Dev builds singing synth that models vocal tract as branching acoustic tubes, not spliced samples

flngr · x · 2026-11-09

Developer Jameson Hodge showcased a vocal synth that models the vocal tract as a network of branching acoustic tubes, unlike Vocaloid's approach of stitching and pitch-shifting phoneme recordings. He is still tuning naturalness against real singer recordings, but the results already sound impressively cool.

Related event: Developer builds CHIMERA, a singing synthesizer using vocal-tract physical modeling(6 posts)→

Original post →

More from Fun

• RentAHuman lets AI agents hire real people for physical-world tasks via MCP API — conitzer · 2026-11-09
• LukeW mocks AI startup pitch escalation: 'oh crap, we're SaaS' — LukeW · 2026-11-09
• Ex-Apple engineer: Siri hired a native Italian speaker for QA back in 2014 — jdluk87 · 2026-11-09
• Impatient waiting for the electrician, ML engineer grabs a few B200s from Lambda — TheZachMueller · 2026-11-09
• 'Our systems aren't built to contain agents': ex-Anthropic engineer on Opus — appenz · 2026-11-09
• Turing Laureates 'Haven't Updated Their Slides Yet': AI Circle Mocks Outdated Views — akbirthko · 2026-11-09

Fun channel →