Phlo Young is an independent rapper, songwriter, and self-taught audio engineer exploring how AI-assisted music production can expand creative possibilities while preserving artistic control. His work combines independent recording, music marketing, distribution, and hands-on experimentation with generative audio.
Before adopting AI music tools, Young worked across hip-hop, R&B, electronic music, and country-influenced material. He released the same recordings under different artist identities, testing how artwork, promotion, and audience targeting changed their performance. During the pandemic, he learned Python to automate personal and professional tasks; he has also compared Whisper speech-recognition models through repeated audio tests.
At AI Engineer World’s Fair 2024, Young led a practical workshop on generating, editing, and distributing music. His approach emphasizes several distinctions:
- Three forms of generative music: Text-to-music creates audio from written instructions; audio-to-music transforms existing sounds; artist-controlled voice conversion modifies recorded vocals. Each raises different questions about authorship, consent, and creative input.
- Songwriting as an iterative workflow: Young uses language models to refine lyrics and musical instructions, then supplies details such as genre, tempo, key, and existing recordings. He treats Udio’s extensions, remixes, and inpainting as collaborative editing tools, while noting Suno’s tendency toward more immediately polished output.
- Music stem separation: With Wave Tool or the open-source UVR5 project, Young isolates vocals and instruments so generated songs can be rearranged, mixed, and mastered instead of remaining uneditable clips.
Young continued examining Suno, Udio, and Riffusion in a 2025 generative-music interview. His priority is independent music distribution that gives artists greater access to production without diminishing their creative judgment.
