[Yandex Cloud documentation](../../index.md) > [Yandex SpeechKit Hybrid](../index.md) > Speech synthesis > About the technology

# Speech synthesis

## Available voices {#voices}

SpeechKit Hybrid offers [premium voices](https://aistudio.yandex.ru/docs/en/speechkit/tts/voices#premium) and [Brand Voice](https://aistudio.yandex.ru/docs/en/speechkit/tts/brand-voice/).

## Getting started {#before-you-begin}

1. Install [Docker Engine](https://docs.docker.com/engine/install/) and [Docker Compose](https://docs.docker.com/compose/install/) on your server.

1. [Authenticating](../../container-registry/operations/authentication.md) in Container Registry.

For the recommended hardware configuration, see [System requirements](../system-requirements.md).

## Installing and setting up speech synthesis {#installing}

1. Put the `docker-compose.yaml` file you got from the SpeechKit team in a folder on your server.

1. Edit `docker-compose.yaml`: replace `N` with your number of CPU threads in the `CPU_THREADS_NUM: N` parameter.

   In Linux, you can find out the number of threads on your server using the following command:

   ```bash
   cat /proc/cpuinfo | grep -E "processor.+:" | wc -l
   ```

1. Download all the required Docker containers:

   ```bash
   docker-compose pull
   ```

1. Start SpeechKit:

   ```bash
   docker-compose up -d
   ```

1. Wait until the service loads

   ```bash
   docker logs tts-server
   tts-server            | INFO: 2021-09-22 15:36:02.765 +0000 server_base.cpp:144 Load finished. Ready to server requests on 0.0.0.0:17001
   ```

The speech synthesis service will be available on TCP port **9080**.