LLM controls vocal synth to perform Ave Maria in 4-part harmony
AAAzzam · x · 2026-11-12
A developer demo shows an LLM manually controlling a vocal synthesis model that models the vocal tract as branching acoustic tubes (unlike Vocaloid's phoneme stitching). Built with Kimi K3.1 Pro on Modal, it performs Ave Maria in 4-part harmony; naturalness tuning against real singers is ongoing.
More from coding & agent
- Peter Yang's feedback on Claude Duet desktop: odd entry points and confusing channels — petergyang · 2026-11-12
- Solo dev builds zombie horde level with Tripo P2.0, Fable and new Kaigen engine — gdechichi · 2026-11-12
- United Airlines to Ban Personal AI Agents From Booking Flights for Customers — Polymarket · 2026-11-12
- Agentic Search explained: a 4-search loop costs about 5x one search — and queries leak to more companies — adnan_hashmi · 2026-11-12
- AWS says thousands of autonomous AI agents wrote every line of AWS Emulator — SumitGup · 2026-11-12
- freeCodeCamp launches free 2-hour course on agentic coding with Codex — adnan_hashmi · 2026-11-12