# Vosk GPU-based speech recognition server available

**URL:** <https://community.asterisk.org/t/vosk-gpu-based-speech-recognition-server-available/91210>\
**Category:** Asterisk Integration\
**Created:** [January 12, 2022, 5:09pm UTC](https://community.asterisk.org/t/vosk-gpu-based-speech-recognition-server-available/91210 "2022-01-12T17:09:08Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![nshmyrev](https://avatars.discourse-cdn.com/v4/letter/n/858c86/32.png) [@nshmyrev](https://community.asterisk.org/u/nshmyrev)\
**Post date:** [January 12, 2022, 5:09pm UTC](https://community.asterisk.org/t/vosk-gpu-based-speech-recognition-server-available/91210/1 "2022-01-12T17:09:08Z")

</div>

Hi

We wanted to announce that [Vosk](https://alphacephei.com/vosk/) speech recognition server now supports GPU decoding. With CUDA and NVIDIA cards it can accurately recognize up to **300 streams in parallel on a single machine in real-time**. If you are using Vosk with Asterisk and look to process more data, try it out.

You need a modern GPU card (like GTX1080) and CUDA11.4 installed to try it.  
You can run the server with a simple docker command:

```auto
docker run --runtime=nvidia -p 2700:2700 alphacep/kaldi-en-gpu

```

Then you can connect to the server as usual, for example, you can integrate Vosk Asterisk module or just forward audio through ARI. See the previous topic.

> [@Module for Vosk speech recognition in Asterisk available](https://community.asterisk.org/t/module-for-vosk-speech-recognition-in-asterisk-available/84262):
>
> Hello everyone. We have just released a module for speech recognition in Asterisk with Vosk server: [Vosk server](https://github.com/alphacep/vosk-server) is an open source speech recognition server which supports several protocols (websocket, grpc). You can install Vosk server with a simple docker and transcribe speech in English, Chinese or Russian like this: docker run -d -p 2700:2700 alphacep/kaldi-en:latest Other models like Spanish are also available on request. Other nice things about Vosk: Implements very accurate speech r…

---

<div class="post-metadata">

**Author:** ![system](https://global.discourse-cdn.com/asterisk/original/2X/4/475d0c889911cfb84ac4881ad6df8b523e3f9105.png) [@system](https://community.asterisk.org/u/system)\
**Post date:** [February 11, 2022, 5:09pm UTC](https://community.asterisk.org/t/vosk-gpu-based-speech-recognition-server-available/91210/2 "2022-02-11T17:09:52Z")

</div>

This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.