facebookresearch/encodec

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

4041 stars · 360 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

EnCodec is a deep learning based neural audio codec from Meta AI that compresses mono 24 kHz and stereo 48 kHz audio to bitrates from 1.5 to 24 kbps with high fidelity. It provides pre-trained encoder/decoder models with residual vector quantization, plus optional entropy coding via a small language model for up to 40% further compression.

Use cases

• compress audio with a neural codec
• get audio tokens for training audio language models
• encode music at low bitrates with high quality
• use EnCodec through Hugging Face Transformers
• build text-to-audio or music generation pipelines needing discrete audio tokens

When to choose

• you need state-of-the-art neural audio compression at low bitrates
• you need discrete audio token representations for generative audio models
• you want pre-trained 24 kHz mono or 48 kHz stereo models

When to avoid

• you need a production codec for real-time communication (use Opus instead)
• you require a permissive license for commercial use of the PyPI weights (CC BY-NC)
• you need active development or frequent updates

Facets

library · maturity maintenance

audio-processing machine-learning deep-learning compression machine-learning deep-learning python cross-platform neural-codec audio-compression vector-quantization pretrained-models research audio gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="facebookresearch/encodec")