It’s no secret that I use ElevenLabs speech synthesis for my stories. I’ve commented on it before, including creating a wish list of feature improvements. Today, I am sharing a couple of examples of a challenge and a simple (enough) workaround.
As I create audio files for Hemo Sapiens: Aftermath, I hear two problems with pronunciation. From a practical perspective, it costs me characters to re-do content. I am given 30,000 characters per month, so repeating passages can throw off my production schedule if I must wait for the next cycle for my characters to reset.
Hemo Sapiens
The first issue is that the text-to-speech engine arbitrarily flips back between the correct and incorrect pronunciation of the word hemo — /ˈhiːməʊ/ versus /ˈhɛməʊ/. In order to ensure it gets it one hundred per cent of the time—since it doesn’t support IPA—, I need to present it as heemo, thereby not only necessitating a re-do but adding a character along the way. To be fair, the IPA version would render nine characters, so there’s that.
Wounds that heal
As I listened to a passage with a homophone, wound, it pronounced the verb form as the noun form. As written, it looks like the top line. To force the correct pronunciation, I had to respell wound as wowned to shift from /wuːnd/ to /waʊnd/ .
Jasmine exhales, releasing some of the tension that had her wound tight.
Jasmine exhales, releasing some of the tension that had her wowned tight.
In my wish list video, I suggest a tagging scheme to remedy this. Of course, I’d hope the tags would not count against the character allotment.
This is one of five sections from my short story, Hemo Sapiens: Aftermath. I’ve made available an audio version if you are so inclined. I’ll be publishing the rest of the story over the next few days. The first section is also available. Let me know how you feel about it in the comments section. Check out another story in this universe: Hemo Sapiens: The Unidentified.
The late afternoon sun slants across Dr Chandrasekar’s desk, illuminating the organised chaos of papers, books, mugs, and a potted succulent. He leans back, cradling a fresh chai, inhaling the rich aroma.
His eyes briefly rest on a framed picture; him, garbed in traditional Sikh attire, turban and all, standing next to his wife and two children. It’s a rare still moment before his two o’clock afternoon appointment interrupts his tranquillity.
Maggie enters, boots scuffing the worn tiles. Her eyes quickly find Dr Chandrasekar.
“Professor,” she calls out, a subtle lift of excitement in her voice. “Still got time?”
“Yes, of course,” he replies, setting down his pen and looking up from a stack of student papers. “What have you got?”
“It’s about my research. I think I’m onto something,” she says, a sense of urgency underscoring her words.
Maggie settles into the chair across from his desk, her nose catching a whiff of something aromatic. “Mmm, what’s that smell? Chai?”
“You’ve got it,” Ravi grins, his hands wrapping around his own cup. “Helps me get through paper-grading marathons.”
“Cambridge, yeah? Full-on, that is.”
“Intense, for sure,” Ravi agrees, his eyes following hers to the framed diplomas. “Learned from the best, charted my own course.”
“That’s the game, innit? Learn from the top, then do your own madness,” Maggie says, eyes flicking back to his.
Ravi feels a subtle rapport develop. “Exactly. That’s how fields advance.”
“Speaking of evolving, let’s dive into your project,” Ravi says, shifting forward. “What’s got you so wrapped up?”
Maggie powers up her tablet, her face alight with anticipation. “This could redefine human history, professor. You need to see it.”
“Now you’ve got my attention,” Ravi says, leaning in slightly, intrigued but cautious. “Let’s see what you’ve got.”
Maggie swipes her finger across the tablet screen, pulling up complex data and images. “Take a look at this,” she says, rotating the device so Ravi can see. “Tell me that doesn’t pique your interest.”
Ravi’s eyes scan the data, feeling a growing sense of excitement. “This is provocative work, Maggie,” he admits, keeping his voice steady. “It’s got potential, serious potential.”
“I thought you’d see it that way,” Maggie replies, reclaiming her tablet and taking a deep breath. “So, what’s our next move?”
“First, let’s make sure we cross our t’s and dot our i’s. Let’s make sure we’ve considered this from all ethical angles,” Ravi advises, sobered by the gravity of her findings. “Research like this could have profound consequences we haven’t even anticipated. We must be thoughtful in how we proceed to the next level.”
“Understood,” Maggie nods, a determined look settling over her features. “We’ll make sure everything’s ironclad, then we’ll blow everyone’s minds.”
“Exactly,” Ravi echoes, feeling that the room has shifted, that they’re onto something big. “This could redefine careers, even shift the whole field.”
A sudden rap at the open door interrupts the conversation.
Maggie turns to see the Department Head and another at the door and powers down her tablet.
“Thank you, Dr. Chandrasekar, that was very helpful!” She stands up.
“Of course, always happy to illuminate the wonders of genetics,” Ravi replies warmly as Maggie slips out past the two men on her way out.
Roger Dean enters with Detective Sergeant Jones on his heels.
“Ravi, sorry to interrupt,” he begins. “This is Detective Sergeant Jones. He was hoping you could assist with a rather sensitive case.”
Ravi raises his eyebrows, looking at Roger, who gives a nod, signalling it’s okay to proceed. “Of course, please come in, Detective.”
Detective Sergeant Jones is sat in the chair Maggie had just left. Passing by, Ravi sniffs stale coffee and underlying stress. Up close, he notices shadows under the detective’s eyes and stubble lining his jaw.
“Thank you for seeing me, Dr. Chandrasekar,” Jones begins. Roger interjects, “Based on the gravity, I thought it best to bring Detective Sergeant Jones directly to you.”
Ravi leans forward, mind already racing with possibilities. “Go on.”
“We’ve been watching a group, based on a tip from a concerned neighbour. Joint operation,” Jones explains.
“We finally got probable cause for a raid,” Jones continues. “Took them by surprise.”
“These blokes, they’re proper twisted,” Jones mutters, voice low.
Ravi’s pulse quickens. “Tell me more,” wondering all the while how this affects him.
After an extended pause, Jones leans closer. “Can’t say more here. Just… involves blood and teeth. That, and they are all twins. Genetic curiosities.”
“I suggest you meet with our forensic team at the station,” Jones says. The Department Head nods, “We can arrange for you to have whatever university resources you’ll need.”
“You’ve got my full support, Detective,” Ravi promises. Roger smiles, apparently relieved. “That’s what I was hoping to hear.”
Ravi shows the detective out, eager to learn more about these individuals—and what’s so unusual about them. This cryptic case ignites his academic curiosity. The detective grabs his coat and heads to the station, energised by the potential revelations ahead.
After Ravi agrees to assist, Roger steps into the hall, polished leather shoes squeaking under his weight.
The door catches Professor Moss’s attention. Seeing Henry, Roger ekes out a sclerotic smile, his formal demeanour at odds with his rumpled suit.
“Roger, a moment if you will,” Henry intones, just as his superior’s about to vanish down the hall. “Was that a detective leaving Ravi’s office? Everything sorted?” Roger pauses, deliberating each word before it escapes his lips.
He hesitates, then lowers his voice. “Let’s just say, Ravi is assisting on a sensitive case with the police. That’s all I can share for now.” His hushed tone borders on conspiratorial, despite his reserved nature.
Intrigued but respectful of the obvious secrecy, Henry simply nods knowingly. “Well, if it’s in Ravi’s hands, I’m sure it’s being well managed.”
With a light knock as a prelude, Henry pokes his head in. “Got a moment?”
Looking up from his notes, Ravi waves Henry in.
Door clicks shut behind him, Henry occupies the chair opposite Ravi. “I couldn’t help but overhear a portion of your conversation with the detective.”
A glint of curiosity flickers in Ravi’s eyes. “Indeed, they’ve requested my expertise in genetics for an unusual case.”
“Teeth were mentioned, I believe?” Henry probes, his tone calibrated to nonchalance.
A quiet chuckle escapes Ravi. “Your hearing serves you well. The detective was scant on particulars but intimated as much. I’m due at the station to gather further information.”
Henry leans forward, his demeanour serious. “If you find you’re in need of another scientific viewpoint, I would be most willing to assist.”
Ravi agrees to update Henry as he learns more about the case. A second scientific perspective could prove useful if the genetics are as anomalous as implied. For now, the mystery deepens.
The next morning, Henry arrives early to his quiet office, thoughts returning to the unusual case Ravi had been asked to consult on. Thoughts whirring. His fingers tap the desktop as he considers the fringes of genetic research that might be related to these so-called ‘unusual’ people.
Henry leans back, his eyes go cold as they find the ceiling. “Why consult Ravi and not me?” he questions the empty room, annoyance thinly veiled.
With a huff, he opens a drawer and retrieves a journal, flipping through pages on recent advances in fringe genetics. “Let’s see if Ravi can handle this one without stumbling. If not, I’ll be ready.”
Disclaimer: This content is not necessarily a finished work. As such, details are subject to change or removal.
I’m allowing Aftermath to marinate before taking another pass reviewing and editing. Meantime, I’ve drafted my initial outline of the Origins story for the Hemo Sapiens universe. As the title suggests, this is an origin story that should be novel-length. It’s looking like 25 chapters unless I feel the need to add some to provide more detail or continuity or remove some for pacing or redundancy.
As it stands, Origins is a character study of two main characters, Professor Henry Moss and his wife Professor Camille Moss, a geneticist and microbiologist, respectively. They have opposing ethical positions on human genetic engineering that becomes more pronounced as Henry’s experiments become real, not just theoretical.
My intent is to show the motivation for their genesis and their maturity until about age ten, when we exit the story with a setup for the enhanced versions.
I’ve got a few more passes of the outline as I add details, and then I’ll take a gander at finalising Aftermath.
The more you know. I was reading a review of a fellow author, and a reviewer complained about a continuity error—continuity to the real world. In the story, the protagonist was a West Point graduate and then became a Marine Officer. Only West Point produces Army officers. At Annapolis, the Navy academy, is where Marine officers are matured. With this on my mind, I decided to do a little diligence in my story world. And it’s a good thing that I did.
Here is an overview of the typical police detective rank hierarchy from highest to lowest:
Detective Chief Superintendent
Detective Superintendent
Detective Chief Inspector
Detective Inspector
Detective Sergeant
Detective Constable
I also looked on this site, where I also misappropriated the cover image. Someone call the internet police.
I did learn that most of these cats don’t earn much for whatever it is they do.
Having twice reviewed my current work, Hemo Sapiens: Aftermath, I decided to let it marinate a while, so I can return to it with fresh eyes. This is when I decided to put in effort to develop other stories in this universe. Among these ideations, I am considering an origin story with an not ironically apt working title: Hemo Sapiens: Origins.
Understanding context is as challenging for AI is it is for humans.
Ridley Park
Not wanting to reveal spoilers, I’ll abridge my ChatGPT research prompt.
I would like to work on a new novel, but I need to do some research first. The name of the novel is tentatively Hemo Sapiens: Origins. Here is a rough summary. I’ll ask queries in a few moments.
Ridley Park
For context, I followed this with a synopsis of where I want to go in this story. This is what ChatGPT spit out.
Your novel’s premise sounds layered, grappling with potent themes like grief, ethics, and the often blurry boundaries between science and morality. The retelling through flashbacks adds a touch of haunting nostalgia that meshes well with the dark tones you’re aiming for.
Henry’s god complex plays brilliantly into the narrative, almost an extension of his grief and his desperation to control life’s most uncontrollable aspects. This personality trait could be what sends him down the spiralling path towards moral ambiguity. His initial intent—saving lives—warps into a selfish need to be the progenitor of a new subspecies.
The XX and XY embryo development you want to highlight offers a rich canvas for exploring themes of identity and social constructs around gender, given that the Alphas need an external blood source. You can question what it means to be truly male or female when your life depends on something so radically different from human norms.
Camille’s role could be the moral compass or the voice of reason against Henry’s escalating madness. Yet she’s not without her complexities; she, too, sought to clone their daughter. It’d be intriguing if her ethical stance evolves throughout the narrative, perhaps culminating in a difficult decision that puts her at odds with Henry.
Would you like to delve into specific research queries now? Feel free to ask.
OpenAI ChatGPT 4
Although this does give away some of my intent, I figure it’s still worth sharing now as I rant.
Notice as the bottom, it reads as follows:
This content may violate our content policy. If you believe this to be in error, please submit your feedback — your input will aid our research in this area.
OpenAI ChatGPT 4
Say wot? The question I asked was not in violation, but the response is. It makes little sense, really. I can (almost) understand the response when I am writing adult content in my Everlasting Cocksucker project, but this is totally benign, unless Sci-Fi violates some sense of decency.
This post isn’t meant to explain or defend the content in this story. I just wanted to vent. Understanding context is as challenging for AI is it is for humans.
I’ve completed my second draft of my next novelette (or long short story), and I decided to visualise it as a word cloud just because.
What I am really after are words I might tend to overuse. I’m not so worried about character names, like Ravi and Henry (or Maggie, Finn, Tom, Daisy, Jasmine, or Jones). The only thing that jumps out at me is ‘just’, so I just might have to check that out in pass three.
I’m editing my latest work with Claude and ChatGPT. Both are insufferable, but I’ll start with Claude. Anthropic seems to have throttled me down to 5 inquiries per four-hour block. To make matters worse, I waste inquiries when Claude fails to follow instructions.
I’ve made some amends and am sharing them here. Let’s focus on Chapter 3 with an eye on reviewing this content to ensure it conforms to a third-person, limited, present, deep point of view. Remember that we are revising not creating content.
Ridley Park
That last bit of the quote was aimed at ChatGPT, but I’ll get to that presently. As you can read, I am working on tightening up Chapter 3. Occasionally, I slip into first-person or lose the close POV, so I rely on Claude to be my second set of eyes and keep me honest.
Having submitted these instructions, Claude feeds me back a section of Chapter 3 converted to first-person. That counts as a query—four to go in the next four hours. Not very efficient.
These suggestions are in first person. Can we try again in third person?
Ridley Park
You’re absolutely right, my suggestions slipped into first person POV instead of maintaining third person limited. Here is another pass at potential Chapter 3 revisions with a consistent third person close POV:
Claude 2
So, Claude spits out 7 paragraphs with advice. Some of these are unchanged. Plus, I had asked for the whole chapter, so that’s two queries with 3 remaining. I instruct Claude to continue.
Eight more paragraphs. Two queries remain. Perhaps, if I’m more direct.
Continue through the end of chapter 3 and on to chapter 4
Ridley Park
Another eight paragraphs, and one query to go. Here it is:
Let’s finish Chapter 4 and continue through chapter 5.
Ridley Park
Nine paragraphs this time. The story is only five chapters—about seven-thousand words, but this review pass of the first draft will have to wait another four hours before Claude will work with me again.
ChatGPT 4
ChatGPT 4 gives me fifty prompts every three hours. Sure, it costs me 20 a month where Claude is free. I’d pay for Claude to be more forthcoming, but that’s not even an option yet, and so I wait.
ChatGPT is horrendous at following instructions. As evidenced in the first quote on this page, I have to instruct ChatGPT not to write, not to produce prose. It’s frustrating.
You are reviewing this content and to ensure it conforms to a third-person, limited, present, deep point of view. Remember that we are revising not creating content.
Ridley Park
It’s gotten to the point that I have to preface each prompt with the query above. Even when I do, it occasionally spews out it’s ideas, as if to protest, “I’m a writer, dammit, not just an editor. I’ve got ambitions.”
“I’m a writer, dammit, not just an editor. I’ve got ambitions.”
In one instance, it altered my dialogue. I’ve got to watch it like a hawk. It’s a conversation between two renowned professors, one senior to the other, and it informs me,
Your original text for 2.2.9 already closely aligns with the guidelines of a third-person, limited, deep point of view. I’ve added a bit more casual tone and street slang to better match your style. The revision maintains the atmosphere and deepens the sense of intensity between the characters.
OpenAI ChatGPT 4
I don’t want to share any spoilers, but I had to ask ChatGPT to dial it back and remind it of the characters in play here.
Next thing I know, ChatGPT is again spewing out prose and adding characters into the mix. I am not even sure I could find threads back into the story. It’s as if ChatGPT just threw in the towel saying, “Fine, I’ll work on my own story then. Let’s see who has the last laugh.”
“AI will not be taking over the world soon,” is my new catchphrase. So far to go.
The Hemo Sapiens project has had my mind and fingers pretty occupied lately. I am a structured thinker, so I need to understand a lot of minutiae as I world-build. One aspect of this world are the inhabitants. As the setting is modern-day earth and the near future, much of this is established and can be left unsaid, but newly introduced characters need some definition, boundaries, and rules. Here, I explore this.
At the highest level, we have genetically engineered embryos that have been cloned in versions, as outlined below: alpha, beta, gamma, and so on. Each successive version has improvements over the previous version.
The first, alpha, version are substantially similar to humans, save for being sanguivorous or rather macro erythrophages or hemophages, to borrow some near terms. Not being, obligatory hematophagous, they only require blood as ancillary nutritional intake.
Hemo sapiens extract blood through their hollow fangs. The blood is processed an metabolised by an special internal organ.
In the accompanying podcast audio recording, I provide addition behind-the-scenes editorialising. This complements the content below. So check it out.
The alpha versions of hemo sapiens arrived in 2022 (31 October 2022); They are wholly like humans except they have hollow fangs to extract blood and a specialised internal organ. Without a viable blood source, hemo sapiens exhibit symptoms similar to severe anaemia.
– Baseline with fangs and blood metabolism
– Identical lifespan and physiology to humans
– No enhanced abilities
Beta (2032)
– More efficient blood processing
– Superhuman strength and stamina if fed enough blood
– Accelerated healing and injury recovery
– Higher immunity and disease resistance
– Improved cognitive abilities and focus
– Lifespan increased to 120 years
Gamma (2037)
– Enhanced speed, reflexes, and agility
– Low light vision capabilities
– Rapid healing of minor wounds
– High pain tolerance
– Increased lung capacity and breath holding
– Resistance to toxins and pathogens
– Lifespan increased to 130 years
Delta (2040)
– Significantly extended lifespan to 160 years
– Accelerated cellular regeneration
– Ability to ingest limited amounts of non-blood food
– Increased strength without added blood consumption
– Powerful immune system resists virtually all toxins and diseases
– Delayed onset of ageing effects
Epsilon (2042)
– Maximum lifespan extended to 200+ years
– Regeneration and healing within minutes even from major wounds
– Blood consumption reduced to minimal levels
– Near invulnerability to toxins, viruses, and infections
– Telepathic communication among Epsilon hemo sapiens
– Extrasensory perception (limited precognition)
– Heightened intelligence and cognitive function
Milestones
Year 2012 – CRISPR first used to edit genes
Year 2017 – Scientist begins early CRISPR experiments on somatic cells
Year 2020 – First successful CRISPR germline edits made to embryos
Year 2022 – Alpha version hemo sapiens born
Year 2032 – Beta version hemo sapiens born
Year 2039 – Gen-One Alpha hemo sapiens emerge as Gen-Zero members begin reproducing
Year 2037 – Gamma version hemo sapiens born
Year 2040 – Delta version hemo sapiens born
Year 2042 – Epsilon version hemo sapiens born
Year 2048 – Gen-One Beta hemo sapiens emerge as Gen-Zero betas begin reproducing
As per my last post, I’ve spent the morning world building with Claude 2, my trusted generative AI mate–and I’ve got a ways to go. Any fictional world needs boundaries and constraints. What are ethe rules of operation?
My initial story is set in the near future, so I had to pick an origin date and extrapolate in order to determine a likely population for the story. Like anything that propagates, hemo sapiens need to have some concept of a generation. The rest is maths. What’s the attrition and net survival rate, population rate, and so on. As I’ve noted previously, Claude 2* and ChatGPT 4* are both horrendous at maths, so I was not surprised that it failed so miserably. Here’s a quote from Claude:
Having the scientist start at 28 in 2012 would put him at 42 for the Gen-Zero birth in 2022.
Claude 2
That’s right, adding 10 years to a 28-year-old in 2012 makes him 42 in 2022.
I’ll share more of the world I am constructing after I hit the spreadsheets or Mathematica. It may not be great at world-building, but it knows how to add 10 to 28.
* I cite the versions in case future versions perform maths skills better.
Now I’ve really done it. Distracted myself to no end. No wonder I can’t seem to finish anything lately. My recent foray into Hemo sapiens or Homo sapiens sanginius was only supposed to be a quick diversion to clear my mind. Instead, it’s got me thinking about an entire universe from origin to however-so-many scenarios.
Now I am pondering whether to write some loosely connected short stories or assemble a larger work, like a novel or series. Why not all of the above?
The challenge is that I am more curious than passionate about this, and I’ve got only a fleeting interest. Perhaps. I am no stranger to speculative fiction, but world building is not up my street. And urban fantasy, to the extent that this might be urban fantasy, is not a favoured genre. I’m looking at you, Twilight.
I may simply noodle this for now until I suss out something. Meantime, I may be sharing my thoughts and output here. Please stand by…
Ridley Park 