The official implement of VITA, VITA15, LongVITA, VITA-Audio, VITA-VLA, and VITA-E.

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

MOSS-Speech is a true speech-to-speech large language model without text guidance.

Open-Source Frontier Voice AI

An official implementation of "Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning".

✨✨[NeurIPS 2025] VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model

A package for NeuCodec: a 50hz, 0.8kbps, 24kHz audio codec.

[ACL 2025] Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis

Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

Colab notebook for fine-tuning Qwen2-Audio with trl's SFT and PPO trainers.

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.

LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM

Codebase for 'Scaling Rich Style-Prompted Text-to-Speech Datasets'

Official PyTorch implementation for "Large Language Diffusion Models"

Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction

LUCY: Linguistic Understanding and Control Yielding Early Stage of Her

GPT-4o-level, real-time spoken dialogue system.

Re-implementation of Self-Refine

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

[ICCV 2025] VideoVAE+: Large Motion Video Autoencoding with Cross-modal Video VAE

Official repo for CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations