Python Forum
Where To start on a voice assistant
Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Where To start on a voice assistant
#1
Brace yourself because this is a lot.

Hello,

I'm looking to build a voice activated assistant (similar to Alexa and Siri) but is private, doesn't spy on me, can work offline, and is programmed by me.

I'm using a Rpi 4 (with Manjaro Gnome for the OS) and looking to use Python to program my "A.I" assistant.

I'm thinking of using pocketsphinx for the STT because it's private & works offline (although I've heard about mozilla Deepspeech and I believe that's supposed be better than pocketsphinx while still being private and can work offline) and ESpeak for the TTS because I like the robotic voice.

The main purposes of my voice assistant is to do general things like play music (through an app on Manjaro --> Elisa Music player), do internet searches, do conversions (Like: cm-mm), remind me of events, set timers and alarms, tell me the weather, news, etc... and carry on a conversation.
Stuff like turning on/off lights will be done through my Arduino since they're already set up to my Arduino from before (I had created a simple offline voice assistant using an Arduino Mega and a Movi Shield. The problem with this was that it has a limited amount of memory, and couldn't do internet searches, and I needed separate modules for stuff like time and music).


Anyways, I'm looking for somewhere to start. I know there's a ton of tutorials out there but I'm looking for a general outline of how to do it.
I'm wondering if anyone can point me to some good tutorials so I can get a good idea of how to go about doing this.

I was thinking of starting off with a simple chatbot and G.U.I then add voice capabilities to it after because I'm thinking it might be easier (please let me know if this is not the case).

Also, are there any other private and offline STT engines that work well (Other than pocketsphinx and deepspeech)?

Thanks in advance.

P.S:
This is a bit off topic, but I'm wondering when you import things into your code (like: pocketsphinx) does that download everything needed for pocketsphinx to work, so if pockesphinx stopped being supported/the developer's deleted it, would it still work since everything needed to run it is already imported onto the pi?
Reply
#2
For starters,
you can find speech recognition packages here: https://pypi.org/search/?q=%22speech+recognition%22
Reply


Possibly Related Threads…
Thread Author Replies Views Last Post
  Voice Authentication/Voice BIometrics ShannonHartley 1 4,205 Mar-16-2018, 06:38 AM
Last Post: Larz60+

Forum Jump:

User Panel Messages

Announcements
Announcement #1 8/1/2020
Announcement #2 8/2/2020
Announcement #3 8/6/2020