douyin-video-extractor

Extract watermark-free Douyin/TikTok videos and transcribe audio to Markdown.

7|2|Updated May 16, 2026
One-click install
npx skills add https://github.com/Aradotso/mcp-skills --skill douyin-video-extractor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: douyin-video-extractor
Source: https://github.com/Aradotso/mcp-skills/tree/main/skills/douyin-video-extractor
Command: npx skills add https://github.com/Aradotso/mcp-skills --skill douyin-video-extractor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Douyin/TikTok share links and videos are hard to turn into usable text because you need reliable extraction of watermark-free video content plus accurate speech-to-text transcription.

Core Features & Use Cases

  • Watermark-free video link extraction: Converts a Douyin/TikTok share URL into a direct download link.
  • AI transcription from video audio: Transcribes spoken content into text using an AI speech recognition model (SenseVoice) with API-key support.
  • Large-file handling and export: Automatically chunks long audio (over ~1 hour or ~50MB) and saves transcripts as Markdown for easy sharing and downstream use.
  • Use case: Paste a Douyin share link to automatically download the video (without watermark) and generate a clean Markdown transcript for notes, summaries, or content repurposing.

Quick Start

Ask the skill to extract a Douyin transcript from the link https://v.douyin.com/xxxxx/ and save the result to your output directory.

Frequently Asked Questions about douyin-video-extractor

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

FAQPage Schema
How do I convert a Douyin share link into a text transcript?

To convert a Douyin share link into a text transcript, paste the URL and the tool extracts the watermark-free video and transcribes its audio into text. It automatically generates a clean Markdown transcript for easy sharing and downstream use.

Does transcribing TikTok video audio require an API key?

Transcribing TikTok video audio requires an optional API key for the speech-to-text model. The AI speech recognition component uses this key to accurately process the extracted audio and generate the written text output.

Can I extract watermark-free videos from long-form Douyin content?

You can extract watermark-free videos from long-form Douyin content. The tool automatically handles large files by chunking long audio that exceeds approximately one hour or 50MB, ensuring reliable transcription and Markdown export.

What is the best way to export short social video transcripts for content auditing?

The best way to export short social video transcripts for content auditing is to input the share URL and let the tool output a Markdown file. This process provides clean written text from the video audio, suitable for meeting notes and summaries.

How does the speech-to-text mechanism handle large media files?

The speech-to-text mechanism handles large media files by automatically chunking audio that exceeds roughly one hour or 50MB. This chunking process ensures the AI speech recognition model can process long-form social videos without failing.

Why does the Markdown export not include the video watermark?

The Markdown export does not include the video watermark because the tool first converts the Douyin or TikTok share URL into a direct download link for the raw media. It then transcribes only the spoken audio content into clean text.