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.
Installs into .claude/skills of the current project.
Are you the author of Podcast Transcription Pipeline Agent?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/agentskillexchange-podcast-transcription-pipeline-agent)
---
name: "Podcast Transcription Pipeline"
slug: "podcast-transcription-pipeline-agent"
description: "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."
verification: "listed"
source: "https://platform.openai.com/docs/guides/speech-to-text"
author: "OpenAI"
category: "Media & Transcription"
framework: "Codex"
---
# 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.
## Installation
No source-backed install or usage instructions could be extracted automatically. Review the upstream project before running this skill in a sensitive workflow.
- Source: https://platform.openai.com/docs/guides/speech-to-text
## Documentation
- https://platform.openai.com/docs/guides/speech-to-text
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/podcast-transcription-pipeline-agent/)
