MegaTTS 3 Voice Cloning
MegaTTS 3 but with voice cloning!
None defined yet.
MegaTTS 3 but with voice cloning!
Upgraded to v1.0!
Generate music from lyrics and prompts
Transcribe audio files into MIDI tracks
Removes room reverb from a speech recording
Fill missing parts in an audio clip using diffusion model
Detect beats and downbeats in audio
Lightweight audio classification/sound event detection model
Separate music into vocals, drums, bass, and other stems
Separate a song into vocal and instrument stems
Detect AI GenMusic via a Fusion Segment Transformer
Generate spoken audio from text
Generate realistic speech and sounds from text
Bass/Drums Accompaniment Generation
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 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