Official inference repo for FLUX.1 models

Code for Talk With Human-like Agents: Empathetic Dialogue Through Perceptible Acoustic Reception and Reaction (ACL24))

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Simple text to phones converter for multiple languages

Unofficial pytorch reproduction for the paper "Utilizing Neural Transducers for Two-Stage Text-to-Speech via Semantic Token Prediction" (arXiv:2401.01498)

Spectral Analysis in Python

vits2 backbone with multilingual-bert(한국어 지원)

Style-Bert-VITS2: Bert-VITS2 with more controllable voice styles.

vits2 backbone with multilingual-bert

DDPM-based Pitch Generation and Pitch Controllable Voice Synthesis.

Official implementation of the source-filter HiFiGAN vocoder

Easy-to-Use Speech MOS predictors

The official implementation of HierSpeech++

Unofficial implementation of NVIDIA P-Flow TTS paper

リアルタイムボイスチェンジャー Realtime Voice Changer

E2E TTS using Conditional Flow Matching (Experimental*)

Core Engine of Singing Voice Conversion & Singing Voice Clone

Collect Voice Conversion researches

Using joint training speaker encoder with consistency loss to achieve cross-lingual voice conversion and expressive voice conversion

Bilingual-TTS (Japanese and Korean)

Multi-speaker Speech Synthesis Using VITS(KO, JA, EN, ZH)

Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform with Multilingual Cleaners

VITS implementation of Japanese, Chinese, Korean, Sanskrit and Thai

XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech (INTERSPEECH 2023)

unofficial vits2-TTS implementation in pytorch

eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.