- Home
- Skills
- Workflow Automation
- Podcast This Tech Stuff
Podcast This Tech Stuff
Converts technical docs and diagrams into tailored, two-host audio podcasts for on-the-go learning.
Free
Works with the AI Agents you already use
Podcast This Tech Stuff
Example session with this skill installed
I need to understand this system-architecture.pdf before my meeting. Podcast this for a semi-technical listener, about 12 minutes long.
- Read your context and instructions
- Compiled the podcast this tech
- Generated the document
I have processed the architecture document and initialized the podcast generation sequence.
I've configured the brief for a
Semi-technical listener with a
~12 min target duration. The generation is now running in a background Chrome instance via NotebookLM.
Podcast Configuration Brief
| Field | Value |
|---|---|
| Source File | system-architecture.pdf |
| Listener Level | Semi-technical (software background, new to this domain) |
| Tone | Concise, fast-paced, curious host + expert |
| Primary Engine | NotebookLM (Cloud) |
| Status | Generating audio... |
Progress Update: The notebook has been created and the PDF has been ingested. I am now polling the generation status. This typically takes 8 minutes for a document of this size. I will notify you as soon as the file is ready in your episodes folder.
Next steps
- Wait for the background process
scripts/poll_notebooklm.shto complete. - Listen to the file at
~/doc2podcast/episodes/system-architecture.m4a. - If you have the original LucidChart link, I can re-run this to weave the diagram into the narrative for more detail.
system-architecture.pdf
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Technical documentation is often too dense to consume during a commute or while multitasking. This skill converts PDFs, diagrams, and PRDs into concise, two-host audio podcasts tailored to a specific audience's technical depth.
What it does
- Source ingestion handles local PDFs, PNG diagrams, markdown files, and Google Doc URLs to build a comprehensive context.
- Audience calibration adjusts the technical complexity and definition frequency based on whether the listener is a non-technical generalist or a domain expert.
- NotebookLM integration drives a browser-based workflow to generate high-quality AI voices and conversational narratives.
- Automated brief generation creates structured instructions for the audio engine to ensure a fast pace without filler or repetitive recaps.
- Offline fallback provides a local script-writing and text-to-speech pipeline using macOS voices when internet access is unavailable.
How it works
- Upload sources by providing file paths, URLs, or pasting raw text for the agent to process.
- Calibrate the episode by answering three quick questions regarding listener expertise, desired duration, and focus angles.
- Generate the audio via an automated Chrome harness that manages source uploads and customization settings in NotebookLM.
- Retrieve and organize the final
.m4afile into a local directory, providing the file path and duration.
Frameworks & tools
The skill utilizes browser-harness for Chromium automation, NotebookLM for high-fidelity audio synthesis, and a Python-based fallback pipeline for local say execution. It includes shell scripts for status polling and afinfo for metadata extraction.
Why this beats prompting it yourself
Manually configuring NotebookLM requires constant tab-switching, manual source uploading, and trial-and-error with custom instructions to avoid fluff. This skill automates the entire browser lifecycle and ensures consistent term definitions and pacing through a pre-validated briefing template.
Use cases
- Convert complex RFCs or system design docs into a 12-minute commute-friendly brief.
- Turn architectural diagrams and flowcharts into audio explanations for stakeholders.
- Onboard new developers by transforming project READMEs into introductory podcasts.
- Summarize long research papers or whitepapers into digestible 20-minute audio sessions.
Known limitations
Requires an active Google account for NotebookLM access. Browser automation may pause if a login wall is encountered. Final audio generation can take between 5 and 20 minutes.
Requires Google account login via browser. Generation takes 5 to 20 minutes. Local fallback uses standard macOS voices with lower quality than AI synthesis.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account
Requires