EnCodec
High-fidelity neural audio codec by Meta for audio compression and tokenization.
About
EnCodec by Meta Research is a high-fidelity neural audio codec that compresses audio to very low bitrates while preserving quality, offering 24 kHz and 48 kHz models at several target bitrates. It also ships pretrained language models that further compress the representation, and it serves as the audio tokenizer behind generative models such as MusicGen. It runs on CPU. Released under the MIT license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Music & Audio Generation
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- MIT
- Added
- Apr 3, 2026
Related Tools
Audio generation framework by Meta including MusicGen for text-to-music.
Latent diffusion model for text-to-audio, music, and speech generation.
Audio super-resolution model for upsampling audio to higher sample rates.
State-of-the-art music source separation model by Meta for splitting tracks.
Fast music generation model producing full songs with lyrics in seconds.
PyTorch library for deep learning research on audio generation including MusicGen and AudioGen.