EnCodec
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Meta AI
- Organisation type
- Industry
- Country
- United States of America
- Published
- 24 October 2022
- Authors
- Alexandre Défossez, Jade Copet, Gabriel Synnaeve, Yossi Adi
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Audio
- Task
- Audio generation
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Training data
- tokens
- Epochs
- 300
~17k hours total, per Table A.1
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA A100
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Open — downloadable
- Model access
- Open weights (non-commercial)
- Training code
- Open source
MIT for repo in general, non commercial weights. Dataset is in repo. https://github.com/facebookresearch/audiocraft/blob/main/docs/ENCODEC.md
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- SOTA improvement
- Record confidence
- Unknown
- Citations
- 1,151
" Finally, our best model, EnCodec, reaches state-of-the-art scores for speech and for music at 1.5, 3, 6, 12 kbps at 24 kHz, and at 6, 12, and 24 kbps for 48 kHz with stereo channels."
Sources
Where this record came from and when it was last checked.
- Reference
- High Fidelity Neural Audio Compression
- Last updated
- 25 May 2026
What the numbers mean
Background
EnCodec was published by Meta AI, in United States of America, in October 2022. It comes out of industry.
It works in Audio, and is recorded as doing audio generation.
Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.
What went into building it
The reason it appears in this catalogue at all is sOTA improvement.
Answers
EnCodec — common questions
What is EnCodec used for?
EnCodec works in Audio, and is recorded as handling audio generation. These are the areas it was designed around; they describe intent rather than a hard boundary.
Where can I download EnCodec?
The weights for EnCodec are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
What GPU do I need to run EnCodec?
We cannot say. EnCodec has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
Is EnCodec open source?
Its weights are published, so EnCodec can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
How many parameters does EnCodec have?
No parameter count has been published for EnCodec, which is why no memory or speed figure appears on this page.
Who created EnCodec?
EnCodec was published by Meta AI, based in United States of America, categorised as industry.
When was EnCodec released?
EnCodec was published in October 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.