Open singing synthesis platform / Open source UTAU successor
An app for creating audio-based content such as song covers and speech using Retrieval-based Voice Conversion.
singing voice synthesizer with 3-part harmony and automatic voice leading
Fast singing-voice acoustic model: harmonic + noise excitation refined into a mel by a 1-step rectified flow (bundled NHVSing vocoder). Multi-speaker + style control; ONNX/OpenUTAU export.
浏览器端虚拟歌姬工作站 — 导入 MIDI，填写歌词，驱动 UTAU 声库演唱，支持 SeedVC 音色转换与多轨伴奏混音。
2019/04~2019/09 투빅스 Singing Voice Conversion
Voice model "LIEE" for DIFF-SVC by julieraptor
Negative Nancy's vocal synthesizer
🔦 A three-dimensional vocal tract acoustic model using the finite-difference time-domain (FDTD) numerical scheme.
An official website for NodoAme
Work-in-progress UTAU-compatible singing voice synthesizer, written in Go
The utility library for CeVIO project file (.ccs / .ccst) and timing label file (.lab).
A template for concatenative singing synthesis (UTAU, Deepvocal, etc.) voicebank development.
Releases and info on Nishiren AI for Diffsinger
Korean dictionary for Japanese SynthV voicebanks
KotoKanade is a tool to make VoiSona Talk sing.
Cross-platform Rust editor for UTAU and OpenUtau voicebanks, with oto.ini editing, waveform and spectrogram tools, audio recording, validation plugins, and synthesis testing.
A JavaScript library & web app for real-time vocal swar (note) detection for Hindustani classical music.
Teach your AI to play piano and guitar, sing, and now LISTEN. 53 MCP tools, 120 songs, 6 engines, a browser cockpit, and an audio inspector that measures a recording: onsets, pitch in cents, transcription, and grading a performance by ear. Ships two public tool-use datasets over symbolic and acoustic music.
To associate your repository with the vocal-synthesis topic, visit your repo's landing page and select "manage topics."