Makes full songs with vocals from lyrics. Made by ACE Studio.
Use the ACE-Step app
ACE-Step 1.5 is a speech or music model from ACE Studio. Makes full songs with vocals from lyrics. Running it locally needs about 12 GB of memory.
The least memory you need, by Apple chip:
Runs well on: RTX 3090, RTX 4060 Ti 16GB, RTX 4070 Ti Super, RTX 4080 / 4080 Super, RTX 4090, RTX 5060 Ti 16GB, RTX 5070 Ti, RTX 5080, RTX 5090, Radeon RX 7800 XT, Radeon RX 9070 XT, Radeon RX 7900 XTX. Runs slowly with help from system RAM on: RTX 3060 12GB, RTX 3080 10GB, RTX 4070 / 4070 Super, RTX 5070.
As an Amazon Associate I earn from qualifying purchases.
About 12 GB of video memory or unified memory. On a Mac, the smallest configuration that runs it is 16 GB.
A 16 GB M4 Mac runs it runs well, about about 3 min per 1 minute song. An 8 GB M1 Mac cannot run it.
Yes, the model is free to download. Its licence is listed as Apache 2.0. That is a permissive licence that allows commercial use.
Use the ACE-Step app.
| Machine | Verdict | Speed |
|---|---|---|
| M1 8GB | Too big | |
| M4 16GB | Runs well | about 3 min |
| M4 32GB | Runs well | about 3 min |
| M4 Pro 48GB | Runs great | about 1 min |
| M4 Max 128GB | Runs great | about 47 s |
| M3 Ultra 512GB | Runs great | about 47 s |
| RTX 4060 | Too big | |
| RTX 4070/4070 Super | Slow | about 3 min |
| RTX 5070 Ti | Runs great | about 47 s |
| RTX 3090 | Runs great | about 1 min |
| RTX 5090 | Runs great | about 25 s |
| Ryzen AI Max+ 395 128GB | Runs great | about 1 min |
| CPU only 32GB | Runs well | about 25 min |