Official implementation of YingMusic-SVC.

[ASRU 2025] Omni-R1: Do You Really Need Audio to Fine-Tune Your Audio LLM?

Implement a reasoning LLM in PyTorch from scratch, step by step

Minimal reproduction of OneRec

Official Repository of Paper: "Towards High-Quality Zero-Shot Singing Voice Conversion in Low-Resource Scenarios"(AAAI 2026)

T5Voice is a lightweight PyTorch implementation of T5-based text-to-speech synthesis, supporting both streaming and non-streaming speech synthesis with zero-shot capabilities.

A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing emotion, speaking style, and paralinguistics, and features robust zero-shot text-to-speech

A Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows

This is the repository for the work "BridgeVoC: Revitalizing Neural Vocoder from a Restoration Perspective".

Official implementation of "Continuous Autoregressive Language Models"

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

An Open-Source Project to Unify Audio Processing and Generation

[ACM MM 2025] AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation

SoulX-Podcast is an inference codebase by the Soul AI team for generating high-fidelity podcasts from text.

哔哩下载姬(跨平台版)downkyi，哔哩哔哩网站视频下载工具，支持批量下载，支持8K、HDR、杜比视界，提供工具箱（音视频提取、去水印等）。

[ICASSP 2025] "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"

轻量级大语言模型MiniMind的源码解读，包含tokenizer、RoPE、MoE、KV Cache、pretraining、SFT、LoRA、DPO等完整流程

Unofficial pytorch implementation of VISinger: Variational Inference with Adversarial Learning for End-to-end Singing Voice Synthesis (ICASSP, 2022)

Contexts Optical Compression

LongCat Audio Tokenizer and Detokenizer

Official code for"DiaMoE-TTS: A Unified IPA-based Dialect TTS Framework with Mixture-of-Experts and Parameter-Efficient Zero-Shot Adaptation"

The best ChatGPT that $100 can buy.

This is the official code for ACM CIKM 2025 Paper: ParaStyleTTS: Toward Efficient and Robust Paralinguistic Style Control for Expressive Text-to-Speech Generation

开箱即用的本地私有化部署语音服务，快速搭建FunASR与CosyVoice2后端

On-device TTS model by Neuphonic

Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation

We Speech Toolkit, LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction