douyin-download

v1.2.0

抖音无水印视频下载和文案提取工具

4· 1.7k·12 current·12 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for whille/douyin-download.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "douyin-download" (whille/douyin-download) from ClawHub.
Skill page: https://clawhub.ai/whille/douyin-download
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required env vars: SILI_FLOW_API_KEY
Required binaries: ffmpeg
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install whille/douyin-download

ClawHub CLI

Package manager switcher

npx clawhub@latest install douyin-download
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name/description (download Douyin no-watermark video + extract text) aligns with the code: the script fetches video info, downloads video, extracts audio, sends audio to Silicon Flow for ASR, and (optionally) calls an LLM for semantic segmentation. However the SKILL.md claims segmentation uses the OpenClaw built-in LLM while the code calls an external MiniMax API if MINIMAX_API_KEY is set. Also SKILL.md lists only SILI_FLOW_API_KEY but the code references MINIMAX_API_KEY — an undeclared credential.
!
Instruction Scope
SKILL.md instructs running the included node script which will: (a) follow network redirects and access iesdouyin.com and video URLs, (b) download files to /tmp/douyin-download, (c) invoke ffmpeg, and (d) call external transcription and LLM endpoints. The code also spawns curl for POSTing audio and for LLM calls; curl is not listed in required binaries. The script reads process.env.MINIMAX_API_KEY in addition to the declared SILI_FLOW_API_KEY — SKILL.md does not document MINIMAX_API_KEY. These are scope/information mismatches and the use of an external LLM provider differs from the documentation's claim of using an internal LLM.
Install Mechanism
No install spec (instruction-only with bundled code) — lower install risk because nothing is downloaded at install time. But the shipped code will spawn system binaries (ffmpeg and curl) at runtime, and write files to /tmp. Because the code executes child processes and performs network calls, review of the included JS file is important before use.
!
Credentials
SKILL metadata declares only SILI_FLOW_API_KEY. The code legitimately uses SILI_FLOW_API_KEY for Silicon Flow ASR, which is expected. However the code also uses MINIMAX_API_KEY (for MiniMax API) if present — this env var is not declared in the skill metadata or SKILL.md usage section (only mentioned in JS comments). Requiring/using an extra credential without declaring it is disproportionate and surprising to users. Also the code will POST audio and text to external endpoints (siliconflow.cn and api.minimaxi.com), which is expected for the feature but worth noting.
Persistence & Privilege
No always:true; the skill is not force-installed and does not request elevated or persistent agent-level privileges. It does not modify other skill configs or system-wide agent settings. Its runtime behavior is limited to running the included script and contacting external services.
What to consider before installing
This skill is functionally consistent with a Douyin downloader/transcriber, but there are important mismatches you should consider before installing: - The SKILL.md declares only SILI_FLOW_API_KEY and ffmpeg, but the code also uses MINIMAX_API_KEY (undeclared) and spawns curl (an undeclared required binary). Expect the script to call external services at https://api.siliconflow.cn and https://api.minimaxi.com. - SKILL.md states it uses the OpenClaw built-in LLM for segmentation, but the code calls an external MiniMax API if MINIMAX_API_KEY is set. Ask the author to clarify whether segmentation uses an internal model or an external provider, and to document MINIMAX_API_KEY if required. - Before using, verify you have (or are willing to permit) ffmpeg and curl on the host, and that you are comfortable that audio and extracted text will be sent to the listed external endpoints. Consider creating/using API keys with limited scope or a disposable key. - If you need higher assurance, review the full douyin.js file locally (it was included) and run the script in a sandboxed environment (container or VM) to observe network calls and file writes. If the author provides an updated SKILL.md that documents MINIMAX_API_KEY and adds curl to required binaries (or modifies the code to use the platform's internal LLM as documented), that would reduce the current concerns.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

🎵 Clawdis
Binsffmpeg
EnvSILI_FLOW_API_KEY
latestvk972gjrc2bxzqdnw5thhcbmxdh81yvm4
1.7kdownloads
4stars
4versions
Updated 1mo ago
v1.2.0
MIT-0

douyin-download Skill

抖音无水印视频下载和文案提取工具。

功能

  • 🎬 获取无水印视频下载链接
  • 📥 下载抖音视频
  • 🎙️ 从视频中提取语音文案(需要 API Key)
  • ✂️ 语义分段(调用 OpenClaw 内置 LLM)

环境变量

  • SILI_FLOW_API_KEY - 硅基流动 API 密钥(用于语音转文字)

获取 API Key: https://cloud.siliconflow.cn/

使用方法

获取视频信息

node /root/.openclaw/workspace/skills/douyin-download/douyin.js info "抖音分享链接"

下载视频

node /root/.openclaw/workspace/skills/douyin-download/douyin.js download "抖音链接" -o /tmp/douyin-download

提取文案(自动语义分段)

#SILI_FLOW_API_KEY="your-api-key"
node /root/.openclaw/workspace/skills/douyin-download/douyin.js extract "抖音链接"
  • 自动调用 Silicon Flow ASR 提取文字
  • 自动调用 OpenClaw 内置 LLM 进行自然语义分段

跳过语义分段

node /root/.openclaw/workspace/skills/douyin-download/douyin.js extract "抖音链接" --no-segment

Comments

Loading comments...