Speech to text

Moonshine

Very small and fast speech recognition models for phones, tablets and embedded devices. Version 2 streams, producing text while the person is still speaking.

Developer
Moonshine AI (Useful Sensors), USA
First release
Oct 2024
Latest release
Aug 2026
Sizes
27M – 245M
License
Commercial use allowedMIT; exception: older non-streaming models for languages other than English (non-commercial Moonshine Community License)
Russian
Not supported
Ready-made builds
GGUF
Running
On your own serverAlso runs without a GPU
Industries
Software development, Media and production
Deploy on your server Hugging Face GitHub

What it does

  • Voice control of devices
  • Offline recognition on a phone
  • Live subtitles
  • Voice interfaces in apps

Where it is used

Device makersMobile appsSmart homeKiosks and terminals

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. Потоковые модели для других языков
  2. Moonshine v2 (потоковая)
  3. Moonshine Tiny / Base

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 Moonshine be used in a commercial project?

Yes. License: MIT; exception: older non-streaming models for languages other than English (non-commercial Moonshine Community License). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Moonshine 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 Moonshine support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download Moonshine and what does it cost?

The Moonshine 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

Speech 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.

DetailsSpeech to textNVIDIA Parakeet / Canary / Nemotron SpeechNVIDIA · USACommercial use with conditions

Fast NVIDIA speech recognition models, including streaming ones for real-time use. Parakeet TDT v3 and Nemotron 3.5 ASR understand Russian.

Details

Source: arxiv.org/abs/2602.12241. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.