Speech to textText to speech

Vosk (русские модели)

Offline Russian speech recognition that runs even on a Raspberry Pi or a phone, without internet. Streaming models for live audio and simple Russian speech synthesis, Vosk TTS, are available.

Developer
Alpha Cephei, Russia
First release
Feb 2023
Latest release
Sep 2025
Sizes
about 45 MB – 1.8 GB
License
Commercial use allowedApache 2.0
Russian
Supported
Running
On your own serverAlso runs without a GPU
Industries
Customer support, Media and production, Documents and accounting
Deploy on your server Hugging Face GitHub

What it does

  • Transcribing Russian calls and recordings without the cloud
  • Voice control in apps and kiosks
  • Low-latency streaming speech recognition
  • Simple Russian text-to-speech

Where it is used

Call centersEmbedded devices and kiosksMobile appsCompanies with a closed IT environment

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. Streaming ru 0.56
  2. vosk-model-ru-0.54 (Zipformer2)
  3. Vosk TTS на StableTTS
  4. Vosk TTS ru multi
  5. Small Streaming (Zipformer)
  6. vosk-model-ru-0.42

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.

Frequently asked questions

Can Vosk (русские модели) be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Vosk (русские модели) need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Vosk (русские модели) support Russian?

Yes, Russian is listed on the model card.

Where can I download Vosk (русские модели) and what does it cost?

The Vosk (русские модели) 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.

Comparisons

Similar models

Speech to textGigaAMSber · RussiaCommercial use allowed

Sber's models for Russian speech recognition, among the most accurate for Russian. Includes emotion recognition, v3 with punctuation, and a multilingual version (Russian, Kazakh, Kyrgyz, Uzbek).

DetailsSpeech to textT-oneT-Bank · RussiaCommercial use allowed

A compact T-Bank streaming model for recognizing Russian speech in phone calls. Works in real time even without a GPU.

DetailsSpeech to textWhisperOpenAI · USACommercial use allowed

Speech recognition in 99 languages, including Russian. The de facto standard for transcribing calls and meetings. Hugging Face's faster Distil-Whisper is English only.

Details

Source: huggingface.co/alphacep/vosk-model-streaming-ru. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.