Synthesize vocal by sinewave.

This repository contains the code for the PhonHuBERT phoneme sequence generator for Singing Voice Synthesis dataset annotation.

Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition.

Robust Singing Voice Transcription and MIDI Extraction

Mixbox is a library for natural color mixing based on real pigments.

New Korean UTAU format with fine-grained aliases

A ChatWaifu Version with official ChatGPT API

Open-Free TTS Platform For All

An audio-labeling web app. You can use it to create oto.ini files.

This repositoy contains two scripts for converting a .TextGrid (Praat file) to a .lab file

Novoic's audio feature extraction library

A browser-based tool to convert International Phonetic Alpha (IPA) phonetic notation to speech using the meSpeak.js package

SOFA: Singing-Oriented Forced Aligner

A simple tool to easily use Montreal Forced Aligner. Also provide alignment(TextGrid) retrieved from ESD.

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

A multi-speaker, multilingual speech generation tool

MARY TTS -- an open-source, multilingual text-to-speech synthesis system written in pure java

The MUSS3640 Vocal Synthesiser is a standalone application/VST3 plugin developed to allow exploratory synthesis of the singing voice. It implements a combination of formant-wave-function and bandpa…

Convert UTAU Sequence Text and JSON to each other. UST情報(UTAU)とJSONを相互変換します。

UTAU Auto Pitchwriter using machine learning

A python converter to convert UTAU voicebanks to hiragana from romaji (and vice versa)

UTAU resampler using the ESPER vocal synthesis framework.

ピッチを自動生成するUTAUプラグイン

✨ UTAU DEBUG ENGINE | UTAU错误检查引擎

A tool to generate basic/advanced lyric file from existing UTAU project.

A Rust port of straycat, a WORLD-based UTAU resampler

Yet another WORLD-based UTAU resampler.

A toolbox for manipulating UTAU voicebank's mark file format(oto.ini)