Skip to content
Back to search

podcast

Generate a podcast episode from content you provide. Paste text, point to local files, or describe a topic. Two AI hosts discuss it in a natural conversation. Listen locally or in your favorite podcast app via RSS.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/zarazhangrui--personalized-podcast/badge.svg)](/listings/zarazhangrui--personalized-podcast)

HTML

<a href="/listings/zarazhangrui--personalized-podcast"><img src="/api/listings/zarazhangrui--personalized-podcast/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. Install

gh repo clone zarazhangrui/personalized-podcast-skill ~/.claude/skills/personalized-podcast

2. Go

/podcast <paste content, point to files, or describe a topic>

That's it. On first run, Claude sets up the Python environment, installs dependencies, and asks you for a free [Fish Audio](https://fish.audio) API key. Default voices are pre-configured. Your first episode generates immediately.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md · Manifest · 235 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. ---
  2. name: podcast
  3. description: Generate a podcast episode from content you provide. Paste text, point to local files, or describe a topic. Two AI hosts discuss it in a natural conversation. Listen locally or in your favorite podcast app via RSS.
  4. ---
  5. ## Path convention
  6. Throughout this file:
  7. - `SKILL_DIR` = the directory where this SKILL.md file lives (the skill's install location)
  8. - `DATA_DIR` = `~/.personalized-podcast` (where user data, config, and episodes are stored)
  9. Resolve these to absolute paths before running any commands.
  10. # Personalized Podcast
  11. When the user invokes this skill, start by introducing it:
  12. > "This skill turns any content into a podcast episode with two AI hosts who discuss it in a natural, conversational style. Think NotebookLM, but you control everything: the script prompt, the hosts' voices, the show format.
  13. >
  14. > You can use it to:
  15. >
  16. > - **Listen to anything on the go.** Paste an article, point to a file, drop a URL. Instead of reading, you get two people breaking it down while you walk, commute, or cook.
  17. > - **Understand yourself from the outside.** Feed it personal content like meeting transcripts, your resume, or journal entries, and have the hosts share their impressions of you. It's genuinely illuminating.
  18. > - **Create your own show.** Set up an RSS feed and new episodes show up in the podcast app you already use (Apple Podcasts, Spotify, Overcast, Snipd). No new app to download.
  19. >
  20. > Let's get started. What content do you want to turn into a podcast?"
  21. If the user already provided content with their `/podcast` command, skip the question and go straight to setup check.
  22. ---
  23. ## First-time setup
  24. If `DATA_DIR/config.yaml` does not exist, run through this setup BEFORE generating. Do each step yourself - don't ask the user to run commands.
  25. ### Step 1: Install dependencies
  26. ```bash
  27. mkdir -p DATA_DIR/{scripts_output,episodes,logs}
  28. python3 -m venv DATA_DIR/venv
  29. DATA_DIR/venv/bin/pip install httpx pydub pyyaml python-dotenv jinja2 audioop-lts
  30. ```
  31. Check ffmpeg is installed:
  32. ```bash
  33. ffmpeg -version
  34. ```
  35. If not found, install it: `brew install ffmpeg` (macOS) or `sudo apt install ffmpeg` (Linux).
  36. ### Step 2: Create config with default voices
  37. ```bash
  38. cp SKILL_DIR/config/config.example.yaml DATA_DIR/config.yaml
  39. ```
  40. The config comes with two pre-picked voices that work out of the box. No voice selection needed for first use.
  41. ### Step 3: Get Fish Audio API key
  42. Tell the user:
  43. > "To turn your script into audio, this skill uses Fish Audio for text-to-speech. They have a free tier with 2 million+ voices. You just need an API key:
  44. >
  45. > 1. Go to https://fish.audio and create a free account
  46. > 2. Go to https://fish.audio/app/api-keys/ and create an API key"
  47. Then create the .env file and open it:
  48. ```bash
  49. echo "FISH_API_KEY=your_key_here" > DATA_DIR/.env
  50. open DATA_DIR/.env
  51. ```
  52. Tell them: "Paste your Fish Audio API key in this file, replacing 'your_key_here'. Save and close."
  53. IMPORTANT: Never ask the user to paste API keys in the chat. Always use the .env file.
  54. ### Step 4: Done
  55. Tell the user:
  56. > "You're all set! The default show has two hosts - Alex (curious, energetic) and Sam (analytical, witty) - with voices pre-configured. Let's generate your first episode."
  57. Then proceed to generate the episode. Do NOT set up RSS or GitHub Pages during first-time setup. That's optional and comes later.
  58. ---
  59. ## Generating an episode
  60. ### Step 1: Read the content
  61. Read all the content the user provided. If they pointed to files, read them with the Read tool. If they pasted a URL, fetch it. Combine everything into your understanding of the source material.
  62. ### Step 2: Write the podcast script
  63. Read the prompt file at `SKILL_DIR/PROMPT.md` for the hosts, style, structure, and output format. Follow those instructions to write the script.
  64. If the user included custom instructions in their `/podcast` message (e.g., "make it a debate" or "hosts should eavesdrop on my conversation"), incorporate those. The user's inline instructions override PROMPT.md for that episode.
  65. Save the script as a JSON array using the Write tool to: `DATA_DIR/scripts_output/YYYY-MM-DD.json` (use today's date). If a file for today already exists, append a number (e.g., `2026-04-05-2.json`).
  66. ### Step 3: Generate audio
  67. Tell the user: "Script written. Now generating audio - this takes about a minute depending on episode length."
  68. Run the speak script:
  69. ```bash
  70. DATA_DIR/venv/bin/python SKILL_DIR/scripts/speak.py --script <path_to_script.json>
  71. ```
  72. This outputs the path to the generated MP3 file.
  73. ### Step 4: Play the audio
  74. IMMEDIATELY open the audio file for the user:
  75. ```bash
  76. open <path_to_mp3>
  77. ```
  78. On Linux use `xdg-open` instead of `open`.
  79. ### Step 5: Post-generation tips
  80. After the audio plays, tell the user:
  81. > "Your episode is ready! A few things you can do from here:
  82. >
  83. > **Try different show formats.** The default is two hosts chatting, but you can do anything. Just describe it when you run `/podcast`:
  84. >
  85. > - "/podcast make it a debate about this article"
  86. > - "/podcast hosts should eavesdrop on my conversation and share their impressions of me"
  87. > - "/podcast interview format, one host asks questions and the other is the expert"
  88. > - "/podcast solo narrator, walk me through this research paper"
  89. > - "/podcast news roundup, read each tweet aloud then discuss"
  90. >
  91. > Or edit `PROMPT.md` to permanently change your show's format.
  92. >
  93. > **Pick your own voices.** The default voices are solid, but Fish Audio has 2 million+ to choose from. Browse https://fish.audio/discovery, find two you like, and update the voice IDs in `DATA_DIR/config.yaml`.
  94. >
  95. > **Listen in your podcast app.** Want new episodes delivered to Apple Podcasts, Spotify, Overcast, or Snipd automatically? Just ask me to set up an RSS feed for you - takes about a minute."
  96. Only show these tips the FIRST time, or if the user asks about customization.
  97. ---
  98. ## RSS feed setup (only when user asks)
  99. When the user wants to set up an RSS feed, explain why it's useful:
  100. > "This creates a personal podcast feed that works in any podcast app. Once it's set up, every time you generate a new episode, it gets published to the feed and shows up where you already listen to podcasts. No new app needed."
  101. Then walk them through these steps:
  102. ### 1. Create a public GitHub repo
  103. Ask for their GitHub username, then:
  104. ```bash
  105. gh repo create USERNAME/podcast-feed --public --description "Personal podcast feed"
  106. ```
  107. ### 2. Enable GitHub Pages
  108. ```bash
  109. cd /tmp && mkdir podcast-feed && cd podcast-feed && git init
  110. echo '[]' > episodes.json
  111. ```
  112. Generate an initial empty feed.xml using the template, then push and enable GitHub Pages:
  113. ```bash
  114. gh api repos/USERNAME/podcast-feed/pages -X POST --input - << 'EOF'
  115. {"source":{"branch":"main","path":"/"},"build_type":"legacy"}
  116. EOF
  117. ```
  118. ### 3. Update config
  119. Update `DATA_DIR/config.yaml` with:
  120. ```yaml
  121. publish:
  122. github_repo: "USERNAME/podcast-feed"
  123. base_url: "https://USERNAME.github.io/podcast-feed"
  124. ```
  125. ### 4. Subscribe in a podcast app
  126. Tell the user their feed URL and give them the steps for their preferred app:
  127. | App | How to subscribe |
  128. | ----------------------- | ------------------------------------------------------ |
  129. | Apple Podcasts (Mac) | Menu bar: File > Add a Show by URL |
  130. | Apple Podcasts (iPhone) | Library > Edit (top right) > Add a Show by URL |
  131. | Overcast | "+" (top right) > Add URL |
  132. | Pocket Casts | Discover tab > paste URL in search bar > Subscribe |
  133. | Castro | Search tab > paste URL in search bar > Add Podcast |
  134. | Snipd | Home > Podcasts > three-dot menu (top right) > Add RSS |
  135. | Spotify | See Spotify instructions below |
  136. Feed URL: `https://USERNAME.github.io/podcast-feed/feed.xml`
  137. **Spotify setup (one-time, takes 24-48 hours for approval):**
  138. IMPORTANT: Before proceeding, warn the user: "Heads up - submitting to Spotify makes your podcast **public**. Anyone on Spotify can find and listen to it. The other apps above are private - only people you share the RSS URL with can find your show. Want to proceed with Spotify?"
  139. If they want to proceed:
  140. 1. Make sure `owner_email` is set in config.yaml. If not, ask for their email and add it.
  141. 2. Go to [podcasters.spotify.com](https://podcasters.spotify.com) and sign in
  142. 3. Click "Add existing podcast"
  143. 4. Paste the feed URL
  144. 5. Spotify sends a verification email - click to verify
  145. 6. The show appears on Spotify within 24-48 hours
  146. ### 5. Publish episodes
  147. After the RSS feed is set up, future episodes can be published with:
  148. ```bash
  149. DATA_DIR/venv/bin/python SKILL_DIR/scripts/publish.py --mp3 <path_to_mp3> --title "<title>" --description "<description>"
  150. ```
  151. ---
  152. ## Troubleshooting
  153. - **"API key not found"** - Check DATA_DIR/.env has a valid FISH_API_KEY
  154. - **"ffmpeg not installed"** - Run: `brew install ffmpeg` (macOS) or `sudo apt install ffmpeg` (Linux)
  155. - **"gh not authenticated"** - Run: `gh auth login`
  156. - **TTS quota exceeded** - Fish Audio free tier has monthly limits. Wait for reset or upgrade your plan.
README.md · README · 135 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Personalized Podcast
  2. **NotebookLM-style AI podcasts, except you control everything.**
  3. The script. The prompt. The hosts' roles. Their voices. The content they discuss. All of it.
  4. A coding agent skill that turns any content into a two-host podcast episode. Paste in text, point it at files, drop a URL. Two AI hosts read your content and have a natural conversation about it. You get an MP3 that plays immediately. Set up an RSS feed and listen in the apps you already use: Apple Podcasts, Spotify, Overcast, Snipd, Pocket Casts. No new app to download.
  5. ## Why this exists
  6. **Turn anything into a podcast you can listen to on the go.** Newsletters, long reads, tweets, research papers, meeting notes. Instead of reading on a screen, you listen to two people break it down while you walk, commute, or cook. Set up the RSS feed once and new episodes show up right where you already listen to podcasts.
  7. **Know yourself from the outside.** This is the unexpected use case. Feed it personal content: your resume, meeting transcripts, journal entries, even your browser history. Then ask the hosts to comment on their impressions of you. What patterns do they see in how you think, communicate, make decisions? It is genuinely illuminating to hear two voices discuss you as if you're not in the room.
  8. ## Quick start
  9. ### 1. Install
  10. ```bash
  11. gh repo clone zarazhangrui/personalized-podcast-skill ~/.claude/skills/personalized-podcast
  12. ```
  13. ### 2. Go
  14. ```
  15. /podcast <paste content, point to files, or describe a topic>
  16. ```
  17. That's it. On first run, Claude sets up the Python environment, installs dependencies, and asks you for a free [Fish Audio](https://fish.audio) API key. Default voices are pre-configured. Your first episode generates immediately.
  18. ## What you can do with it
  19. **Consume content as audio**
  20. ```
  21. /podcast read ~/Downloads/newsletter.txt
  22. /podcast https://some-article-url.com
  23. /podcast Here's a thread about AI agents I want to hear discussed...
  24. ```
  25. **Self-reflection**
  26. ```
  27. /podcast read ~/Documents/my-resume.pdf and have the hosts analyze my career trajectory
  28. /podcast read ~/transcripts/meeting.txt and have the hosts eavesdrop and share their impressions of me
  29. ```
  30. **Custom formats**
  31. ```
  32. /podcast read ~/notes.md, make it a debate between an optimist and a skeptic
  33. /podcast read these 3 files, hosts should focus on what's surprising or counterintuitive
  34. ```
  35. You can change the prompt, the hosts' personalities, the episode length, the tone. It is all in your config file.
  36. ## How it works
  37. ```
  38. /podcast <your content>
  39. |
  40. v
  41. Claude reads the content and writes a two-host conversation script
  42. |
  43. v
  44. Fish Audio generates speech for each line (different voice per host)
  45. |
  46. v
  47. Audio gets stitched together with natural pacing
  48. |
  49. v
  50. MP3 opens and plays on your computer
  51. ```
  52. The default show has two hosts:
  53. - **Alex** (Speaker A): The curious one. Introduces topics, asks questions, gets excited.
  54. - **Sam** (Speaker B): The analytical one. Adds depth, offers opinions, drops the witty takes.
  55. They sound like two friends talking over coffee. Not news anchors. Not a lecture.
  56. ## Make it yours
  57. **Customize the script prompt.** This is the big one. [`PROMPT.md`](https://github.com/zarazhangrui/personalized-podcast-skill/blob/main/PROMPT.md) controls how the hosts behave, the show structure, and the writing style. Edit it to create your own show format. Some ideas:
  58. - **Debate:** Two hosts take opposing sides. One is bullish, the other is skeptical. They challenge each other.
  59. - **Eavesdrop:** Two hosts discuss a person (from transcripts, writing, or personal content) as if that person isn't in the room. They share observations about personality and communication patterns.
  60. - **Interview:** One host interviews the other as an expert on the topic.
  61. - **Solo narrator:** One voice walks through the content in a thoughtful monologue.
  62. - **News roundup:** Hosts go through a list of items (tweets, headlines) one by one. Each is read aloud, then discussed.
  63. **Pick your own voices.** Browse [fish.audio/discovery](https://fish.audio/discovery/). Find voices you like. Copy their reference IDs into your config. You can make your hosts sound however you want.
  64. **Change the show's personality.** Edit `show_name` and `tone` in `~/.personalized-podcast/config.yaml`. Make it serious, funny, academic, casual, confrontational. Up to you.
  65. **Set up an RSS feed.** Want episodes delivered to your podcast app automatically? Just ask Claude: "Set up an RSS feed for my podcast." It creates a GitHub Pages feed you can subscribe to in Apple Podcasts, Overcast, Pocket Casts, Snipd, Spotify, or any podcast app that supports RSS.
  66. ## Requirements
  67. - A coding agent that supports skills (e.g. Claude Code, Gemini CLI, Copilot CLI)
  68. - Python 3.10+
  69. - ffmpeg (`brew install ffmpeg` on macOS)
  70. - [Fish Audio](https://fish.audio) account (free tier available)
  71. ## About
  72. Built by [Zara Zhang](https://x.com/zarazhangrui). Your AI coding agent already understands context, writes well, and follows instructions. Why not have it write you a podcast script, generate the audio, and deliver it to your ears?
  73. The entire pipeline runs locally through your coding agent. No separate backend. No hosted service. No subscription. Just a skill that turns your coding agent into a podcast producer.
  74. ## Under the hood
  75. ```
  76. ~/.claude/skills/personalized-podcast/ # The skill (this repo)
  77. SKILL.md # Instructions for the coding agent
  78. scripts/
  79. speak.py # Fish Audio TTS + audio stitching
  80. publish.py # Push episodes to GitHub Pages (optional)
  81. bootstrap.py # One-time repo setup (optional)
  82. utils.py # Config, logging, .env loading
  83. templates/
  84. feed_template.xml # RSS feed template (optional)
  85. config/
  86. config.example.yaml # Default config with pre-picked voices
  87. ~/.personalized-podcast/ # Your data (created automatically)
  88. config.yaml # Your config
  89. .env # Your Fish Audio API key
  90. scripts_output/ # Generated scripts (JSON)
  91. episodes/ # Generated MP3 files
  92. ```
  93. **Script generation:** Your coding agent writes the script directly. No separate LLM API call needed.
  94. **Text-to-speech:** [Fish Audio](https://fish.audio) with 2M+ voices and a free tier.
  95. **Audio processing:** pydub + ffmpeg for stitching segments with natural pauses and fade effects.
  96. **Feed hosting (optional):** GitHub Pages, auto-deploys on every push.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.