Skip to content

Category: Spoken Word

A Real Poet Writing a Poem with AI

This is a somewhat real-time deep dive into one of the ways I use generative AI (in this case ChatGPT4) to develop a poem, along with my views on doing so.

Apologies in advance for the clickbait-y title.

After searching YouTube for videos on the topic, I wound up being more than a little disappointed. All I found were either rants about “AI will ruin poetry” or demos of “look at how cool this is with only a prompt or two”.

I can do better than that, even with an admittedly less than perfect presentation.????

Be warned, this is a long one, folks, so buckle up.

Comments closed

Poem: The Garden of the Patrons

Took me a while, but I’ve created a little video of my poem, “The Garden of the Patrons,” which was published in Pandemic Atlanta 2020 magazine, an assortment of artwork, literature, poetry, and photography documenting the experiences of Atlanta-based artists during the COVID-19 pandemic.

Hope you enjoy.

Comments closed

Revolution (with apologies to Gil Scott Heron)

This isn’t part of my soon-to-be-published poetry collection. In fact, it’s not even a new poem. I wrote this almost twenty years ago, and up until now, I didn’t think it was quite ready.

But it seems, unfortunately, befitting the times, so I’ve updated some of it to account for technology.

Here is the text:

Revolution (with apologies to Gil Scott Heron)

On this day of June 19, Two-thousand-you-name it,
the long-awaited
comes to you live via the inter-tubes,
and yes, carrier pigeon,
from Atlanta, GA!

There is a parade on the information superhighway
as the Panther struts out onto the cathode catwalk.
Its image is sliding into social media,
and fluttering
into packets

“We here at See-and-End
promise freeze this cybernetic Simba
with liquid crystal eyes,
slice it into wafers,
and serve it up for communion.

So get your wafers at pick-a-season.revolution.anarchy.rebellion.S-and-E.something.something-else.bullshit.”


Under the light of the moon, the Panther stalks its prey.
The Ghettobird bub-bub-bubs over the water, night-eyes green.
The Panther’s bionic ears and night-vision scope-vision pick up movement in the treetops.
It creeps out of the forest to cool off for a swim in a pond.
They see each other there,
and they are shadows in a world of midnight blue
and omnipresent coordinates:
the silent Panther,
the Ghettobird bub-bub-bubbing over the water.

They have nothing to say.

They bow their heads and turn away.


Under the light of the sun,
the commentary locusts spill out of their concrete nests,
subway tunnels,
and fiberglass cocoons.

The Panther roars as it stalks its prey.

The locusts bite into its speeches.
Death is not quick;

the commentaries gnaw out its throat.

The information jackals lick their lips.
They split him
and split him
and split him
and split two
and split one,
scattering his pieces
on the concrete
in the summer sun.

They chew the panther with spiced commercials
for sport fluids
and the world’s most powerful malt liquor:

Live, via wave motion,
it is the REVOLUTION
you’ve all been waiting for!

The Ghettobird tilts its cockpit and flies away.

“I’m sorry. I have nothing to say.”

Everything is entertainment here,
and you are required by law to purchase tickets…

“I’m sorry. I am sorry.”

The opinion engineers guarantee a
racy, rowdy, rad,
sassy, sad,
slick, sappy,
fly, and
box office smash!

“I am sorry. I am so sorry.”

The Grammys are being delivered by the busload.
The awards ceremony will take place in D.C.,
and everyone will pay.
And it will only take 15 minutes…yes, just 15 minutes
and it will all be over.

The DVD sales will more than make up for the damages and special effects.

S & E recommends everyone to sit back,
and shut their mouths…

“They’ll be right back after these messages,
Don’t touch that dial.

They will shoot you.”

Comments closed

Taking a Coursera Class: Survey in Music Technology

I’ve been taking this course now for about three weeks, and it’s already filled in a few gaps in my knowledge of audio processing. For instance, I was always fuzzy on the physics and psychoacoustics of sound – now I’ve got a “less clueless” level of knowledge.

I’m also less afraid of MIDI than I was before. Setting up connections to hardware and/or software was, and is, still a little bit of a pain, but it’s getting easier.

The course has also forced me to learn a new Digital Audio Workstation (DAW) – Reaper. I’m running it on a Windows machine because it’s easier to do it that way. For the sake of the class, I want to spend time learning the tool instead of how to make it work in my other environments. I’ll run it in Linux and Mac OS X eventually – just not yet. I’ve also got a Mac Mini my brother-in-law gave me, but I haven’t taken the time to get comfortable with that system.

My first assignment is due by the end of this weekend, and I’ve chosen to use this as an opportunity to revisit an old project. I’m going to do a new recording of “The Love Song of J. Alfred Prufrock”, by T.S, Eliot. I really like this poem, and it was among the first pieces I uploaded to SoundCloud. Here’s the first version:

[soundcloud url=”″ params=”color=00cc11&auto_play=false&hide_related=false&show_comments=true&show_user=true&show_reposts=false” width=”100%” height=”166″ iframe=”true” /]

This time, I feel I’m relying more on my own musical compositon chops. Here’s how I’m starting:

[soundcloud url=”″ params=”color=ff5500&inverse=false&auto_play=false&show_user=true” width=”100%” height=”20″ iframe=”true” /]

The assignment constrains the length of the piece (60 to 120 seconds) so the reading will only cover the first section. I’ll post the completed assignment to this article once it’s done.

UPDATE: Here’s the completed assignment:

[soundcloud url=”″ params=”color=00cc11&auto_play=false&hide_related=false&show_comments=true&show_user=true&show_reposts=false” width=”100%” height=”166″ iframe=”true” /]

I’m pleased  with how it came out. Now to finish the rest of the poem…

Comments closed

Poetic Tech at the Decatur Book Festival: The “Bloop-Bleep” Stage

On Sunday, August 31, 2014, I did a presentation on the intersection of technology and poetry at art|DBF, an art-oriented segment of the Decatur Book Festival. The presentation was the culmination of several months of coding to develop a system that allowed a poet and an audience to create an interactive soundscape.


Why did I do this?

Most people, when they think of poetry, they think of it as this fundamentally human, often life-affirming human activity.

Most people, when they think of technology, think of it as this inhumane, if not inhuman, often soul-crushing process.

This is a false dichotomy, of course. Poetry and technology are both artifacts of what humans do. They are both profoundly human acts.

From the campfire to the cathedral, from the crystal AM radio to the liquid crystal display, our technology has affected what form poetry takes, who creates it, who listens to it, where it is experienced, and how it is distributed.

My intent was to build a demonstration of one possible way to enhance the the experience of poetry for both poet and audience.


How did it work?

I built a web based audio application that controlled sounds with smartphones.

The phones accessed a web server running on my laptop. The pages for the audience could read through the poems being performed and manipulate sounds using one of three instruments.

Audience UI

The audience accesses a website via smartphone. The site offers a view of the current poem, a dropdown selection of poems, and links to one of three musical interfaces, the first of which displays by default.

The three interfaces do the following things:

  • Instrument 1: create a rain stick-like sound with different effects based moving a point within an small window;
    swipe demo - Chromium_465
  • Instrument 2: a set of four percussion pads;
    swipe demo - Chromium_466
  • Instrument 3: a text area that creates sounds for each word typed.
    swipe demo - Chromium_467

Poet UI

The interface for the poet has six options – unfortunately only four worked at the time of performance, and only three worked without issues.

  • Effect 1: pitch follower creating audio effect a fifth higher than detected frequency
  • Effect 2: pitch follower creating audio effect a seventh higher than detected frequency
  • Effect 3: Multicomb filter
  • Effect 4: Spectacle filter
  • Effect 5: Hypnodrone – drone effect kicked off by detected amplitude
  • Effect 6: Stutter – warbling bass line using sine oscillator. Originally intended to create a glitch effect.

Poet UI - Chromium_468


The speaker had a separate interface for adding vocal effects and a background beat.

The web pages sent messages to a set of ChucK scripts running on my laptop. The scripts generated the sounds and altered the vocals as well as recorded the presentation.


How did it go?

The presentation itself was well-received. It was in the tent for Eyedrum, an Atlanta-based, non-profit organization developing contemporary art, music and new media in its gallery space.

I did my presentation outside with a set of powered PC speakers attached to the laptop. Later, I borrowed a PA and mixer from my friend and fellow poet Kevin Sipp. By the way, check out his debut graphic novel, The Amazing Adventures of David Walker Blackstone:



The laptop was attached to a wireless router that passersby could use to connect to the website. Everyone was able to connect and interact with the site. There were some glitches – which I’ll talk about later – but for the most part, people seemed intrigued by the possible uses of mobile and web technology for poetic performances.

A couple of components either did not perform as expected or did not work at all. Of the audience-specific pages, Instrument 3 did not play or was at too low a volume to be heard over the ambient sounds of the festival. There were also some issues with switching between poems.

The poet-specific pages had issues with two of the six effects: “Multicomb” and “Spectacle”. The multicomb filter had a problem with feedback and was too loud. The spectacle effect didn’t work at all. In addition, the audio started suffering from latency issues. The recording of the first twenty minutes of the presentation started suffering from unintended glitching and was pretty much ruined. The recording of the last fifteen minutes was a little better (I stopped the recording to switch to Kevin’s PA setup), but suffered from the same issue not long into the presentation.



Overall, I think the presentation was well-received, and people were intrigued by what they heard. The issues with the setup became clear when I reviewed the recordings. There’s definitely room for improvement, and I will definitely build upon this design for future performances.

So good, bad, or ugly, I’m posting both recordings (Part 1 and Part 2) and the code for all to see.

Despite the issues, I consider the project a success. This is a prototype, so I expected some problems. Luckily, none of the problems were catastrophic. There were lots of bloops and bleeps, but nothing went “boom”. It would only have been a failure if I had learned nothing from the experience.

Until next time, check out the code, play with, let me know if you use it or modify it.


Comments closed