All tasks / Models
MOSS-TTS v1.5
Open-weights 8B text-to-speech model from OpenMOSS for long-form and multi-speaker speech.
- OpenMOSS (Fudan University / MOSI)
- Open weights
- Released 25 May 2026
Where it ranks
- –Text to speechModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- OpenMOSS (Fudan University / MOSI)
- Family
- MOSS-TTS
- Released
- 25 May 2026
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 8.49B
- GPU memory to run locally
- ~19 GB (Derived: about 8.49B parameters is roughly 17.0 GB of bf16 weights plus runtime overhead; not an official requirement.)
- Access
- Free (open weights)
- Last verified
- 19 Oct 2026
Benchmark results
No public benchmark results recorded yet.
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.