OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.

Lightweight coding agent that runs in your terminal

Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.

Mobile-Agent: The Powerful GUI Agent Family

Voice Activity Projection Models: Self-supervised learning of Turn-taking Events

Turn detection for full-duplex dialogue communication

Open-Source Turn-Taking Detection Model and Dataset for Full-Duplex Spoken Dialogue Systems

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

OSUM & OSUM-EChat, open speech understanding model and empathetic spoken chatbot based on it, open-sourced by ASLP@NPU.

[ICML 2025 Tokenization Workshop] HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling

LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation

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

Janus-Series: Unified Multimodal Understanding and Generation Models

[ACM CCS'24] SafeEar: Content Privacy-Preserving Audio Deepfake Detection

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

A family of state-of-the-art Transformer-based audio codecs for low-bitrate high-quality audio coding.

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

A Survey of Spoken Dialogue Models (60 pages)

Ultra-low-bitrate Speech Codec for Speech Language Modeling Applications

✨✨[NeurIPS 2025] VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Run frontier AI locally.

A generative speech model for daily dialogue.

A Framework for Speech, Language, Audio, Music Processing with Large Language Model

[ICLR 2024] Official code for the paper 'Elucidating the Exposure Bias in Diffusion Models'

Daily tracking of awesome audio papers, including music generation, zero-shot tts, asr, audio generation