AIMADANG

Audio-Omni

Work

Back
Public profileAI modelSource · Hugging Face

AI model · HKUSTAudio by · any-to-any

Field
audio_omnitext-to-audiotext-to-speechaudio-editingmusicspeechdiffusionmultimodalaudio-generationany-to-anyarxiv:2604.10708license:cc-by-nc-4.0
Tools used
any-to-any
First collected
30 Jul 2026
Last checked
30 Jul 2026

Request a change to this item

You can take over this profile after verification and edit it yourself, or ask for a change, hiding or deletion. Nothing happens automatically — an admin checks against the original first.

Log in Log in to request a takeover. Change and deletion requests work without logging in.