Text to speech

Fish Speech / OpenAudio

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.

Developer
Fish Audio, USA / China
First release
Apr 2024
Latest release
Mar 2026
Sizes
0.5B – about 4.5B
License
Non-commercial onlyEarly versions CC BY-NC-SA 4.0, S2-Pro under the Fish Audio Research License; commercial use only under a separate agreement
Russian
Supported
Running
On your own serverNeeds a GPU
Industries
Media and production, Science and research
Deploy on your server Hugging Face GitHub

What it does

  • Voice cloning
  • Emotional voiceover
  • Multilingual voiceover

Where it is used

ResearchMediaPrototyping

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. Fish Audio S2-Pro
  2. OpenAudio S1-mini
  3. Fish Speech 1.5
  4. Fish Speech 1.0

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 Fish Speech / OpenAudio be used in a commercial project?

No. License: Early versions CC BY-NC-SA 4.0, S2-Pro under the Fish Audio Research License; commercial use only under a separate agreement. A commercial product needs a different model or a separate agreement with the rights holder.

What hardware does Fish Speech / OpenAudio 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 Fish Speech / OpenAudio support Russian?

Yes, Russian is listed on the model card.

Where can I download Fish Speech / OpenAudio and what does it cost?

The Fish Speech / OpenAudio 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 speechCosyVoice / Fun-CosyVoiceAlibaba (Tongyi, FunAudioLLM) · ChinaCommercial use allowed

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

DetailsText to speechIndexTTSbilibili · ChinaCommercial use with conditions

Speech synthesis with voice cloning and precise duration control, handy for video dubbing. Controls emotion separately from timbre.

DetailsText 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.

Details

Source: huggingface.co/fishaudio/s2-pro. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.