# How to make Raspberry Pi 4B a standalone device?

**URL:** https://forum.core-electronics.com.au/t/how-to-make-raspberry-pi-4b-a-standalone-device/12953
**Category:** Raspberry Pi
**Created:** [28 January 2022 15:00 UTC](https://forum.core-electronics.com.au/t/how-to-make-raspberry-pi-4b-a-standalone-device/12953 "2022-01-28T15:00:36Z")
**Posts on this page:** 1
**Showing post:** 10

<div class="post-metadata">

### Author: ![James](https://yyz2.discourse-cdn.com/flex028/user_avatar/forum.core-electronics.com.au/james/32/4400_2.png) [@James](https://forum.core-electronics.com.au/u/James)
#### Post date: [31 January 2022 02:11 UTC](https://forum.core-electronics.com.au/t/how-to-make-raspberry-pi-4b-a-standalone-device/12953/10 "2022-01-31T02:11:23Z")

</div>

Hi Harold,

That should be doable, check out Tim’s guide on object recognition:

> **[Object and Animal Recognition With Raspberry Pi and OpenCV - Tutorial Australia](https://core-electronics.com.au/guides/raspberry-pi/object-identify-raspberry-pi/)**
>
> \[Update – Until there is correct compatibility of OPEN-CV with the new Raspberry Pi ‘Bullseye’ OS I highly recommend at this stage flashing and using the previous Raspberry Pi ‘Buster’ OS onto your Micro-SD for use with this guide...

Were you looking to get it saying object names aloud? If so, you’re not the first!

> [@Object and Animal Recognition With Raspberry Pi and OpenCV](https://forum.core-electronics.com.au/t/object-and-animal-recognition-with-raspberry-pi-and-opencv/11211/28):
>
> Hi Tim, I was from the YouTube comment and I’m trying to use a Text To Speech software to say out loud the name of any object the code is able to detect. I’m having some trouble on a few things. How would I make it so that the if the same object stays on the screen for a while, to stop saying it’s name out loud, and only resume when a NEW object has been spotted? Thanks for the help.

I made another post on that thread talking about how to grab the list of objects it found:

> [@Object and Animal Recognition With Raspberry Pi and OpenCV](https://forum.core-electronics.com.au/t/object-and-animal-recognition-with-raspberry-pi-and-opencv/11211/30):
>
> Hi Niseem, That’ll be super easy! In the Python code in the guide, the getObjects function spits out two things, an image, and a list of all the objects it found in an image, each one a smaller list of two elements, the object name, and the model’s confidence that it got it right. Let me know if this needs more sense added to it! -James

From there, you’ll just need to pick a TTS option, gTTS seems popular:

> **[gTTS](https://pypi.org/project/gTTS/)**
>
> gTTS (Google Text-to-Speech), a Python library and CLI tool to interface with Google Translate text-to-speech API

Or if you’re after something self contained:

> **[TTS is a library for advanced Text-to-Speech generation. | PythonRepo](https://pythonrepo.com/repo/mozilla-TTS-python-natural-language-processing)**
>
> mozilla/TTS, TTS is a library for advanced Text-to-Speech generation. It's built on the latest research, was designed to achieve the best trade-off among ease-of-training, speed and quality. TTS comes with pretrained models, tools for measuring...

-James

---

_[View the full topic](https://forum.core-electronics.com.au/t/how-to-make-raspberry-pi-4b-a-standalone-device/12953)._