[Interspeech 2025] DualCodec: A Low-Frame-Rate, Semantically-Enhanced Neural Audio Codec

[ICLR2026] FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates

Neural Audio Codecs implemented in C# - DAC, SNAC, Encodec, Dia

Unofficial fairseq-free PyTorch implementation of UTMOS (v1, 2022), matching the original system.

Causal zero-shot voice conversion at 44.1kHz.

Implementation of the Descript Audio Codec in MLX

Author's code of "Speaker anonymization using neural audio codec language models" (ICASSP 2024).

Unofficial PyTorch implementation of Higgs Audio V2 Tokenizer with HuBERT semantic features. Complete training pipeline for semantic-acoustic audio tokenization with 960x downsampling and 8-layer RVQ.

A minimal neural audio codec 🔊

Neural audio codec inference in C/C++

A lightweight neural audio codec.

Unofficial fairseq-free PyTorch implementation of SCOREQ (2024), matching the original system.

Transfer sonic characteristics from reference sounds to a source audio using Music2Latent embeddings

Open research toward end-to-end spoken dialogue systems. Ships SoviaMate-Codec — a neural audio codec for LLM integration with ASR-constrained encoding, enhancement training, and zero-shot speaker adaptation.

"Minimal" implementation of xcodec2

Neural audio codec and tokenizer for audio language models — SEANet encoder with residual vector quantization in PyTorch

Pytorch implementation of a Moshi-inspired audio LM based on multiple backbones, inlcuding Qwen and a transformer decoder.

Browser voice-QR and push-to-talk app using neural speech compression, WebAssembly, local model caching, and a real-time edge relay.

AI-powered ultra-low bitrate audio codec CLI built on SNAC — Compress audio at 0.98-2.6 kbps with near-original quality (392:1 ratio vs WAV)

APU-Codec: Neural audio codec from source, optimized for AMD APU tri-processor inference (NPU encoder, GPU decoder)