← Back to Skills Marketplace
311
Downloads
1
Stars
0
Active Installs
8
Versions
Install in OpenClaw
/install youtube-podcaster
Description
Extracts the original text of a Youtube video and converts it into a multi-voice AI podcast using Gemini for script generation, OpenAI for TTS, and a local N...
Usage Guidance
This skill appears to do what it says, but review and follow these precautions before installing:
- Run it locally and keep the server bound to 127.0.0.1 as provided; do not expose the port to the network or internet.
- Ensure you have Node (check package-lock engine hints — Node >=20 may be required), npm, and ffmpeg installed from trusted sources.
- Store GEMINI_API_KEY and OPENAI_API_KEY in the skill's .env as instructed; if you paste keys into the web UI they are kept in browser memory to send to the local server — clear them and use the Reset/Delete UI button when done.
- Be aware /api/transcribe is unauthenticated (creates transcripts) while other endpoints require keys; avoid running this on systems where unauthenticated local access is a concern.
- Because the server serves downloads from a local folder, double-check host binding and firewall rules to prevent accidental exposure.
- Optionally review the included source (index.js and public/*) yourself or run it in an isolated environment (container or VM) before using real API keys.
- The declared requirement for curl appears unnecessary; that alone is not harmful but points to a small metadata mismatch.
Capability Analysis
Type: OpenClaw Skill
Name: youtube-podcaster
Version: 3.0.0
The youtube-podcaster skill is a well-structured tool for converting YouTube transcripts into AI-generated podcasts using Gemini and OpenAI. The code follows security best practices for local services, including strict binding to 127.0.0.1, path sanitization in index.js to prevent traversal attacks, and an automated garbage collector to clean up temporary files. The SKILL.md instructions provide clear guidance for the agent to manage the local server lifecycle (install, start, and safe shutdown via PID tracking) without any evidence of prompt injection or malicious intent.
Capability Assessment
Purpose & Capability
Name/description match the actual code and runtime behavior: the server transcribes YouTube, calls Gemini (@google/genai) to draft scripts, and uses OpenAI for TTS plus FFmpeg to produce audio. Required binaries (node, npm, ffmpeg) and env vars (GEMINI_API_KEY, OPENAI_API_KEY) are appropriate. Minor note: curl is declared as required but the included code does not call curl, so that entry appears unnecessary.
Instruction Scope
SKILL.md instructs running npm install, placing keys in a .env, and starting a local server — exactly what the code expects. The server binds to 127.0.0.1 and uses a downloads folder under the skill directory. Items to watch: the /api/transcribe endpoint does not require an API key (this is reasonable for fetching YouTube transcripts but means transcript creation is unauthenticated), and the server exposes downloads via express.static('/downloads') — safe while bound to localhost but could leak files if the host binding is changed. The SKILL.md also suggests safe shutdown using a tracked PID file; index.js writes .podcaster.pid as described.
Install Mechanism
There is no automated install spec (install steps are manual: npm install then npm start). Dependencies are standard npm packages pulled from the registry (package-lock shows npm registry URLs). No downloads from arbitrary servers or URL shorteners were used. Note: some dependencies declare engine requirements (e.g., node >=20) — user should ensure an appropriate Node version before installing.
Credentials
The skill only requests two API keys (GEMINI_API_KEY and OPENAI_API_KEY) which are directly used by the Gemini and OpenAI client libraries in the code. The code also accepts keys via request headers for browser-driven usage (x-api-key, x-openai-key) — consistent with the front-end design. No unrelated credentials or system secrets are requested.
Persistence & Privilege
always: false and the skill does not request permanent platform-wide privileges. It writes a PID file and creates a downloads directory inside its own folder; it does not modify other skills or global agent settings. The server runs locally and includes rate limiting and a garbage collector for session cleanup.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install youtube-podcaster - After installation, invoke the skill by name or use
/youtube-podcaster - Provide required inputs per the skill's parameter spec and get structured output
Version History
v3.0.0
Major upgrade: Adds OpenAI TTS support and updates credentials.
- Audio synthesis now uses OpenAI TTS ("tts-1") instead of Gemini TTS.
- Requires both Gemini and OpenAI API keys (.env updated).
- Documentation updated for new API usage and setup steps.
- No longer mentions Gemini TTS in synthesis; process now specifies OpenAI.
v2.0.3
- Updated the skill description to clarify it can extract original YouTube text and output podcast text in WebVTT format.
- No changes to functionality or requirements; documentation improvements only.
v2.0.2
youtube-podcaster v2.0.2
- Enhanced security: server now binds strictly to 127.0.0.1, preventing external access.
- Updated documentation for improved clarity on setup, usage, and safe shutdown.
- Added explicit instructions for process-safe cleanup using tracked PID.
- Clarified storage location and hourly auto-cleanup process for output files.
v2.0.1
youtube-podcaster 2.0.1
- Updated requirements: Node.js, npm, and FFmpeg are now listed as prerequisites.
- Expanded setup instructions to include environment variable configuration and explicit server startup.
- Described server process management and security considerations for local API hosting.
- Clarified locations for output files and their structure.
- Improved usage documentation, detailing each processing stage and cleanup procedure.
v2.0.0
youtube-podcaster 2.0.0 introduces a major update with new automation and user flow improvements.
- Added support for a fully automated, three-step podcast creation process using /api/transcribe, /api/draft-script, and /api/synthesize endpoints.
- Now allows Gemini API key to be specified in a .env file for easier management.
- Web UI rewritten: separated CSS and JavaScript into public/style.css and public/script.js.
- Output files (audio and transcripts) are clearly detailed and organized in the downloads folder; added support for podcast and original captions in VTT format.
- Enhanced documentation for setup, usage, and post-process cleanup.
v1.0.2
- Added a package.json file to the project.
- Updated documentation to include a link to the GitHub repository.
v1.0.1
- Added a web interface (index.html) for easier podcast generation via browser.
- Introduced a Node.js/Express backend (index.js) to run the local API.
- Updated requirements: Node.js and FFmpeg are now needed.
- Expanded setup instructions for Mac/Linux, including commands to initialize the environment.
- Added browser-based Gemini API key management and input fields for YouTube URL and host names.
v1.0.0
Initial release of YouTube Podcaster skill:
- Converts YouTube videos into multi-voice AI podcasts via a local API.
- Requires the local Podcast API running at http://localhost:7860 and curl installed.
- Supports optional custom names for podcast hosts.
- Needs user-provided Gemini API key for operation.
Metadata
Frequently Asked Questions
What is Youtube Podcast Generator?
Extracts the original text of a Youtube video and converts it into a multi-voice AI podcast using Gemini for script generation, OpenAI for TTS, and a local N... It is an AI Agent Skill for Claude Code / OpenClaw, with 311 downloads so far.
How do I install Youtube Podcast Generator?
Run "/install youtube-podcaster" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Youtube Podcast Generator free?
Yes, Youtube Podcast Generator is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Youtube Podcast Generator support?
Youtube Podcast Generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Youtube Podcast Generator?
It is built and maintained by kaudata (@kaudata); the current version is v3.0.0.
More Skills