Podcast Transcription Pipeline
Podcast Transcription Pipeline
Transcribes podcast episodes using OpenAI Whisper API with speaker diarization via pyannote.audio. Exports formatted transcripts to SRT, VTT, and searchable JSON with timestamped segments.
Overview
The Podcast Transcription Pipeline provides end-to-end audio transcription for podcast episodes and audio content. It uses the OpenAI Whisper API (whisper-1 model) for high-accuracy speech-to-text conversion with word-level timestamps. Speaker diarization is performed using the pyannote.audio pipeline with pretrained speaker segmentation models, identifying and labeling individual speakers throughout the episode. The agent handles audio preprocessing with FFmpeg for format conversion, noise reduction via SoX noisered, and silence trimming. It supports batch processing of RSS feeds using the podcast index API to automatically fetch new episodes. Output formats include SRT subtitles, WebVTT captions, plain text transcripts, and searchable JSON with segment-level timestamps and speaker labels. The pipeline integrates with Transistor.fm API and Podbean API for automatic transcript attachment to published episodes. It generates chapter markers from topic changes detected via semantic similarity scoring using sentence-transformers embeddings. Includes keyword extraction using spaCy NER and automatic show notes generation summarizing key topics, guest mentions, and referenced resources.
Installation
Any Agent
npx skills add agentskillexchange/skills --skill podcast-transcription-pipeline-agent
Claude Code
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.
24playwright 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