kuaishou-video-extract

Kuaishou Video Transcript Extraction

📝 Introduction

Extract spoken-word transcripts (ASR transcription) via Kuaishou video links. The script automatically completes the two-step process of "submit task → poll → get results", returns the full transcript and timestamped sentences, and supports task ID follow-up queries.

✨ Features

Feature Module	Capability Description	Core Value
One-Click Transcript Extraction	Submit a video link to automatically complete submission + polling	One-click conversion of spoken-word scripts to text
Full Transcript	Return the full transcript text concatenated from all segments	Directly replicate topic scripts
Timestamped Sentences	Array of timestamped sentences (text/start/end)	Precise positioning for subtitles/editing
Task Follow-Up Query	Support --task-id to query existing task results	If it times out midway, you can follow up without losing the task
Status Compatibility	Compatible with multiple statuses such as succeeded/failed/processing	Stable and reliable polling process

🎯 Target Users

🔍 Content Creators — Replicate the spoken-word scripts of viral videos and break down topic structures.
📊 Operations / Data Analysis — Quickly transcribe video content and evaluate copy quality.
🎬 Editing / Subtitles — Quickly generate subtitle scripts using timestamped sentences.

🔑 Authentication

Get API Key

Visit Red Fox Hub official website to learn more about the service
Go to registration page to register an account
Newly registered users will receive free credits, and can immediately start using the API service
After registering and logging in, obtain the API Key in the personal center. The format is ak_xxxxxxxx

Configure API Key

REDFOX_API_KEY obtained from environment variables, format ak_xxxxxxxx
If not set, prompt the user to configure it themselves:export REDFOX_API_KEY=<你的apikey>; if the user does not know how to configure it, the Agent should proactively help the user set it up:
- macOS/Linux: Append export REDFOX_API_KEY=<值> to ~/.zshrc(zsh) or ~/.bashrc(bash), then source the corresponding file to make it take effect globally
- Windows: Use [Environment]::SetEnvironmentVariable("REDFOX_API_KEY", "<值>", "User") to set a user-level permanent environment variable (requires restarting the terminal to take effect)
- After configuration is complete, verify:echo $REDFOX_API_KEY(macOS/Linux) or echo %REDFOX_API_KEY%(Windows), to ensure it can be read even when switching to another skill

🔄 Usage Guide

Extract spoken-word transcripts via Kuaishou video links, automatically complete the "submit task → poll → get results" process, return the full transcript and timestamped sentences, and support task ID follow-up queries.

For detailed execution steps, parameter descriptions, and output format, see references/core_workflow.md

📂 Related Files

Path	Purpose
`scripts/extract_ks_text.py`	Video script extraction script
`references/core_workflow.md`	Core execution flow and output specifications
`README.md`	Complete interface description and return field documentation