📑Website - https://sohamratnaparkhi.github.io/VoiceAssistant/
🎇Please open the Project_Basic_struct folder to view the code!
This is Voice Assistant coded using Python which can do the following: -
1. Speak Text entered by User.
2. Search anything on Google.
3. Search anything on Wikipedia.
4. Read a MS Word(docx) document.
5. Convert speech to text.
6. Read a book(PDF).
Download - https://github.com/SohamRatnaparkhi/Voice-Assistant/releases/tag/v1.0.0
Download the rar file.
1. Extract the folder.
2. Open VoiceAssistant folder.
3. Double-click on the file _1_VoiceAssistant for using it.
In-case, if you don't find _1_VoiceAssistant in Voice Assistant folder, just install the executable(.exe) file AND SAVE IT IN VoiceAssistant FOLDER. It is advisable to run the (.exe) file in the VoiceAssistant folder; else the file won't run.
- Saying "Hello Python" will activate the Voice Assistant.
- Then the table that will be displayed on the screen shows the tasks that Voice Assistant can do.
- Saying the respective commands of the task that is intended will enable the Voice Assistant to do those tasks.
-
text to speech - User needs to type the text and then it will be spoken by the VoiceAssistant.
-
Search on Google - Voice Assistant will ask you "What do you want me to search on Google".
>Voice Assistant then starts recording your voice and will record anything that is spoken henceforth. >Then it will open the search results in default browser.
-
Search on Wikipedia - Voice Assistant will ask you "What do you want me to search on Wikipwedia? please say the exactsentence or word to search.".
>Voice Assistant then starts recording your voice and will record anything that is spoken henceforth. >Then it will speak out and print the summary of the search results. >It then asks, whether the respective search result should be opened in the default browser.
-
Read MS word document - Asks user to enter the location of file to be read and reads it.
NOTE :- 1. A file location without an extension(i.e. '.docx') will give an error. 2. A file inside a third party folder(Ex OneDrive) can't be accessed and will give an error.
-
Convert speech to text - Prints out the speech spoken by user.
By default, it record the voice for 60 seconds but it can be changed.
-
Read a book - Asks user to enter the location of file to be read and reads it.
NOTE :- 1. A file location without an extension(i.e. '.pdf') will give an error. 2. A file inside a third party folder(Ex. OneDrive) can't be accessed and will give an error.
Language: Python
For more information, follow the given links -
https://github.com/SohamRatnaparkhi/Voice-Assistant/blob/master/DOCUMENTATION.md
https://github.com/SohamRatnaparkhi/Voice-Assistant/blob/master/GUIDE.md
https://github.com/SohamRatnaparkhi/Voice-Assistant/blob/master/PRE-REQUISITES.md
THANK YOU!