vampnet
Remixes and extends audio by masked generation
None defined yet.
Remixes and extends audio by masked generation
Restyle piano music by rhythm and polyphony
Generative automatic mixing of 2-6 dry stems
Render expressive piano performance from a score
Beat tracking in a dual-interpreter Docker Space
Magenta DDSP timbre transfer and synthesis
Zero-shot TTS with voice and emotion references
Transfer a reference recording's production style
Four-step text-to-audio sound effect generation
Studio effects chain via Spotify Pedalboard
ITU-R BS.1770-4 loudness and range metering
Restores degraded speech of any kind
Edit music with source and target descriptions
Splits audio into harmonic and percussive parts
Timestamped chord sequence via Chordino on CPU
Extract any instrument using an audio query
SpeechBrain Tacotron2 TTS on LJSpeech
Generates a piano cover from a pop song clip
Restyle, inpaint, or continue music from a prompt
Zero-shot speech and singing conversion and TTS
Splits a drum mix into five individual drum stems
Detects AI-generated music from structure and MERT
Text-to-music generation with melody conditioning
Text-to-music with chord and rhythm control