Dev builds vocal synth modeling vocal tract as branching acoustic tubes
TinfoilTricorn · x · 2026-11-10
Developer Jameson Hodge demonstrated a vocal synthesis model that models the vocal tract as a network of branching acoustic tubes — unlike Vocaloid's phoneme-stitching approach. Still tuning naturalness against real singer recordings, but early results already sound impressively cool.
More from Multimodal
- Seedream 5.5 text handling: sharper small-text accuracy for posters and layouts — azed_ai · 2026-11-10
- Seedream 5.5 realism upgrades: better skin texture, expressions, and lighting — azed_ai · 2026-11-10
- Seedream 5.5 adds direct RGBA transparent-background generation and stable multi-round editing — azed_ai · 2026-11-10
- Seedream 5.5 hands-on: near-photoreal images at just $0.02 per image — azed_ai · 2026-11-10
- Adobe ships MCP support across its entire Creative Cloud stack, from Photoshop to Firefly — LinusEkenstam · 2026-11-10
- One message to a realistic UGC video: Fish Audio's Creative Agent workflow — socialwithaayan · 2026-11-10