Music Generation
Services that make songs and instrumentals on your own GPU, for the chat's background music, songs about the story, and the Music Playground.
Music Generation (the MusicGen service type) makes a whole track from a style description and, for a song, tagged lyrics. A track is made, then sent back as a file. Nothing streams while it plays.
Where it is used
/musicand/songin a chat: background music that fits the scene, or a song about the story, sung and attached to the chat.- The Music Playground: write a song, make takes, repaint, remix and mix them.
- The chat's Gallery, which keeps the chat's tracks to play again or download.
- Service Tests.
The chat loads the service on its first track and unloads it once the track is done, unless another one is queued. This way the music model does not hold video memory the rest of the chat needs.
Add one
- Add Modules → Services, pick a music module and Install, then follow the install steps. All three are experimental and can only be installed by an administrator.
- Pick a preset or model, on the Music Generation row of the Configuration page's Music tab. ACE-Step and LeVo install a few presets, by model size. audio.cpp picks its model in the install's Models step.
- In a chat,
/musicand/songuse the chat's music generation service, and its summarization model to write the style and lyrics.
Each module's Writing Instructions tell the language model how to write the style and lyrics for that model.
Modules
All run locally and download their models from Hugging Face. ACE-Step and LeVo run in Voxta's own Python, audio.cpp without Python on a CUDA GPU.
ACE-Step
ACE-Step 1.5 (MIT). Fast: a song in seconds. Vocals in 50+ languages, repaint, remix and LoRAs.
audio.cpp Music
ACE-Step 1.5 in one GGUF file, without Python. Generate, repaint and remix. CUDA only.
LeVo 2
Tencent's SongGeneration 2. Vocals and backing as separate stems. Non-commercial license.
| ACE-Step | audio.cpp Music | LeVo 2 | |
|---|---|---|---|
| License | MIT | MIT | Academic, research and education use only |
| Speed | Seconds per song on a recent GPU | Seconds per song on a recent GPU | About a minute per minute of song |
| Video memory | ~5 to ~17 GB, by planner | ~8 GB, ~13 GB to repaint or remix | ~12 GB medium, ~22 GB large |
| Length | 10–600 s, or let the model choose | 10–600 s | Follows the lyrics |
| Vocal languages | 50+ | 50+ | English, Chinese, Spanish, Japanese |
| Takes per request | Up to 4, in one pass | Up to 4, one after the other | Up to 4, one after the other |
| Stems | No | No | Vocals and backing |
| Repaint, extend, remix | Yes | Repaint and remix | No |
| BPM, key, beats per bar | Yes | Yes | No |
| LoRAs | Yes | No | No |