Podcast Transcript TXT

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.