Open-weights model producing full songs up to five minutes from lyrics with section tags and a style description
MiniMax Music 3 (open weights) is listed under AI Music & Audio, in the Content & Media Generation category on Flocci AI Tools. Open-weights model producing full songs up to five minutes from lyrics with section tags and a style description. It is free, with no paid plan attached, and it lives at huggingface.co.
MiniMax Music 3 (open weights) is listed as fully free — there is no paid tier attached to it in the catalog. That makes it one of the 397 entries on Flocci AI Tools with no upgrade path built in.
MiniMax Music 3 (open weights) needs to be installed or self-hosted — it doesn't run in a browser tab. It is available on self-hosting.
MiniMax Music 3 (open weights) does 3 things the catalog singles out: Open-weights model producing full songs up to five minutes from lyrics with section tags and a style description; 8b global llm plus 0.6b local llm with flow-matching synthesis, 32 khz stereo wav; runs in comfyui, diffusers or sglang-omni; hosted version at minimax.io/audio/music.
Podcastfy is the closest free alternative: it sits in the same AI Music & Audio sub-category and is free. Riffusion, Treblo (formerly Sonauto) and YuE also start free. The full list is on the alternatives page.
See the full list →