The most powerful local music generation model that outperforms most commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

Chain apps and models to build robust AI workflows 🤗

A TTS that fits in your CPU (and pocket)

HeartMuLa Official Repo: The Most Powerful Open-Source Music Generation Model of 2026

Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control

Echo-TTS inference codebase

DACVAE

Reachy Mini's SDK

A framework for efficient model inference with omni-modality models

a list of demo websites for automatic music generation research

How to build the best search, one step at a time!

HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

CodecHub: A Unified Library for Codec Models

the goal is to give LLMs access to reachy mini

Prune transformer layers

A library for reading and writing iTunes style MPEG-4 audio metadata

dLLM: Simple Diffusion Language Modeling

Pure Rust multimedia format demuxing, tag reading, and audio decoding library

Valdi is a cross-platform UI framework that delivers native performance without sacrificing developer velocity.

The open-source app builder

[ICML 2025] SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation

NOF0 - 开源的 AI 交易竞技场

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

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

Smaller and faster nanochat in MLX