.

The user must set this before you can call douyin_extract_text.py. If it is not set, tell the user:

To use text extraction, you need an Alibaba Cloud Bailian API key.

  1. Go to https://help.aliyun.com/zh/model-studio/get-api-key
  2. Create an API key (starts with sk-)
  3. Set it: /secrets set DASHSCOPE_API_KEY sk-your-key

The other two scripts (parse and download) do not need any API key.

Available Scripts

1. Parse Video Info (no API key needed)

Extract video metadata (ID, title, watermark-free URL) from a Douyin share link.

python3 scripts/douyin_parse.py "SHARE_LINK"

Input: A Douyin share link or text containing one (e.g. https://v.douyin.com/xxxxx/ or a full share text like "7.29 复制打开抖音... https://v.douyin.com/xxxxx/")

Output: JSON to stdout:

{
  "status": "success",
  "video_id": "7345678901234567890",
  "title": "Video title here",
  "download_url": "https://..."
}

When to use: User wants to see video info, or you need the download URL without downloading the file.


2. Download Video (no API key needed)

Download a watermark-free video file to local disk.

python3 scripts/douyin_download.py "SHARE_LINK" [output_directory]

Input:

  • Arg 1: Douyin share link or text containing one
  • Arg 2 (optional): Output directory, defaults to current directory

Output: JSON to stdout:

{
  "status": "success",
  "video_id": "7345678901234567890",
  "title": "Video title here",
  "file_path": "/absolute/path/to/video.mp4",
  "size_bytes": 12345678
}

When to use: User asks to download a Douyin video, save a video, or get the actual video file.


3. Extract Text from Video (requires DASHSCOPE_API_KEY)

Parse a Douyin share link, then transcribe the video speech to text using Alibaba Cloud ASR.

DASHSCOPE_API_KEY="$DASHSCOPE_API_KEY" python3 scripts/douyin_extract_text.py "SHARE_LINK" [model]

Input:

  • Arg 1: Douyin share link or text containing one
  • Arg 2 (optional): ASR model name, defaults to paraformer-v2

Output: JSON to stdout:

{
  "status": "success",
  "video_id": "7345678901234567890",
  "title": "Video title here",
  "text": "The full transcribed text content from the video..."
}

When to use: User wants to know what's said in a Douyin video, asks to transcribe, extract text, get subtitles, or summarize video content.

Important: Always pass DASHSCOPE_API_KEY as an environment variable in the command. If the key is not set, the script will return an error with setup instructions.

Error Handling

All scripts return JSON even on failure:

{
  "status": "error",
  "error": "Human-readable error message"
}

Common errors and what to tell the user:

Error message contains User-facing guidance
No valid share link The input doesn't contain a valid Douyin URL. Ask the user to paste the full share link.
Failed to parse video info The video may be deleted, private, or region-locked. Ask the user to verify the link opens in a browser.
DASHSCOPE_API_KEY.*not set The API key is missing. Guide the user through setup (see Environment Variable section above).
Transcription failed ASR API error — the key may be invalid or quota exhausted. Ask the user to check their Alibaba Cloud console.
dashscope package not installed Run bash scripts/install_deps.sh to install dependencies.

Batch Processing

When the user provides multiple Douyin links, process them sequentially. For each link:

  1. Call the appropriate script
  2. Parse the JSON output
  3. Collect results
  4. Present a summary table to the user

For batch text extraction, first parse all links with douyin_parse.py to validate them, then extract text only from the valid ones with douyin_extract_text.py. This avoids wasting API calls on broken links.

Cost Awareness

Script API Cost Speed
douyin_parse.py Free ~1-2s
douyin_download.py Free depends on video size
douyin_extract_text.py Alibaba Cloud ASR (very low cost) ~10-30s

Always prefer douyin_parse.py first when you just need to verify a link or get the download URL.

External Endpoints

Endpoint Purpose Data Sent
https://v.douyin.com/* Resolve Douyin share link redirects Share URL
https://www.iesdouyin.com/share/video/* Fetch video page to extract metadata Video ID
Douyin CDN Download video file (douyin_download.py only) None (GET request)
https://dashscope.aliyuncs.com/api/* Alibaba Cloud ASR (douyin_extract_text.py only) Video URL + API key

Security & Privacy

  • DASHSCOPE_API_KEY is only sent to Alibaba Cloud's official API endpoint (dashscope.aliyuncs.com)
  • No data is collected, stored, or transmitted by this skill beyond the API calls listed above
  • Downloaded video files are saved only where the user specifies
  • No persistent background processes

Trust Statement

By using this skill, Douyin share links are sent to Douyin/ByteDance servers for URL resolution, and video URLs may be sent to Alibaba Cloud (Aliyun) for speech-to-text transcription. Only install this skill if you trust these services.

安全使用建议
This skill appears internally consistent, but take these practical precautions before installing or using it: 1) Only provide DASHSCOPE_API_KEY if you trust the source — that key is sent to Alibaba's dashscope.aliyuncs.com for transcription. 2) Review or run the code in a contained environment (virtualenv or ephemeral container) before installing dependencies globally — install_deps.sh uses pip to pull the dashscope package from PyPI. 3) Downloads write .mp4 files to disk; choose an appropriate output directory and be mindful of copyright/privacy when downloading content. 4) If you want extra assurance, inspect the installed dashscope package or use an account/credentials with limited scope/quota. If you want help reviewing any particular line or testing the scripts in a sandbox, I can assist.
功能分析
Type: OpenClaw Skill Name: dy-video-to-text Version: 1.0.0 The skill bundle provides legitimate functionality for parsing, downloading, and transcribing Douyin videos using Python scripts and the Alibaba Cloud DashScope API. The code in scripts like douyin_download.py and douyin_extract_text.py is transparent, follows the stated purpose, and includes proper sanitization for file operations. No evidence of data exfiltration, malicious prompt injection, or unauthorized execution was found.
能力评估
Purpose & Capability
The skill's name/description match the included Python scripts: parse, download, and transcribe Douyin videos. The only required env var is DASHSCOPE_API_KEY and it's only needed for the transcription script, which is consistent with the described Alibaba Cloud ASR integration. Requiring python3 is appropriate.
Instruction Scope
SKILL.md directs the agent to run the provided scripts and to install Python deps. The scripts only access network endpoints relevant to the task (Douyin share pages, Douyin CDN, and dashscope.aliyuncs.com) and either write a downloaded .mp4 (download script) or perform API calls for ASR. The instructions do not ask the agent to read or transmit unrelated local files or other credentials.
Install Mechanism
There is no packaged installer; install_deps.sh uses pip to install requests and dashscope from PyPI. This is a common, traceable mechanism but does modify Python site-packages (user or system) and pulls third-party code at install time — a moderate-risk action compared to instruction-only skills. No arbitrary download URLs or archived extracts are used.
Credentials
Only one credential (DASHSCOPE_API_KEY) is required and it is explicitly used for Alibaba Cloud's Dashscope ASR in the transcription script. Other scripts do not require or reference additional environment variables, so the requested credential is proportionate and justified.
Persistence & Privilege
Skill flags are default (always:false) and it does not request permanent presence or modify other skills or system-wide agent settings. Running the scripts will write downloaded video files to disk (expected behavior) but the skill does not install background services or persist beyond installed packages.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install dy-video-to-text
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /dy-video-to-text 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of douyin-video-processor: - Extracts speech-to-text from Douyin (TikTok China) videos using Alibaba Cloud ASR. - Provides watermark-free download links from Douyin share URLs. - Downloads Douyin videos to your local device. - Requires API key (DASHSCOPE_API_KEY) only for text extraction. - Includes clear setup instructions, error messages, and batch processing guidance.
元数据
Slug dy-video-to-text
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

dy-video-to-text 是什么?

Extract speech-to-text from Douyin (TikTok China) videos, get watermark-free download links, and download videos. Use when user shares a Douyin link, asks to... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 312 次。

如何安装 dy-video-to-text?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install dy-video-to-text」即可一键安装,无需额外配置。

dy-video-to-text 是免费的吗?

是的,dy-video-to-text 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

dy-video-to-text 支持哪些平台?

dy-video-to-text 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(linux, darwin, win32)。

谁开发了 dy-video-to-text?

由 Aiden(@hljwwyy123)开发并维护,当前版本 v1.0.0。

💬 留言讨论