skills.rest
ychenjk-sudo
ychenjk-sudoCOMMUNITY
Explore all skills by this author →
GitHub

xiaoyuzhou-transcription

Transcribe 小宇宙 podcast episodes into timestamped Markdown with speaker segmentation.

19|1|Updated Feb 13, 2026
Search Tags:#summarization#transcription#q&a#podcast#xiaoyuzhou#speaker timestamps
One-click install
npx skills add https://github.com/ychenjk-sudo/xiaoyuzhou-transcription-skill --skill xiaoyuzhou-transcription
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: xiaoyuzhou-transcription
Source: https://github.com/ychenjk-sudo/xiaoyuzhou-transcription-skill/tree/main
Command: npx skills add https://github.com/ychenjk-sudo/xiaoyuzhou-transcription-skill --skill xiaoyuzhou-transcription

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires curl, jq, python3, and includes scripts (resource) components.

What problem does it solve?

Converting 小宇宙播客 episodes from audio into readable text is slow and manual, and summarizing the content afterwards takes even more time.

Core Features & Use Cases

  • Auto-extracts audio from a 小宇宙 episode link: Pulls the underlying audio URL from the page so you can start transcription directly.
  • Produces speaker-segmented, timestamped verbatim transcripts: Formats output into structured Markdown with speaker headers and time ranges, including paragraph auto-splitting for long text.
  • Generates structured summaries and Q&A: Creates theme-grouped key points and key question-answer pairs to quickly capture what the episode is about.

Quick Start

In your OpenClaw skills directory, run the skill’s transcription script on a 小宇宙 episode link, then format and review the generated Markdown transcript and summary.

Frequently Asked Questions about xiaoyuzhou-transcription

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

FAQPage Schema
How do I transcribe a Chinese podcast from a xiaoyuzhou link into text?▼

You can transcribe a xiaoyuzhou podcast by running the skill's script on the episode link, which pulls the audio and uses Qwen ASR to generate a verbatim transcript.

Can I get speaker timestamps and segmentation when converting podcast audio to Markdown?▼

Yes, the transcription output is structured Markdown with speaker headers, time ranges, and automatic paragraph splitting every 300 characters for readable podcast transcripts.

Do I need a QWEN_API_KEY to run the podcast transcription script?▼

Yes, you need a QWEN_API_KEY configured to access the qwen3-asr-flash-filetrans API, along with curl, jq, and python3 installed in your environment to execute the script.

Does the transcription workflow support generating summaries and Q&A pairs for podcast episodes?▼

Yes, after producing the verbatim transcript, the skill generates structured summaries with theme-grouped key points and key question-answer pairs to quickly capture episode content.

What are the limitations of using Qwen ASR for xiaoyuzhou podcast transcription?▼

The skill is specifically designed for xiaoyuzhou podcast episodes and relies entirely on the Qwen ASR API for speech recognition, meaning it requires network access and a valid API key to function.

Related Skills

Explore More Content & Communication Skills→
vm0-aivm0-ai
76

qiita

Search, read, and publish Qiita articles via CLI with curl and jq.

Official
Advanced
quanganh208quanganh208

ck:ai-multimodal

Process images, audio, video, and documents into transcripts, OCR, and generated media.

Community
Advanced
beshkenadzebeshkenadze
3

markdown-formatter

Format unstructured text and code into structured Markdown documentation.

Community
Basic
digresik-techdigresik-tech
1

ASR

Transcribe audio files and base64 audio into text using the z-ai-web-dev-sdk.

Community
Intermediate