podcast-transcript-txt skillA
podcast-transcript-txt is agent-read markdown (skill) from kingjing1/podcast-transcript-txt-skill: Deterministic workflow to find and export full podcast transcripts as cleaned TXT files from YouTube URLs, episode webpages (including Xiaoyuzhou), Apple Podcasts title search, X/Twitter links, direct audio URLs, or plain episode titles. Use when users ask for 逐字稿/文字版/transcript/txt and want minimal trial-and-error..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Podcast Transcript TXT ## Overview Produce clean TXT transcript-like outputs for podcast/video episodes with a fixed decision tree. Prioritize official transcript sources first, then platform subtitles or official page text, then local ASR fallback. ASR fallback uses `faster-whisper` with selectable `--asr-model small|medium` (default `small`). All transcript outputs are working drafts; always recommend one strong-LLM proofreading pass. ## Workflow Decision Tree 1. Normalize input. - Accept one or more `--input` values. - Support (stable): YouTube URL/ID, episode webpages (including Xiaoyuzhou), direct audio URLs, or plain title. - X/Twitter status URL: best-effort resolver to outbound sources. 2. Resolve canonical episode source. - Stable path A: if input is YouTube URL/ID, use it directly. - Stable path B: if input is direct official transcript URL/JSON, parse it directly. - Stable path B2: if input is a local official transcript file (`.ttml`, supported `.json`), parse it directly. - Stable path C: if input is direct audio URL, go to local ASR path. …
Read the whole file at its exact version.
How to install
mdr add kingjing1/podcast-transcript-txt-skill/podcast-transcript-txt@git:20260404.e93217bmdr add kingjing1/podcast-transcript-txt-skill/podcast-transcript-txt@sha256:165ce41c3a723f46Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_c7r4ajsdpyg2jnr5)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260404.e93217b latest | 2026-04-04 | e93217b | 6,650 B | A | view · diff |
| git:20260401.578f861 | 2026-04-01 | 578f861 | 6,431 B | A | view · diff |
| git:20260325.baee125 | 2026-03-25 | baee125 | 6,361 B | A | view · diff |
| git:20260323.3a74874 | 2026-03-23 | 3a74874 | 6,361 B | A | view · diff |
| git:20260322.8f6462c | 2026-03-22 | 8f6462c | 5,406 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6650 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kingjing1/podcast-transcript-txt-skill · 46 stars · license MIT · pushed 2026-09-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_c7r4ajsdpyg2jnr5 GET https://markdownregistry.com/api/v1/resolve?ref=kingjing1/podcast-transcript-txt-skill/podcast-transcript-txt GET https://markdownregistry.com/api/v1/blob/165ce41c3a723f468c93dd7ab0ed2c8475e6c06dc595d5a3f63a60b1a24fff19
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.