Text to speech

CosyVoice / Fun-CosyVoice

Speech synthesis with voice cloning from a short sample and streaming output for live dialogue. Version 3 supports 9 languages, including Russian.

Developer
Alibaba (Tongyi, FunAudioLLM), China
First release
Jul 2024
Latest release
Dec 2025
Sizes
300M – 0.5B
License
Commercial use allowedApache 2.0
Russian
Supported
Running
On your own serverNeeds a GPU
Industries
Customer support, Marketing and content, Media and production, Education
Deploy on your server Hugging Face GitHub

What it does

  • Voice for a bot or assistant
  • Cloning a brand voice
  • Voicing videos
  • Multilingual voiceover

Where it is used

Call centersMedia and marketingOnline learningVoice bots

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. Fun-CosyVoice 3 0.5B
  2. CosyVoice 2 0.5B
  3. CosyVoice 300M

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 CosyVoice / Fun-CosyVoice 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 CosyVoice / Fun-CosyVoice 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 CosyVoice / Fun-CosyVoice support Russian?

Yes, Russian is listed on the model card.

Where can I download CosyVoice / Fun-CosyVoice and what does it cost?

The CosyVoice / Fun-CosyVoice 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

Text to speechQwen3-TTSAlibaba (Qwen) · ChinaCommercial use allowed

Speech synthesis in 10 languages, including Russian: voice cloning from 3 seconds, ready-made voices and creating a voice from a text description.

DetailsText to speechVoxCPMOpenBMB (ModelBest, Tsinghua University) · ChinaCommercial use allowed

Speech synthesis with voice cloning and natural intonation. VoxCPM2 supports 30 languages, including Russian.

DetailsText to speechFish Speech / OpenAudioFish Audio · USA / ChinaNon-commercial only

Speech synthesis with voice cloning and emotion control in 80+ languages, including Russian. Quality is close to paid services, but the weights are for research only.

Details

Source: huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.