Models
MMAudio
hkchengrex/MMAudio
MMAudio is a CVPR 2025 model for high-quality video-to-audio synthesis, generating synchronized sound from video and text with released checkpoints and code.
Topics
Related projects
descript-audio-codec1.9kDescript'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.
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.
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.
opencv91.5kThe open-source computer vision library offering image processing and vision algorithms for apps and research.
ai-engineering-from-scratch77.1kAn open-source AI engineering course with hundreds of lessons, labs, and projects built from scratch.
mediapipe37.7kA cross-platform framework and task libraries for on-device ML perception across vision, text, and audio on mobile, web, and edge.