Stars
A curated list of awesome skills, hooks, slash-commands, agent orchestrators, applications, and plugins for Claude Code by Anthropic
ResoNova is a transparent, fully-customizable AI pipeline that balances, compresses and limits electronic tracks to industry loudness specs—powered by LibROSA & TensorFlow.
A set of ready to use scientific skills for Claude
Audio Codec Speech processing Universal PERformance Benchmark
FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music generation et.al.
Pitch-shifting, time-stretching, and vocoding of speech with Controllable LPCNet (CLPCNet)
The first Large Audio Language Model that enables native in-depth thinking, which is trained on large-scale audio Chain-of-Thought data.
[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.
An Open-source Streaming High-fidelity Neural Audio Codec
Real-time binaural target sound extraction model.
A deep neural network architecture for low-latency audio processing
Join the community on Discord for more discussions around Neutone! https://discord.gg/VHSMzb8Wqp
The collection of awesome papers on alignment of diffusion models.
Dataset of dry/wet pairs for audio effects research
Lets make video diffusion practical!
🎛️ Compact GUI for fine-tuning parameters and monitoring value changes
Visualizer for neural network, deep learning and machine learning models
Residual Quantization with Implicit Neural Codebooks
STOI loss functions in PyTorch (mirror of https://github.com/mpariente/pytorch_stoi)
a MUSHRA compliant web audio API based experiment software
YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Easily train a good VC model with voice data <= 10 mins!
zero-shot voice conversion & singing voice conversion, with real-time support