Text to speech

Piper

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

Developer
Rhasspy / Open Home Foundation, USA
First release
Jun 2023
Latest release
Mar 2025
Sizes
about 5M – 30M
License
Commercial use with conditionsThe old engine is MIT, the new piper1-gpl is GPL-3.0; each voice has its own license (some free, some non-commercial)
Russian
Supported
Ready-made builds
GGUF
Running
On your own serverAlso runs without a GPU
Industries
Software development, Customer support
Deploy on your server Hugging Face GitHub

What it does

  • Voicing notifications and bot replies
  • Voice for offline devices
  • Voice menus
  • Reading text aloud

Where it is used

Smart homeEmbedded devicesVoice botsTerminals and kiosks

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. piper1-gpl (новая ветка движка)
  2. Piper и первые голоса

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 Piper be used in a commercial project?

With conditions. License: The old engine is MIT, the new piper1-gpl is GPL-3.0; each voice has its own license (some free, some non-commercial). Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Piper 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 Piper support Russian?

Yes, Russian is listed on the model card.

Where can I download Piper and what does it cost?

The Piper 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 speechSilero TTSSilero · RussiaCommercial use with conditions

Lightweight Russian speech synthesis that runs on a regular CPU. Version v5 added CIS languages and languages of Russia's peoples: Tatar, Bashkir, Yakut, Kazakh and others.

DetailsText to speechKokorohexgrad (independent developer) · not disclosedCommercial use allowed

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.

Details

Source: github.com/OHF-Voice/piper1-gpl. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.