LLM Comparison
OmniVoice vs VoxCPM
Side-by-side specs, pricing & capabilities · Updated October 2026
Add to comparison
2/6 modelsSame tier:
| Organization | ||
| OpenTools Score | ||
| Family | OmniVoice | VoxCPM |
| Status | Current | Current |
| Release Date | Mar 2026 | Apr 2026 |
| Context Window | — | 4K tokens |
| Input Price | — | — |
| Output Price | — | — |
| Pricing Notes | Open-source model repository; hosted API pricing is not listed in the GitHub README. | Open-source Apache-2.0 code and model weights; self-hosting compute costs apply. |
| Capabilities | text-to-speechvoice-cloningmultilingual-audiovoice-design | text-to-speechmultilingualvoice-cloningvoice-designstreaming-inference |
| Training Cutoff | Not publicly specified | VoxCPM2 trained on over 2 million hours of multilingual speech |
| API Identifier | k2-fsa/OmniVoice | openbmb/VoxCPM2 |
| Benchmarks | ||
| Real-time factor (best-case author claim) | 0.025official-github-readme | — |
| View OmniVoice | View VoxCPM | |
K2-FSA
OmniVoice
OmniVoice is an open-source massively multilingual zero-shot text-to-speech and voice-cloning model from K2-FSA. The project README says it supports more than 600 languages, voice design controls, and fast inference with real-time factor as low as 0.025.
OpenBMB
VoxCPM
VoxCPM is OpenBMB’s tokenizer-free text-to-speech model family. VoxCPM2 is a 2B-parameter release for multilingual speech generation, voice design, and controllable voice cloning.
More Comparisons
Looking for more AI models?
Browse All LLMs