Models
descript-audio-codec
descriptinc/descript-audio-codec
Descript's neural audio codec model, released with weights plus training and inference scripts. It compresses 44.1 kHz audio at very low bitrates while preserving fidelity.
Topics
Related projects
Confucius4-TTS852Confucius4-TTS is an open multilingual, cross-lingual zero-shot text-to-speech model that clones a speaker's voice across 14 languages while preserving emotion and identity.
vocal-remover1.8kA deep-learning vocal separation tool that splits songs into vocals and instrumental tracks using pretrained PyTorch models, with optional scripts for training your own separator.
voxcpm41.3kAn open-source 2B tokenizer-free multilingual TTS model for voice design, controllable cloning, and studio-quality synthesis.
MMAudio2.3kMMAudio is a CVPR 2025 model for high-quality video-to-audio synthesis, generating synchronized sound from video and text with released checkpoints and code.
RAVE1.8kThe official implementation of RAVE, a realtime neural audio variational autoencoder. It includes training, export, and realtime inference tools for timbre transfer and music generation.
ultralytics63.3kA Python library for YOLO object detection, segmentation, pose, and tracking with training and deployment tools.