Qwen · Alibaba/Music
Qwen Enters Music Generation With Qwen-Music
Alibaba's Qwen team debuts a text-to-song model that produces high-fidelity tracks complete with vocals.
Category · audio
Latest Music models
Open models that generate music and audio from text or melody — instrumentals, sound design, and full tracks, with weights you can download and tune.
5 releases
MuScriptor/Music
MuScriptor Large Turns Real Music Into MIDI
A new open model tackles multi-instrument transcription of real audio mixes, converting songs directly into editable MIDI.
Stability AI/Music
Stability AI's Demon brings real-time music diffusion to local GPUs
An open-source engine generates audio on the fly at 25Hz, no cloud required.
HKUSTAudio/Any-to-Any
HKUST Releases Audio-Omni, a Unified Audio Model
The new diffusion-based model handles speech, music, and general audio tasks like conversion and editing within a single, versatile framework.
Soul AILab/Music
Soul-AILab Releases Zero-Shot Singing Voice Model
The new model, SoulX-Singer, can replicate a singing voice from a short audio sample and supports both English and Chinese under a permissive license.
