All tasks / Models
Fun-CosyVoice3-0.5B-2512
Open-weights multilingual zero-shot text-to-speech model from Alibaba's FunAudioLLM team.
- Alibaba (FunAudioLLM)
- Open weights
- Released 11 Dec 2025
Where it ranks
- –Text to speechModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- Alibaba (FunAudioLLM)
- Family
- CosyVoice
- Released
- 11 Dec 2025
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 0.5B
- GPU memory to run locally
- ~2 GB (Derived: about 0.5B parameters is roughly 1 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.