Ereboas/MagiCodec
A single-layer, streaming codec model providing SOTA audio quality and discrete tokens designed for superior downstream modelability.
MagiCodec helps developers working with audio data to convert raw audio files into discrete tokens and reconstruct high-quality audio from these tokens. It processes audio inputs to produce a compressed, discrete representation, and can also generate audio outputs from these codes. This is useful for anyone building or researching systems that need to process, generate, or transmit audio efficiently, such as those in AI-powered voice assistants or music generation.
113 stars. No commits in the last 6 months.
Use this if you are a developer building audio-native AI models and need a lightweight, high-fidelity audio codec that provides both excellent reconstruction quality and easily modelable discrete tokens.
Not ideal if you are an end-user simply looking to play or convert audio files without needing to work with discrete audio tokens or integrate with AI models.
Stars
113
Forks
7
Language
Python
License
MIT
Category
Last pushed
Jun 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Ereboas/MagiCodec"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ZHZisZZ/dllm
dLLM: Simple Diffusion Language Modeling
pengzhangzhi/Open-dLLM
Open diffusion language model for code generation — releasing pretraining, evaluation,...
EnnengYang/Awesome-Model-Merging-Methods-Theories-Applications
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM...
THUDM/LongWriter
[ICLR 2025] LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
AIoT-MLSys-Lab/SVD-LLM
[ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2