Chimera vocal synth models the vocal tract as branching acoustic tubes, ditching phoneme stitching
rickasaurus · x · 2026-11-11
Developer jameson hodge shared Chimera, a vocal synth that takes a fundamentally different approach from Vocaloid: instead of stitching together and pitch-shifting phoneme recordings, it models the vocal tract as a network of branching acoustic tubes.
He is still tuning naturalness against recordings of real singers, but says he's already impressed by how cool the results sound.
More from Multimodal
- Dev generates entire AI movie with Fable 5.2, admits he never watched it — TuhinChakr · 2026-11-11
- Canva Opens Its Craft AI Design Model to Developers via API — aziz4ai · 2026-11-11
- Seedream 5.5 lands on Lovart with RGBA transparency and better in-scene text rendering — aziz4ai · 2026-11-11
- Claude turns 27 reference images and a life allegory into a game with 1,159 paintings — gorkem · 2026-11-11
- rea-video: open-source tool reverse-engineers any video shot by shot, 6.5k GitHub stars — songguoxiansen · 2026-11-11
- DEZO: an AI-generated teaser for a 'lost' 1980s cyberpunk action film — RealBrainRocket · 2026-11-11