OpenMOSS / MOSI.AI · Apache 2.0
MOSS-TTS-Nano
A 100M voice model for 20 languages that its authors say runs on a 4-core CPU.
How much memory it needs
Memory to run each model, from its model card or the size of its files. Smaller versions trade some quality for less memory.
| Model | Version | Needs | Business use |
|---|---|---|---|
| MOSS-TTS-Nano | Full | 0.3 GB | Allowed |
Which computers run it
The best model in this group for each machine.
| Computer | Best version | Fit |
|---|---|---|
| Laptop or PC, no graphics card, 32 GB | MOSS-TTS-Nano Full | Runs great |
| RTX 4060 · 8 GB | MOSS-TTS-Nano Full | Runs great |
| RTX 3060 · 12 GB | MOSS-TTS-Nano Full | Runs great |
| RTX 5060 Ti · 16 GB | MOSS-TTS-Nano Full | Runs great |
| RTX 4090 · 24 GB | MOSS-TTS-Nano Full | Runs great |
| RTX 5090 · 32 GB | MOSS-TTS-Nano Full | Runs great |
| Mac with M4 · 16 GB | MOSS-TTS-Nano Full | Runs great |
| Mac with M4 Pro · 48 GB | MOSS-TTS-Nano Full | Runs great |
| Mac with M5 Max · 128 GB | MOSS-TTS-Nano Full | Runs great |
| Ryzen AI Max+ 395 · 128 GB | MOSS-TTS-Nano Full | Runs great |
| DGX Spark · 128 GB | MOSS-TTS-Nano Full | Runs great |
| RTX PRO 6000 · 96 GB | MOSS-TTS-Nano Full | Runs great |
| Mac Studio with M5 Ultra · 256 GB | MOSS-TTS-Nano Full | Runs great |
| Mac Studio with M3 Ultra · 512 GB | MOSS-TTS-Nano Full | Runs great |
What it is good and bad at
Good at
- Runs on CPU
- Streaming
Not good at
- Small model: less natural than bigger ones
Start it
- MOSS-TTS-Nano: runs in MOSS-TTS-Nano (PyTorch / ONNX Runtime) (also mlx-audio). Model card