Freelance AI / ML engineer
Custom voice, image, and text systems with a sharp visual identity.
I am a freelance engineer who builds custom voice models, image models, text models, LoRA fine-tunes, vector databases, AI/ML frameworks, and more. The problem with voice models is that we can always tell it's AI. I strive to create models that are indistinguishable from real human voices.
CONTACT
DIRECT LINKS
WELCOME
PORTFOLIO
Some of my work is showcased through the demo audio below. Please visit my GitHub and Hugging Face to see examples of the text and image models as well as the software I have developed.
If you'd like to work together, join my Discord and you can use the bot to fill out a contact form or you can send me an email.
SYSTEM CONTROLS
DISPLAY TUNING
AUDIO SPECTRUM ANALYZER
DEMO SAMPLES
API RESPONSE TIME
127ms
INFERENCE SPEED
2.4K tok/s
MODEL TEMPERATURE
0.7
NO FILE SELECTED
SYSTEM TERMINAL
ONLINE
NEXUS PORTFOLIO INITIALIZED.
responsive.layout.enable(true);
three.js scene replaced with lightweight html/css/js modules.
audio.visualizer.bind({ fftSize: 2048, smoothing: 0.8 });