skills.rest
KingJing1
KingJing1COMMUNITY
Explore all skills by this author →
Website𝕏@KingJing001GitHub

podcast-transcript-txt

Export podcast episodes into cleaned TXT transcripts with .meta.json diagnostics.

37|2|Updated Feb 21, 2026
Search Tags:#transcript#web scraping#youtube#podcast#asr#txt export#quality diagnostics
One-click install
npx skills add https://github.com/KingJing1/podcast-transcript-txt-skill --skill podcast-transcript-txt
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: podcast-transcript-txt
Source: https://github.com/KingJing1/podcast-transcript-txt-skill/tree/main
Command: npx skills add https://github.com/KingJing1/podcast-transcript-txt-skill --skill podcast-transcript-txt

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yt-dlp, faster-whisper, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Turning podcast episodes into searchable transcripts is slow and inconsistent, especially when official transcripts are missing. This Skill reliably extracts transcript text (or falls back to subtitles or local ASR) and writes a cleaned TXT plus a .meta.json for debugging.

Core Features & Use Cases

  • Deterministic transcript resolution: prioritizes official transcript sources, then YouTube subtitles, then episode/page visible text, and finally local ASR with selectable small|medium models.
  • Multiple input types: handles YouTube URLs/IDs, episode webpages (including Xiaoyuzhou), official transcript URLs/files (TTML/JSON), direct audio URLs, Apple Podcasts title search, X/Twitter links (best-effort), and plain episode titles.
  • Observable output quality: always emits a matching .meta.json containing resolver path and quality/attempt diagnostics so you know whether the result is official/subtitle/page-text/ASR-derived.

Quick Start

Run python3 scripts/podcast_transcript_txt.py --input "https://www.youtube.com/watch?v=n1E9IZfvGMA" --out-dir "/tmp/transcripts" and then use the generated TXT and .meta.json.

Frequently Asked Questions about podcast-transcript-txt

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

FAQPage Schema
How do I export a YouTube podcast transcript to TXT?▼

To export a YouTube podcast transcript to TXT, run the script with a YouTube URL or video ID. It prioritizes official subtitles and writes a cleaned text file alongside a .meta.json diagnostics file.

Can I transcribe a podcast from Xiaoyuzhou or Apple Podcasts?▼

Yes, you can transcribe podcasts from Xiaoyuzhou episode webpages and Apple Podcasts title queries. The tool resolves episode page text and falls back to local ASR if no official transcript is available.

What sources are prioritized when resolving a podcast transcript?▼

Podcast transcript resolution prioritizes official transcript URLs or files, then YouTube subtitles, then structured episode page text, and finally local faster-whisper ASR as a fallback.

Do I need faster-whisper to generate podcast transcripts?▼

You only need faster-whisper when official transcripts, platform subtitles, or page text are unavailable. It acts as a local ASR fallback with selectable small or medium models to generate text from audio.

How do I check the quality of an extracted podcast transcript?▼

You check podcast transcript quality by reading the emitted .meta.json file. It contains the resolver path, quality metrics, and attempt diagnostics indicating whether the output is official, subtitle, page-text, or ASR-derived.

What file formats are supported for official podcast transcript imports?▼

Official podcast transcript imports support TTML and JSON file formats. The script processes these direct transcript URLs or local files to output a cleaned, searchable TXT transcript.

Related Skills

Explore More Content & Communication Skills→
HKUDSHKUDS
46.8k

summarize

Summarize URLs, YouTube videos, PDFs, and text files into concise overviews.

Official
Advanced
math-incmath-inc
1.2k

youtube-content

Extract YouTube transcripts and convert them into JSON or text formats.

Official
Intermediate
zcacereszcaceres
7

transcribe-youtube

Download YouTube audio with yt-dlp and transcribe it to markdown using Whisper.

Community
Intermediate
davpatel605-beepdavpatel605-beep

whisper

Transcribe spoken audio into timestamped text across 99 languages.

Community
Intermediate