Voice assistants

Moshi / Hibiki

A voice assistant that listens and speaks at the same time, with no delay for recognition and synthesis. Hibiki does simultaneous speech-to-speech translation between several European languages.

Developer
Kyutai, France
First release
Sep 2024
Latest release
Feb 2026
Sizes
2B – 7B
License
Commercial use with conditionsMoshi and Hibiki are CC-BY-4.0; Hibiki-Zero and some newer fine-tuned versions are non-commercial (CC BY-NC)
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Customer support, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Real-time voice conversation partner
  • Simultaneous speech translation
  • Zero-latency voice interfaces

Where it is used

Voice botsInternational meetingsProduct development

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
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Hibiki-Zero 3B
  2. Hibiki 2B
  3. Moshi (Moshiko, Moshika)

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 Moshi / Hibiki be used in a commercial project?

With conditions. License: Moshi and Hibiki are CC-BY-4.0; Hibiki-Zero and some newer fine-tuned versions are non-commercial (CC BY-NC). Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Moshi / Hibiki 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 Moshi / Hibiki support Russian?

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

Where can I download Moshi / Hibiki and what does it cost?

The Moshi / Hibiki 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 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.

DetailsVoice assistantsMiniCPM-oOpenBMB (ModelBest, Tsinghua University) · ChinaCommercial use allowed

A small model that sees, hears and replies by voice in real time, and can clone a voice. Voice dialogue in English and Chinese, text in 30+ languages.

DetailsVoice assistantsSeamlessM4T / SeamlessMeta · USANon-commercial only

Speech and text translation across roughly a hundred languages, including Russian: speech to text, speech to speech, and streaming translation that keeps intonation.

Details

Source: huggingface.co/kyutai/hibiki-zero-3b-pytorch-bf16. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.