Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

arXiv 每日论文，每周一到周五更新。

Open Source Speech Language Model

MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenario…

Chinese Text Normalization and Dataset

Grapheme-to-Phoneme transductions that preserve input and output indices, and support cross-lingual g2p!

Executable file for VITS inference

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

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Japanese Converter Kanji to Hiragana, Katakana, Roma-ji

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

全局指针统一处理嵌套与非嵌套NER的Pytorch实现

Implementing DeepSeek R1's GRPO algorithm from scratch

GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning

汉字拼音数据

A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset

Chinese polyphone disambiguation for Text-to-Speech application

High-quality speech synthesis with LoRA fine-tuning on index-tts, enhancing prosody and naturalness for single and multi-speaker voices.

LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

FlashCosyVoice: A lightweight vLLM implementation built from scratch for CosyVoice.

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

结巴中文分词

CMUdict maintenance, and tools

Production First and Production Ready End-to-End Text-to-Speech Toolkit

The official repository of SpeechCraft dataset, a large-scale expressive bilingual speech dataset with natural language descriptions.

Official Repository of Paper: "SynParaSpeech: Automated Synthesis of Paralinguistic Datasets for Speech Generation and Understanding" (ICASSP 2026)

Official implementation of the TTS model Lina-Speech

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning