The $0 Personalized News Roundup That Lands in Your Podcast App Every Week - Ad HocAd Hoc
Published in AI
John A. Federico
Aug 3, 2026
For anyone who knows me, you know that audio is a big part of my life - podcasts, audiobooks, music - All The Aural Things.<br>I typically start my morning by reading newsletters but sometimes that ritual gets thrown off due to scheduling issues. Listening to tech news helps fill that gap - but I usually have to jump between podcasts to find what I want.<br>This past weekend, I was using Perplexity for some Deep Research and stumbled upon a Podcast Skill designed to be used by Perplexity’s Computer. You provide a topic to the skill and it will create a two-person, discussion-style podcast on that topic. It’s a beefy 14-step pipeline that does everything from researching the topic to ensuring the audio uses the proper LUFS for spoken audio to creating the cover art.<br>Instead of Perplexity’s original use case - give it a topic and it returns a podcast on the subject - I created a Hermes workflow that produces a weekly tech news roundup podcast using my local, owned systems with the following instructions:<br>Every day, search for the most significant technology developments, focusing on: 1) Edge Computing; 2) Edge AI, 3) AI and ML breakthroughs; 4) Emerging tech trends and their potential impact; 5) Major tech company strategic moves.<br>When worthy news is found, save what you find to a reference file.<br>Every Monday morning at 4 AM US Central Time, review that reference file and create a podcast based on the previous week’s findings and post it to the RSS feed. Send a notification via Telegram when it’s ready. No need to send the audio to Telegram.<br>In the episode, note the source or sources of the news for each newfound item. (Full URL’s are not required in audio, only the name of the most notable publication.) Note how many publications covered it as a signal of its significance. (“This was covered in at least n publications.”)<br>In the episode description, include any relevant links to each of the topics.<br>Before creating this workflow, suggest any improvements to my request.
The Final Product<br>Does it sound as good as a podcast made by humans? Hell, no. Does it sound as good as Google’s NotebookLM podcasts? Also, no.<br>Sure, I could create higher quality audio by using a service like Eleven Labs or Fish Audio, each of which have much better voices, but there are no incremental costs to my workflow, and it’s good enough to keep me informed on a Monday morning while I walk my dogs.<br>But first, I needed to adapt the original skill for my owned infrastructure.<br>TL;DR: If you just want my adapted skill for your own use, you can find it here.<br>Listen to the test episode .<br>Adapting Perplexity’s Podcast Skill for Hermes<br>The original skill was an impressive pipeline that researched topics, wrote multi-host scripts, synthesized speech, sourced music, assembled audio, and ran multiple QA passes including WavLM artifact detection and multimodal listenability review (where the LLM actually “listens” to the audio output). The problem: almost none of its prescribed tools existed in my environment.<br>The Gap<br>The original skill assumed a platform with a text_to_speech (TTS) tool that accepted per-line voice parameters, a transcribe_audio tool, an audio-capable multimodal model for listenability QA, browser-based authenticated downloads for music sourcing, and a full PyTorch stack for neural audio quality checks. I had none of those.<br>What I did have: a Kokoro TTS server on a Mac Studio, a Whisper model on the same machine, ffmpeg on the Debian LXC where I run Hermes, Tailscale connecting everything, and a Telegram bridge for notifications. The adaptation was an exercise in mapping capabilities - not feature-matching, but instead asking “what does this step produce, and what’s the simplest way to get there given what I already have?“<br>Multi-Voice TTS Without the Tool<br>The biggest architectural change was TTS. Hermes ships with a text_to_speech function that reads one voice from it’s configuration - great for Telegram voice replies, but useless for a two-host podcast where af_heart and am_adam (AI voices that ship with Kokoro) alternate every line.<br>The fix was to stop using the built-in Hermes tool entirely for this task. Kokoro exposes an OpenAI-compatible API, so each dialogue line became a direct curl call with a voice parameter:<br>curl -s http://TailscaleIP:8000/v1/audio/speech \<br>-X POST -H "Content-Type: application/json" \<br>-d '{"model":"mlx-community/Kokoro-82M-bf16","input":"Welcome to the show.","voice":"af_heart"}' \<br>-o line_001.mp3<br>(Yes, Hermes backed by Deepseek v4 Pro helped me figure this out.)<br>This bypasses Hermes’ single-voice constraint entirely. The podcast uses af_heart and am_adam for its hosts, while my Telegram voice (am_eric) stays untouched. Clean separation and zero config changes between modes.<br>Transcription: Fixing Whisper on oMLX<br>The Mac Studio already served whisper-large-v3-turbo through...