Certaines informations sont présentées en anglais.
À propos de moi
I build music, voice, and agent AI products from prototype to tested delivery.
I hold an MSc in Sound and Music Computing from QMUL and have 4 years of AI R&D experience. My work includes EmoHeal—emotion analysis plus therapeutic music retrieval/generation—and VoxSketch, a voice-to-editable-song workflow using Audiotool NEXUS.
I deliver generative music workflows, STT/TTS, audio analysis, voice agents, RAG, FastAPI, Docker, source code, tests, and documentation.
Expect clear scope, honest technical boundaries, milestone delivery, and a system you can keep building after handoff.... Plus d’infos