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…

An instruct text-to-speech solution based on LLaSA and CosyVoice2 developed by the ASLP lab and collaborators.

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

A high quality and fast TTS repository

The best ChatGPT that $100 can buy.

A framework for efficient model inference with omni-modality models

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

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

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

We Speech Transcript based on LLM, in 300 lines of code.

Text-audio foundation model from Boson AI

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

Phonetisaurus G2P

Text Normalization & Inverse Text Normalization

The Triton TensorRT-LLM Backend

Count the MACs / FLOPs of your PyTorch model.

Official implementation of the paper "BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec"

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

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

基于SparkTTS、OrpheusTTS等模型，提供高质量中文语音合成与声音克隆服务。

A Conversational Speech Generation Model

Spark-TTS Inference Code

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

Running the F5-TTS by ONNX Runtime

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)

AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model

GLM-4-Voice | 端到端中英语音对话模型