All tasks / Models
OmniVoice
Open-weights multilingual zero-shot text-to-speech model with voice cloning from the k2-fsa project.
- k2-fsa (Next-gen Kaldi)
- Open weights
- Released 30 Mar 2026
Where it ranks
- –Text to speechModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- k2-fsa (Next-gen Kaldi)
- Family
- OmniVoice
- Released
- 30 Mar 2026
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 0.61B
- GPU memory to run locally
- ~2 GB (Derived: about 0.61B parameters is roughly 1.2 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.