Text to speech

Kokoro

A tiny speech synthesis model (82M) that sounds on par with large ones. Runs on a regular CPU; English and a few other languages, no Russian.

Developer
hexgrad (independent developer), not disclosed
First release
Dec 2024
Latest release
Feb 2025
Sizes
82M
License
Commercial use allowedApache 2.0
Russian
Not supported
Ready-made builds
GGUF, MLX (Apple)
Running
On your own serverAlso runs without a GPU
Industries
Media and production, Education, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Voicing articles and notifications
  • Voice for apps without a GPU
  • Bulk text voiceover

Where it is used

Mobile and web appsMediaOnline 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. Kokoro v1.1-zh
  2. Kokoro v1.0
  3. Kokoro v0.19

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 Kokoro 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 Kokoro 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 Kokoro support Russian?

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

Where can I download Kokoro and what does it cost?

The Kokoro 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

Text to speechPiperRhasspy / Open Home Foundation · USACommercial use with conditions

Very fast speech synthesis that runs even on a Raspberry Pi. Ready-made voices in 35+ languages, including several Russian ones.

DetailsText to speechStyleTTS 2Columbia University · USACommercial use with conditions

A lightweight English speech synthesis model with natural intonation. Many other models, such as Kokoro, are built on it.

DetailsText to speechChatterboxResemble AI · USACommercial use allowed

Speech synthesis with voice cloning and adjustable expressiveness. The multilingual version supports 23 languages, including Russian; Turbo and Flash are sped up for live dialogue.

Details

Source: huggingface.co/hexgrad/Kokoro-82M. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.