# Podcast

Turn research into a spoken podcast, script, synthesize, stitch.

- Repository: https://github.com/codewhale-hq/Codewhale (41164 stars)
- Category: Writing
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add codewhale-hq/Codewhale --skill podcast -g -a claude-code -y`
Codex: `npx skills add codewhale-hq/Codewhale --skill podcast -g -a codex -y`
Cursor: `npx skills add codewhale-hq/Codewhale --skill podcast -g -a cursor -y`
Gemini CLI: `npx skills add codewhale-hq/Codewhale --skill podcast -g -a gemini-cli -y`

## Description

Turn research into a spoken podcast, script, synthesize, stitch. Use when: podcast, generate a podcast, audio briefing, narrate, or turn this into audio.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Podcast

## When to use
Producing a spoken-audio episode from a topic, document set, or briefing, the full pipeline from research to an mp3.

## Setup
Requires `ffmpeg` for stitching (`brew install ffmpeg`, `apt install
ffmpeg`). Voices come from the `tts` skill. Fail loud when `ffmpeg` is missing.

## Workflow
1. Research the topic and draft a spoken script (~150 words per minute of
   audio). Read it back for approval before synthesizing.
2. Synthesize per segment with `tts`; keep segments under 2 minutes each.
3. Stitch: `ffmpeg -f concat -safe 0 -i segments.txt -codec:a libmp3lame out.mp3`.
4. Report duration, segment count, and the output path.

## Non-goals
- Do not publish or upload the episode anywhere.
- Do not synthesize more than the approved script.
- Do not clone real people's voices (see `tts` non-goals).