Do I need a specific API key to use this skill?

Yes, you must provide a GEMINI_API_KEY as an environment variable to allow the script to access Google's Gemini Flash for transcription.

How much does it cost to transcribe a podcast using this skill?

Using the Gemini Flash model, it costs approximately $0.005 per hour of audio, making a typical one-hour episode cost less than a penny.

Where does the skill save the output files?

By default, all generated markdown transcripts are saved to the 'output/podcasts/' directory within your workspace.

What format are the transcripts provided in?

Transcripts are generated as markdown files with YAML frontmatter containing metadata like title, author, and date, followed by a summary, topics list, and speaker-labeled transcript.

Can I transcribe multiple episodes at once?

Yes, you can use the --limit flag to specify the number of latest episodes you want to transcribe from a specific RSS feed.

Podcast Ingest & Transcription

Name: Podcast Ingest & Transcription
Author: cdeistopened

bycdeistopened

•

Content Management

Transcribes podcast episodes from RSS feeds into structured, searchable markdown files using Gemini Flash AI.

Podcast Ingest streamlines the process of converting audio content into written intelligence by fetching podcast RSS feeds and generating polished markdown transcripts. It uses Gemini Flash to provide an ultra-affordable transcription solution that includes YAML frontmatter, summaries, topic categorization, speaker identification, and full sectioned transcripts. This skill is perfect for researchers, content creators, and developers looking to build a structured knowledge base from audio sources directly within their Claude Code environment.

Key Features

01Cost-effective transcription using Gemini Flash (~$0.005/hour)

028 GitHub stars

03Batch processing for multiple recent episodes

04Direct audio URL support for specific episode ingestion

05Automated RSS feed parsing and episode discovery

06Structured markdown output with metadata and summaries

Use Cases

01Automating the collection of podcast content for secondary AI analysis

02Building a searchable markdown knowledge base from industry podcasts

03Generating written summaries and speaker-identified transcripts for research

Key Features

01Cost-effective transcription using Gemini Flash (~$0.005/hour)

028 GitHub stars

03Batch processing for multiple recent episodes

04Direct audio URL support for specific episode ingestion

05Automated RSS feed parsing and episode discovery

06Structured markdown output with metadata and summaries

Use Cases

01Automating the collection of podcast content for secondary AI analysis

02Building a searchable markdown knowledge base from industry podcasts

03Generating written summaries and speaker-identified transcripts for research