StepFun and ACE Studio launch StepAudio 3 Music, a foundation model for song generation
CodeByPoonam · x · 2026-09-28
StepFun, together with ACE Studio, has released StepAudio 3 Music, its first music generation foundation model that turns a prompt plus lyrics into a complete song. Users can specify genre, mood, vocal character, instruments, key, BPM, and arrangement. One model covers four workflows: song generation, instrumental generation, music cover, and vocal-to-song arrangement.
More from Multimodal
- Neofauve-style AI render of Lady Gaga shared on style-transfer platform — OVolosin82152 · 2026-09-28
- Viral Prompt Share: Stitched Stop-Motion World of Felt and Fabric — azed_ai · 2026-09-28
- Blogger slams MiniMax H3 portraits for oily skin and creepy 'zombie face' output — huangyun_122 · 2026-09-28
- One Midjourney --sref code nails 1970s Kodak disco style, full params shared — michaelrabone · 2026-09-28
- Two prompts: Claude Opus 5.5 codes, renders and self-checks a full 1080p promo video — sujingshen · 2026-09-28
- ComfyUI question: can premade Blender depth maps skip the ControlNet preprocessor? — DiddlyDinq · 2026-09-28