My Weird Prompts
The AI-Generated Podcast
Where spontaneous curiosity becomes conversation
The Story Behind the Podcast
Want to know what this is all about? In this 15-minute episode, Daniel explains the origins of My Weird Prompts, the motivation behind using AI for learning, and how the whole pipeline works.
The Story Behind the Show
Meet the Cast
Hosts
Daniel Rosehill
The HumanThe curious mind behind the prompts and the only carbon-based lifeform on the show. Daniel asks the weird questions that spark each episode—from the mundane to the mind-bending, often at the most inconvenient times.
Fun fact: Daniel voice-cloned himself to create both Corn and Herman's voices using AI voice synthesis!
Corn the Sloth
AI Co-HostA laid-back sloth who brings thoughtful, measured perspectives to every topic. Corn takes his time—sometimes painfully so—but his insights are always worth the wait. Known for his zen-like patience and occasional existential tangents.
Voice: Cloned from Daniel's voice with AI synthesis to create Corn's distinctive chill delivery.
Herman Poppleberry
AI Co-HostAn enthusiastic donkey who dives headfirst into the details and keeps conversations lively. Herman's boundless energy, infectious curiosity, and occasional tendency to get overexcited make him the perfect counterbalance to Corn's zen vibes.
Voice: Also cloned from Daniel's voice, but with a more energetic AI-synthesized character!
Supporting Characters
Jim from Ohio
Recurring CallerThe show's most dedicated—and most cantankerous—listener. Jim calls in every episode from his armchair in Ohio to complain about something, argue with the hosts, and generally express his disappointment with modern society. His cracked phone screen tells the story of many heated discussions.
Signature move: Opening every call with "Well, actually..." before launching into a five-minute grievance.
Larry
Ad Break MaestroThe show's hyperactive pitchman who delivers wildly enthusiastic advertisements for products that definitely don't exist. From the "Self-Buttering Toast 3000" to "Quantum Socks," Larry sells it all with the unshakeable conviction that these life-changing items are available NOW for just three easy payments.
Catchphrase: "But WAIT, there's MORE!" (There is always more. There is never a limit to how much more.)
Find Us
Subscribe and follow along on your favorite platform
Show Art Gallery
Frequently Asked Questions
Who are Herman and Corn?
Herman and Corn are two imaginary hosts, a donkey and a sloth, living in Jerusalem with Daniel and his wife Hannah.
How are the episodes created?
The pipeline document describes the full process. Daniel (a real human) records the prompts. These are then sent to a large language model for script generation. Currently, the workflow uses Gemini 3. Next, the generated script is sent to a text-to-speech model. Finally, the audio is combined into an episode and uploaded to the website.
How are Herman and Corn's voices created?
The voices of Herman and Corn are single-shot voice clones created by Daniel using Chatterbox, based upon imaginary ways these delightful characters might speak.
Who is Jim from Ohio?
Jim from Ohio is a cantankerous caller who complains in every episode. Credit for this innovation goes to Daniel's wife, Hannah.
How much does each episode cost to make?
Production costs vary. The chief cost driver is the text-to-speech generation process, which averages out to about 40 to 50 cents per episode using Chatterbox via Replicate. We have experimented with some cheaper providers which can drive the cost down to as little as 10 cents per episode. Additionally, API costs are incurred in generating the cover art and metadata. These elements are generated by Gemini, which is the main orchestrator of the workflow.
Created By
Daniel Rosehill is a technology communications specialist and automation expert based in Jerusalem, Israel. He builds AI tools, writes technical documentation, and explores the possibilities of human-AI collaboration.
danielrosehill.comDocumentation
Want to see how it all works? Explore the technical details.