lucadellalib/focalcodec
A low-bitrate single-codebook 16 / 24 kHz speech codec based on focal modulation
This project helps you shrink audio files containing human speech while keeping the sound clear. It takes standard audio recordings, compresses them significantly into a smaller data format, and can then rebuild the audio from this compressed data. This is useful for anyone working with spoken audio who needs to save storage space or transmit files over limited bandwidth.
152 stars.
Use this if you need to efficiently store or transmit speech audio at very low bitrates, especially for applications requiring real-time processing or reduced file sizes.
Not ideal if you need to compress music or complex soundscapes, as this codec is specifically optimized for human speech.
Stars
152
Forks
15
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Nov 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/lucadellalib/focalcodec"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
descriptinc/descript-audio-codec
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz...
drethage/speech-denoising-wavenet
A neural network for end-to-end speech denoising
YuanGongND/ast
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
iver56/torch-audiomentations
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
lmnt-com/wavegrad
A fast, high-quality neural vocoder.