This project is about using Raspberry pi with USB microphone and Speaker for interactive answering machine. We are calling it Talking Ganesha. In Hindu Culture , God Ganesha is called as God of Knowledge. We have created this project just to create Talking Ganesha in Ganesh Festival. We have used Google Speech API for converting speech to text, WolfarmAlpha API for answering questions and then eSpeak to speak out the answer return by WolframAlpha.
It is based on initial work done by Mr Dave. His instruction can be found in “http://makezine.com/projects/universal-translator/.
This project was developed with the help of Utsav (my Infosys team mate) and Suhas (Vigyan Ashram Fab Lab Instructor)
You need following hardware :
1. Raspberry Pi B+
2. Sound Card (In case you don’t have USB headphone or USB Mic + Speaker)
3. Headphone or Mic + Speaker with audio jack
4. Internet Connection
Step 1: Set up Raspberry Pi
(This is taken from step 1 of Universal Translator “http://makezine.com/projects/universal-translator/)
Assuming you have Raspbian installed on your Raspberry Pi.
Update the software on your Raspberry Pi: sudo apt-get update sudo apt-get upgrade
Install the software required for this project with following commands:
sudo apt-get install python-pip mplayer flac python2.7-dev libcurl4-gnutls-dev
# To get object via any HTTP request e.g. calling Speech API from python script
sudo pip install requests pycurl
# To get answers for your questions
sudo pip install wolframalpha
# To manage sound / audio devices
sudo apt-get install alsa-utils
# To convert text to speach
sudo apt-get install espeak
# We shall use google Speech API to convert Speech to Text
Step 2: Create Google Sppech API Key and Wolfram API Key
Download required python and shell scripts.
Create new folder called “Talking Ganesha” inside home folder
Download the following scripts from download section :
Execute command on Raspberry Pi
sudo chmod +x stt.sh
Google Speech API Key :
Use instructions from http://makezine.com/projects/universal-translator (Step 4).
This google api key shall be used in script “text-to-translate.py (key=’GoogleKey’)
For Wolfram Key :
Complete Form to activate your account
Click on Get an AppID button on right
Enter application Name and Description
Now copy APPID.
This key shall be used in script “queryProcess.py” (app_id = “WolframAlpha Key”)
Note that you can make 50 calls to Google Speech API (per day) and 2000 calls to Wolfram Alpha API (Per month). And this usage must be restricted to personal use (non commercial).
For more detail:Raspberry Pi based answering Ganesha