good-TTvideo2text

Extract audio from Douyin/TikTok videos and transcribe it to timestamped text.

195|44|Updated Jan 8, 2026
One-click install
npx skills add https://github.com/ImGoodBai/goodable --skill good-ttvideo2text
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: good-TTvideo2text
Source: https://github.com/ImGoodBai/goodable/tree/main/skills/good-TTvideo2text
Command: npx skills add https://github.com/ImGoodBai/goodable --skill good-ttvideo2text

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Douyin/TikTok video audio can be tedious to extract and convert into readable text, especially when timestamps and metadata matter. This Skill automates the process of pulling audio from short videos and transcribing it to text with precise timing, reducing manual effort and improving accessibility.

Core Features & Use Cases

  • Audio extraction from Douyin/TikTok videos and transcription to timestamped text.
  • Web UI plus script-based workflow for end-to-end transcription, including URL parsing and ASR orchestration.
  • Handles short URLs, redirects, and metadata, with optional cookies for restricted videos.

Quick Start

Provide a Douyin/TikTok URL in the UI or pass it to the transcribe script to start transcription.

Frequently Asked Questions about good-TTvideo2text

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

FAQPage Schema
How do I extract audio and transcribe TikTok videos to text?

Douyin video transcription automates audio extraction and ASR processing to convert short video audio into timestamped text. It handles URL parsing, metadata retrieval, and ASR orchestration end-to-end.

Can I transcribe restricted Douyin videos using cookies?

Yes, you can transcribe restricted Douyin videos by providing optional cookie support. This allows the TikTokDownloader component to access and extract audio from videos that require authentication.

Does the transcription process support short URLs and redirects?

Yes, the transcription process fully supports short URLs and redirects. It automatically resolves them to retrieve video metadata and extract audio before sending it to the ASR service.

How do I configure ASR services for video transcription?

You configure ASR services for video transcription by setting the GOODABLE_ASR_SUBMIT_URL and GOODABLE_ASR_QUERY_URL_TEMPLATE environment variables. The FastAPI server uses these to orchestrate speech recognition.

Are there limitations when extracting audio from short videos?

Audio extraction from short videos depends on TikTokDownloader for data access and a configured ASR service for transcription. Without proper environment variables or optional cookies for restricted content, extraction will fail.