Posted in AI Experiments

Read It To Me Differently

One Story. Three Voices. What Delivery Does To Meaning.

I’ve been thinking lately about how much of a story lives in the telling rather than the text. The same words, read differently, can make you laugh, unsettle you, or send you to sleep. Tone of voice, pace, register, these aren’t decorative. They’re structural. They change what a story actually is. So I ran an experiment.

I took one of my favourite pieces from this blog, ‘The Queue At 10:47,’ the story of a waiting room that never seems to empty, and asked Claude to rewrite it three times. Same story. Same characters. Same fish tank, same purple cardigan, same tuna sandwich. But each version reshaped for a completely different delivery: a bedtime story, a breaking news report, and a nature documentary. Then I took each version into ElevenLabs and chose a voice to match.

What came out surprised me. Not because the story changed, it didn’t, not really, but because each version revealed something different about the material that was always there, waiting to be unlocked by the right tone of voice.

Have a listen. Then I’ll share what Claude and I both noticed.

Continue reading “Read It To Me Differently”
Posted in AI and Creativity

What Happens When Light and Shadows Fight?

Today I have a story for you to read, listen to, or both. The story was written by Claude and the narration was created using ElevenLabs. Enjoy.

Continue reading “What Happens When Light and Shadows Fight?”
Posted in AI and Creativity

A Story From a Reader – ‘Nothing Ever Grew There Again’

Many thanks to Valerie for leaving this story in the comments. It was created with the help of Gemini. I thought I would give voice to it with the help of ElevenLabs. The voice is one from their library and the description is – ‘Michael – Deep, Resonant, Confident – a male British voice for a storyteller with a rough undertone.’ I hope Valerie approves.

I’ve included the audio and Valerie’s original text. I also put the story into ChatGPT’s new image generator for the picture above.

I hope you enjoy.

Nothing Ever Grew There Again – Audio

Nothing ever Grew There Again – Text

The sun was a blister in the sky, cracking the clay earth into a mosaic of despair. Elias knelt by the ruined plot, his fingers scraping at the dust. He remembered the seedlings, bright green promises against the brown, planted with a hope that now felt like a cruel jest. He’d watered, he’d tended, he’d even spoken softly to the soil, but the blight, unseen and absolute, had taken root first. His wife had wept when the last shoot withered, a sound Elias carried like a stone in his chest. Now, only the brittle, pale husks of dead weeds remained, monuments to a vanished dream of bounty. He pushed himself up, wiping the grit from his calloused palms. The air tasted of defeat, dry and metallic. Nothing ever grew there again.



Posted in AI Experiments

Writing, Emotion Tags, and a Voice That Sounds Like Me

This post is part of an ongoing habit of trying small, contained experiments rather than grand declarations about what AI can or cannot do. In this case, the experiment was simple: could a short piece of writing be performed by an AI voice in a way that felt deliberate rather than mechanical.

I prompted ChatGPT to write a brief dystopian monologue and asked it to include emotional cues directly in the script. I then copied and pasted the text into ElevenLabs and generated the audio using a cloned version of my own voice. No editing, no post-production, no technical tinkering. Just text, instructions, and a voice.

What interested me wasn’t realism or polish, but interpretation.

The Audio – ‘Where Silence Is Suspicious’

Continue reading “Writing, Emotion Tags, and a Voice That Sounds Like Me”
Posted in AI and Creativity

When Six Images Became a Mini-Film: Testing Midjourney + ElevenLabs 

How two AI tools turned still pictures into moving art, and why this is just the beginning

This week I tried a small experiment that turned into something surprisingly delightful. I took six still images created in Midjourney and asked it to turn each one into a five-second video. Nothing fancy, no complicated prompting, just a simple “animate this” test to see what it could do.

Continue reading “When Six Images Became a Mini-Film: Testing Midjourney + ElevenLabs “