VQ VAE Timbre Transfer Demo
Transfer timbre from one audio to another
Fixed fork of the original audio sr!
Enhance audio quality with AudioSR
Higgs Audio Demo
MegaTTS 3 but with voice cloning!
Demo space for Mistral latest speech models
Search audio for relevant chunks
Track and visualize points in a video
Generate audio for videos using captions and descriptions
Part-level image-to-3D generation.
Next-Gen High-Resolution 3D Model Generation
Audio-Driven Multi-Person Conversational Video Generation
State-of-the-art target speech extractor
Stylized TTS โ design voice, accent, and emotion your way
Generate text responses to your queries
Generate customized speech from text using a reference audio