Vocal Synthesis

I am a recent graduate from SAE Expression Creative Media College, where I earned a Bachelor of Applied Science in Animation and Visual Effects in April 2020. My background includes experience as a digital artist with a special emphasis on Vocal Synthesis, Vocal AI, and 3D Modeling. I am excited about the possibility of using my creativity and artistic skills to create AI voicebanks and datasets.


  • Sound engineered and edited over 500 audio projects for music, podcasting, and audio quality development

  • Edited and revised 40+ audio transcribed datasets to feed into various ai architecture/models such as: Talknet, Tacotron2, Diff-SVC, Cicumreality etc.

  • Trained and troubleshot over 25 Diff-SVC datasets to improve voice data quality for data analysis for revision.

  • Transcribed and trained 30+ Talknet models using ARPAbet (a phoneme set) for quality analysis in audio engineering projects

  • Proficient experience in a variety of software tools, including: Maya, Pro Tools, Logic Pro, After Effects, Adobe Premiere Pro, 3Ds Max, Krita, FL Studio, Reaper, and Studio One.

In particular, I am interested in leveraging my skills to create datasets for AI voicebanks. I believe that my experience in vocal synthesis and Vocal AI will be invaluable in this role. Additionally, my background in music and video production gives me a unique perspective on the creation of voicebanks and the use of AI in the music industry.

My creativity and passion for digital art allows me to think outside the box and approach problems in innovative ways. I am excited about the opportunity to contribute my skills to a team that is dedicated to pushing the boundaries of AI technology and creating cutting-edge voicebanks and datasets.

Vocal Synth Articles

RVC+ trained Model

Diff-SVC trained Model

Utau voicebank Recorded

RVC trained Model