MegaTTS 3 Voice Cloning
MegaTTS 3 but with voice cloning!
None defined yet.
MegaTTS 3 but with voice cloning!
Upgraded to v1.0!
Text-to-music generation with melody conditioning
Separate music into vocal and instrumental stems
Audio production style transfer (EQ, compression)
LA-2A compressor/limiter emulation with a neural TCN
Synthesize piano audio from MIDI with 10 learned timbres
Synthesize guitar audio from MIDI using DDSP
Meta AudioSeal Watermarking
Extract timestamped chords from music on CPU
Compact English text-to-speech on CPU
Score audio content and production aesthetics on CPU
Contrastive Audio-Text Model
Demonstrate all HARP UI controls with pass‑through audio/MIDI
Convert MIDI files to high‑quality audio
Edit, inpaint, and continue music audio from text prompts
Generate audio variations and extensions with controllable masks
Generate spoken audio from text with optional voice cloning
Piano Cover Generation
Demucs stem separator wrapped in pyharp
Upscale audio to high‑quality 48 kHz
Convert audio to MIDI or text transcription
Single-channel Blind Unsupervised Dereverberation
Generate a full song from lyrics, description, and optional voice