podcast-ingest

Transcribe podcast episodes from RSS feeds or audio URLs into structured Markdown files.

24|6|Updated Nov 15, 2025

Search Tags:#markdown #transcription #audio #gemini #podcast #rss

Ready to run

npx skills add https://github.com/cdeistopened/skill-stack --skill podcast-ingest

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: podcast-ingest
Source: https://github.com/cdeistopened/skill-stack/tree/main/public/skills/podcast-ingest
Command: npx skills add https://github.com/cdeistopened/skill-stack --skill podcast-ingest

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the process of transcribing podcast episodes from RSS feeds or direct audio URLs into polished Markdown files, making podcast content easily searchable and usable.

Core Features & Use Cases

Automated Transcription: Transcribes audio from podcast episodes using advanced AI models.
RSS Feed Ingestion: Can process entire podcast feeds to transcribe multiple episodes.
Flexible Input: Supports both RSS feed URLs and direct audio file URLs.
Structured Output: Generates Markdown files with YAML frontmatter including title, podcast name, author, date, and source.
Use Case: A content creator wants to turn their latest podcast episode into a blog post. They provide the RSS feed URL, and the Skill generates a complete Markdown document with a summary, topics, speakers, and the full transcript.

Quick Start

Use the podcast-ingest skill to transcribe the latest episode from the RSS feed at https://example.com/podcast.rss.

Frequently Asked Questions about podcast-ingest

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

FAQPage Schema

How do I transcribe podcast episodes from an RSS feed into Markdown?▼

To transcribe podcast episodes into Markdown, provide an RSS feed URL or direct audio URL to process single or multiple audio files and generate structured Markdown with summaries, topics, and full transcripts.

Can I batch transcribe multiple podcast episodes at once?▼

Yes, batch transcription is supported by ingesting entire podcast RSS feeds, which automatically processes multiple episodes and outputs individual structured Markdown files for each audio file.

Do I need Gemini Flash to transcribe audio files?▼

Yes, Gemini Flash is required for audio transcription. It processes the podcast audio and generates the text content, adhering to a cost-effective processing model for the output.

What metadata is included in the generated Markdown frontmatter?▼

The Markdown frontmatter includes title, podcast name, author, date, and source, providing structured metadata alongside the generated summary, topics, speaker lists, and sectioned transcripts.

Can I transcribe a podcast from a direct audio URL instead of an RSS feed?▼

Yes, direct audio URLs are fully supported as input. This allows you to transcribe individual podcast episodes directly without needing to supply the full RSS feed.

Are there limitations to processing audio for podcast transcription?▼

Processing limitations depend on the Gemini Flash model's capabilities and the cost-effective processing model. Transcriptions are structured with summaries, topics, and speakers, but complex audio may impact accuracy.