Voice assistants

Samsone

Tiny audio-understanding models for smartphones: they listen to speech, music and ambient sounds and answer in text - describing a recording and answering questions about it. They run on the device itself; prompts and answers are in English - no other languages are present in the training data.

Developer
Samsung, South Korea
First release
Sep 2026
Latest release
Sep 2026
Sizes
99M – 356M
License
Non-commercial onlyNo license is stated for the weights or the code in the repository - there is no LICENSE file and no one has granted commercial rights; terms must be clarified with Samsung (the CC BY 4.0 license applies only to the arXiv paper)
Russian
Not supported
Running
On your own serverAlso runs without a GPU
Industries
Media and production, Manufacturing and logistics, Science and research
Deploy on your server GitHub

What it does

  • Describing an audio recording in words
  • Answering questions about a sound
  • Identifying the type of sound and the setting
  • Processing audio on the device without sending it to the cloud

Where it is used

Mobile appsMedia and audio productionManufacturing and equipment monitoring

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. Samsone-99M / 134M / 356M

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.
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 Samsone be used in a commercial project?

No. License: No license is stated for the weights or the code in the repository - there is no LICENSE file and no one has granted commercial rights; terms must be clarified with Samsung (the CC BY 4.0 license applies only to the arXiv paper). A commercial product needs a different model or a separate agreement with the rights holder.

What hardware does Samsone 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 Samsone support Russian?

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

Where can I download Samsone and what does it cost?

The Samsone 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

Voice assistantsAudio FlamingoNVIDIA · USANon-commercial only

Models that listen to speech, sounds and music and answer questions about them. Audio Flamingo Next handles recordings up to 30 minutes. Research use only.

DetailsVoice assistantsKimi-AudioMoonshot AI · ChinaCommercial use allowed

A general-purpose audio model: speech recognition, answering questions about sounds, detecting emotions and voice dialogue. Trained on 13 million hours of audio; languages are English and Chinese.

DetailsVoice assistantsQwen OmniAlibaba (Qwen) · ChinaCommercial use allowed

Models that understand text, images, audio and video and reply by voice in real time. Qwen3-Omni speaks 10 languages, including Russian.

Details

Source: github.com/SamsungLabs/samsone/releases/tag/v1.0.0. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.