Podcast RSS Feed Transcriber
Podcast RSS Feed Transcriber
Automatically fetches podcast episodes from RSS feeds using feedparser, downloads audio enclosures, and transcribes them through OpenAI Whisper API or local faster-whisper models. Generates timestamped SRT files and searchable markdown transcripts with speaker diarization via pyannote.audio.
Overview
Podcast RSS Feed Transcriber automates the end-to-end workflow from podcast feed subscription to searchable transcript generation. It parses RSS feeds using Python’s feedparser library, extracts audio enclosure URLs, and downloads episodes with proper handling of redirects, CDN authentication tokens, and content-type validation.
Audio processing routes through either the OpenAI Whisper API for cloud-based transcription or local faster-whisper models for privacy-sensitive workflows. The skill automatically selects the appropriate Whisper model size based on audio duration and available compute resources. Speaker diarization uses pyannote.audio’s pretrained pipeline to segment transcripts by speaker, assigning speaker labels to each utterance segment.
Output formats include timestamped SRT and VTT subtitle files, speaker-attributed markdown transcripts, and plain text for full-text search indexing. The transcriber maintains a local SQLite database tracking processed episodes to avoid re-transcription. For ongoing podcast monitoring, it runs on a configurable schedule, checking feeds for new episodes via ETag and Last-Modified HTTP headers. Transcript quality is improved through post-processing that corrects common Whisper errors using a custom dictionary of domain-specific terms.
Installation
Any Agent
npx skills add agentskillexchange/skills --skill podcast-rss-feed-transcriber
Claude Code
npx skills add agentskillexchange/skills --skill podcast-rss-feed-transcriber -a claude-code
Cursor
npx skills add agentskillexchange/skills --skill podcast-rss-feed-transcriber -a cursor
Codex
npx skills add agentskillexchange/skills --skill podcast-rss-feed-transcriber -a codex
OpenClaw
clawhub install podcast-rss-feed-transcriber
Source
More from agentskillexchange/skills
your skill name
A clear description of what this skill does and when to use it. Reference specific APIs, tools, or techniques.
18playwright visual regression tester
Automates visual regression testing using the Playwright screenshot comparison API and pixelmatch diffing library. Captures baseline snapshots, detects pixel-level UI changes across viewport sizes, and generates HTML diff reports with threshold-based pass/fail results.
2playwright visual regression suite
Automated visual regression testing using Playwright’s screenshot comparison API (page.screenshot with maxDiffPixelRatio) and toMatchSnapshot assertions. Supports cross-browser testing on Chromium, Firefox, and WebKit.
2stripe payments connector
Full Stripe API integration using the stripe-node SDK. Creates PaymentIntents via stripe.paymentIntents.create(), manages Customers and Subscriptions, handles webhook events through stripe.webhooks.constructEvent(), and supports Stripe Connect for marketplace payouts.
2grafana loki log query agent
Queries Grafana Loki log aggregation system using LogQL via the Loki HTTP API. Filters log streams by labels, parses structured JSON logs, and correlates log entries with Grafana dashboard panels.
2great expectations data validation pipeline
Validate data quality using the Great Expectations Python library. Define expectations as unit tests for your data, run validation suites, and generate human-readable data quality reports.
1