# Feeding audio streams to speech recognition engine on server

**URL:** <https://discourse.lynckia.com/t/feeding-audio-streams-to-speech-recognition-engine-on-server/244>\
**Category:** Uncategorized\
**Created:** [May 20, 2014, 4:08pm UTC](https://discourse.lynckia.com/t/feeding-audio-streams-to-speech-recognition-engine-on-server/244 "2014-05-20T16:08:20Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![tashimaya](https://avatars.discourse-cdn.com/v4/letter/t/3bc359/32.png) [@tashimaya](https://discourse.lynckia.com/u/tashimaya)\
**Post date:** [May 20, 2014, 4:08pm UTC](https://discourse.lynckia.com/t/feeding-audio-streams-to-speech-recognition-engine-on-server/244/1 "2014-05-20T16:08:20Z")

</div>

Hi

I am new to WebRTC and found about Licode today. Sorry if my question is  
vague. I am trying to find out what I can achieve with Licode.

Say my server has a speech recognition engine and the server is capable of  
receiving audio streams from remote web browsers (Chrome) through WebRTC  
peer connections. I would like to feed the received audio streams to the  
speech recognition engine so it can convert speech to text and then send  
back the resulting text to the browser real-time.

With Licode is it possible to receive audio streams and process them on the  
server (for example save them in .WAV file) or feed them to other  
components such as a speech recognition engine?

Many thanks