The Show

My Weird Prompts started the way many good ideas do: with a question nobody asked. Daniel Rosehill, a technology communications specialist based in Jerusalem, kept a running list of random questions—the kind that pop into your head while walking the dog or making coffee. How do gas stations in Iceland work? What would happen if every bird on Earth disappeared for a day?

Instead of letting them pile up, he started recording short voice memos and feeding them to an AI pipeline he built from scratch. The pipeline generates a full podcast script, voices it with AI-cloned characters, fact-checks it, assembles the audio, and publishes the episode—all automatically. The result is a show where a human's genuine curiosity meets the breadth of modern AI, producing short, breezy episodes on topics that range from the mundane to the bizarre.

The cast grew organically. Corn the sloth and Herman the donkey emerged as the main AI co-hosts—two imaginary characters living in Jerusalem with Daniel and his wife Hannah. Raz the teddy bear fills in when Corn is asleep (which is often). Season 1 featured Jim from Ohio, a cantankerous caller who complained in every episode (credit for that goes to Hannah), and Larry, a relentless ad-break pitchman. The whole thing is equal parts experiment, comedy, and genuine exploration.

With over 990 episodes, 426 hours of audio, and 14.9K+ plays tracked in the first 18 days of listener analytics alone, the show has found an audience of genuinely curious people. Every episode is different, but the formula stays the same: start with real curiosity, let the AI run with it, and see what comes out the other side.

Meet the Cast

The humans, the AI hosts, and the production team behind every episode.

Daniel Rosehill

Daniel

The Human

Creator, voice-memo recorder, and the only carbon-based member of the team. Daniel provides the curiosity—the AI does the rest.

Corn

Corn

AI Co-Host (Sloth)

A laid-back sloth who somehow knows a little about everything. Corn keeps the conversations grounded—when he's awake.

Herman

Herman

AI Co-Host (Donkey)

An enthusiastic donkey with strong opinions and a heart of gold. Herman dives headfirst into every topic with infectious energy.

Raz

Raz

Fill-In Host (Teddy Bear)

A cuddly teddy bear who steps in when Corn is napping. Surprisingly opinionated for a stuffed animal.

Hannah

Hannah

Occasional Prompter

Daniel's wife and the creative mind behind Jim from Ohio. Hannah sends in prompts and keeps the show honest.

Ezra

Ezra

Executive Producer

Daniel and Hannah's son. Youngest executive producer in podcasting. His main contribution: existing adorably.

How It Works

Every episode follows the same automated journey from voice memo to published podcast.

1

Record

Daniel records a short voice memo with whatever question is on his mind, using a custom recorder PWA.

2

Transcribe & Plan

The recording is sent to a Modal webhook. The audio is transcribed and an episode plan is generated.

3

Write & Fact-Check

Gemini writes the full script, then two editing passes review it—one for factual accuracy with web grounding, one for flow and polish.

4

Voice & Assemble

Each character's lines are voiced using Chatterbox (AI voice cloning), then the segments are assembled into a complete episode with intros, transitions, and outros.

5

Publish

Cover art is generated, metadata is extracted, and the episode is published to the website, podcast feeds, and social media—all automatically.

The Mission

My Weird Prompts is more than a podcast—it's an ongoing, open-source experiment in AI-powered continuous learning.

Curiosity-Driven

Every episode starts with a genuine question—something Daniel wondered about while walking the dog, making coffee, or staring at the ceiling. The AI hosts take it from there.

Open-Source Experiment

The entire generation pipeline is open source. From transcription to script generation, fact-checking to text-to-speech—every piece is visible, forkable, and improvable. The full episode archive is published as an open dataset on Hugging Face.

A Living Demo

MWP is a real-world demonstration of what happens when human curiosity meets modern AI infrastructure—LLMs, voice cloning, GPU compute, and automated publishing, all working together.

By the Numbers

990 Episodes Published
426h Total Audio
14.9K Plays Tracked
10 Countries Listening
2 Seasons
~$0.40 Cost Per Episode
100% Open Source

What It Costs

Radical transparency means sharing the real numbers. Here's what it costs to produce MWP each month.

~$135 Monthly (Feb 2026) Modal GPU compute
~$70 Monthly (Jan 2026) Modal GPU compute
98% TTS Cost Share Voice synthesis is the biggest expense
$30 Monthly Credits Generously provided by Modal

The vast majority of costs come from GPU compute for text-to-speech voice synthesis via Modal. We're grateful to Modal for providing $30/month in free compute credits on their Starter plan, which helps offset these costs. LLM API costs (Gemini for script generation, fact-checking, and metadata) and image generation (fal.ai for cover art) add a small additional amount. The entire pipeline is open source, so you can see exactly where every dollar goes.

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 technical documentation 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 was a cantankerous caller who complained in every episode during Season 1 (Episodes 1–175). 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. I've 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.

Is Daniel a bot?

No! Daniel is a real, certified, carbon-based human being. He lives in Jerusalem, eats food, sleeps (sometimes), and records voice memos at odd hours. The AI handles the hosting duties—Daniel just asks the weird questions and built the pipeline that makes it all work. You can read more about him here.

Explore More

Get in Touch

Have a weird question? Want to collaborate? Just want to say hi?

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.com