Text to speech

OmniVoice

Speech synthesis with voice cloning from a short sample in 646 languages, including Russian and languages of Russia's peoples. A voice can be described in words. Weights are for non-commercial use only.

Developer
k2-fsa (Next-gen Kaldi), China
First release
Mar 2026
Latest release
Mar 2026
Sizes
0.6B
License
Non-commercial onlyCode Apache 2.0, weights CC BY-NC (non-commercial because of the training data)
Russian
Supported
Ready-made builds
MLX (Apple)
Running
On your own serverNeeds a GPU
Industries
Media and production, Education, Science and research
Deploy on your server Hugging Face GitHub

What it does

  • Voiceover in rare languages
  • Voice cloning from a sample
  • Research and prototypes of multilingual voiceover

Where it is used

ResearchEducationMedia (non-commercial projects)

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. OmniVoice

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can OmniVoice be used in a commercial project?

No. License: Code Apache 2.0, weights CC BY-NC (non-commercial because of the training data). A commercial product needs a different model or a separate agreement with the rights holder.

What hardware does OmniVoice need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does OmniVoice support Russian?

Yes, Russian is listed on the model card.

Where can I download OmniVoice and what does it cost?

The OmniVoice weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Text to speechF5-TTSShanghai Jiao Tong University and partners · ChinaNon-commercial only

A voice cloning model that needs only a few seconds of a sample, in English and Chinese. The community has released many fine-tuned versions for other languages, including Russian.

DetailsText to speechCosyVoice / Fun-CosyVoiceAlibaba (Tongyi, FunAudioLLM) · ChinaCommercial use allowed

Speech synthesis with voice cloning from a short sample and streaming output for live dialogue. Version 3 supports 9 languages, including Russian.

DetailsText to speechFish Speech / OpenAudioFish Audio · USA / ChinaNon-commercial only

Speech synthesis with voice cloning and emotion control in 80+ languages, including Russian. Quality is close to paid services, but the weights are for research only.

Details

Source: github.com/k2-fsa/OmniVoice. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.