MegaTTS 3 Voice Cloning
MegaTTS 3 but with voice cloning!
None defined yet.
MegaTTS 3 but with voice cloning!
Upgraded to v1.0!
Restore degraded speech audio with VoiceFixer
Separate any instrument from a mix using an audio query
Text-to-music generation with chord and rhythm control
Piano Cover Generation
Generate music from a text description (optional melody)
Generate a short sound effect from text
Generate music from text and optional melody
Convert piano MIDI to jazz or classical style
Diffusion-based restoration for historical recordings
Automatic Mixing Model based on Fx-Normalization
Lightweight audio classification/sound event detection model
Unified Model For SpeechGen, SoundGen, and In-Scene-Editing
Automatic Mixing via Generative Model of Effect Embeddings
Transfer audio to a different instrument timbre
Single-channel Blind Unsupervised Dereverberation
Generate singing in a reference voice from a melody
Contrastive Audio-Text Model
Enhance audio with naturalβlanguage instructions
Adjust audio levels and apply effects to your sound file
Separate Anything You Describe