Text to speech

Dia

A model that voices entire two-person dialogues with laughter, sighs and pauses. English only.

Developer
Nari Labs, South Korea
First release
Apr 2025
Latest release
Nov 2025
Sizes
1B – 2B
License
Commercial use allowedApache 2.0
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Media and production, Marketing and content, Education
Deploy on your server Hugging Face GitHub

What it does

  • Voicing dialogues and podcasts
  • Ads with natural speech
  • Training role-plays

Where it is used

Media and podcastsMarketingOnline learning

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. Dia2 1B и 2B
  2. Dia 1.6B

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 Dia 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 Dia 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 Dia support Russian?

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

Where can I download Dia and what does it cost?

The Dia 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 textVibeVoiceMicrosoft · USACommercial use allowed

Microsoft speech models: long multi-voice dialogue synthesis, fast synthesis for live conversation, and recognition of long recordings split by speaker, including in Russian.

DetailsText to speechHiggs AudioBoson AI · USACommercial use with conditions

Expressive speech and dialogue synthesis with voice cloning, plus recognition models. Version 3 of the synthesis supports about 100 languages, including Russian, but is non-commercial.

DetailsText to speechMOSS-TTS / MOSS-TTSDOpenMOSS (Fudan University) · ChinaCommercial use allowed

A speech synthesis family: multi-voice dialogue voicing (TTSD), fast synthesis for live conversation and the tiny Nano. Version 1.5 supports 30+ languages, including Russian.

Details

Source: huggingface.co/nari-labs/Dia2-2B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.