You could create a separate audio file (e.g. hey_tim.mp3) which is played every time the wakeword is detected. That would speed up the wakeword detection because the program wouldn't have to create a new file every time.
Hi Tim, Are you going to continue to improve the Voice Assistant? You were talking about adding web scraping. The UI could be improved as well with an avatar for instance and what about integrating AI? The assistant could understand commands even if different words are used to start it and it could have AI chatting capabilities for prolonged times. You are doing a great job!
Hey! you literally explained exactly what i am tryin to make right now. Did you managed to do it and if so would you please like to help me out with the Ai part ?
The whole of your content (this series and the previous) is state-of-the-art. I believe that you inspire thousands of enthusiast who follow you on TH-cam. The content is all the time up to date and clearly displayed. Beside your remarkable and outstanding work on TH-cam channel I hope that you will complete your study on time. Analyzing the popularity of your videos , it seems that the most popular are projects and videos where you solve the problems. It is extremely interesting to use our brains more often and presents SW from this approach (as an amazing tool to solve the challenges). Regarding this series it can be probably good idea to control HW by voice. You can deploy SW on Raspberry PI or the other microcontroller). The script can be pretty easy but very practical in order to build intelligent house. Thanks you again and good luck!
You can add double while (true) loop ,one runs every time and other runs only when we say the wake word , we can also create another sleep word and trigger to break the inner while loop ...
Could you make it so that it can learn? Like if you tell it to learn a sound you make and to play it back whenever you want, or have it play a game of chess against you and learn as it plays so it can get better?
I need help i can't figure this out or what to do. Every time I ask it about a day it says "you have one event this day" and then stops shows the event but doesn't do anything after except this. start_time = str(start.split("T")[1].split("-")[0]) IndexError: list index out of range How do i fix this and have return to listening after I hear the event?
can be done using cloud facility connect your android app to google firebase and set a flag variable anytime any voice request(you have voice api for android) is made to application it goes to firebase sets flag and accordingly sends request to running py script or else make use of kivy library for python and make a basic android app.
Interesting video, I would love it if you continue this series! There are some nice suggestions already in the comments :) Just one thing about the wake up command, I think it's not optimal, is it? I guess there should be a more efficient way than converting ever input to check it (maybe check the sound wave itself instead of sending all to the google speech to text). I guess it would use way too much battery if assistants like siri would do this constantly or do I assume this wrong?
Use Machine Learning to make the voice sound more realistic. You can program the assistant to watch a lot of movies and TV shows overtime using machine learning to learn the different pitches of certain words and stuff like that.
Hi Tim, I really like your videos and specially this playlist but i have some issues running the program. I don´t know if is the speech recognition or the pyttsx3 but the assistant is to slow answering questions and recognizing the audio. What could fix this?, I hope that you can answer this, thanks you so much I really appreciate your work.
I noticed another very minor bug. Let's say you have an event scheduled from one day to another (like a movie from 11:30 PM on Monday to 12:30 AM on Tuesday). When you ask for events on Tuesday, it says you have an event named movie at 11:30 PM, even though that event is actually on the previous day at 11:30 AM.
Hey @Tech With Tim, I am currently having a problem withe the event function: It gives me the right events but they are all two hours earlier displayed than they are. I am thinking that it has something to do with the timezone... But i don't know how to fix it. (I live in Germany, Munich)
Is there a way to make it learn with machine learning (I think that is the right term for what I am wanting to say?. As in, it can learn about your habits and have more personalized suggestions for new calendar events, it can understand what you say so you don't have to say exact phrases, it can learn English so it can say things in different ways, etc. If so, that would be amazing! And if this doesn't make sense, please let me know and I can try to explain it better
no need to wait for confirmation after giving the wake up word. you can simple say the full command like "hey mike say hello" and then remove the hey mike.
This works great! Thank you. Now that I got it all running. When I try to run main.py from the CMD I get ModuleNotFoundError: No module named 'pyaudio' Works with no errors in Pycharm but not from command prompt. Any ideas?
Hi Tim, there is a way to change the voice? for example to drag voice from a .mp3 or .wav file? i had try it but i can't find something can you help? or make a video with that?
Hi tim, as you can see before you spell out wake word, all that you are saying in printing as it is so, is there any way to not to print all this and print only wake word
it shows me an error if i have more than one event on a day it shows first event but this error while printing out second event Traceback (most recent call last): File "C:/Users/yadav/PycharmProjects/voicerecognition/voice.py", line 176, in get_events(date, SERVICE) File "C:/Users/yadav/PycharmProjects/voicerecognition/voice.py", line 85, in get_events print(start, event['summary']) KeyError: 'summary' couldn't find any solution
One small bug - The program continually loops through printing Exception/Listening statements because it's continuously trying to analyse what you say. If you don't say anything, that's an exception because it's trying to convert empty sound to text and then it returns to waiting for you to say your 'wake' phrase. Now, this can be changed simply by removing the print('listening') and replace print('exception') with pass lines but that only removes the display to the user of what's going on, doesn't stop the error from occurring... Any ideas?
I have the problem that after prolonged use after too many exceptions the bot just freezes and wont understand any incoming commands anymore. Do you have the same issue(caused by this bug you just described)?
add limit to it example of code:- audio = r.listen(source,phrase_time_limit=10) #it will limit time for 10 seconds so whatever you will speak for 10 sec it will listen it and respond you accordingly and you can also change the limit from 10 to 5 sec or anything you like :-)
Maybe slightly change how it accepts commands. above CALENDAR_STRS, try for phrase in text: if phrase in calenderstrings then.. elif phrase in notestrings then.. else: speak('not recognised) /disclaimer: just learning, don't know that it would be the best way to work but a setup like that would check the whole text for any phrase in the phrase dictionaries (calenderstrings, notestrings), then execute the appropriate command and if no phrase recognised then return your desired 'unrecognized' result
I absolutely love this project. This project really started my interest in using voice technology. Unfortunately i never really got it working just as i wanted. Somehow after prolonged use, after hearing too many non command requests or silences, the program just stops receiving new commands. Making it impossible to have the program constantly on waiting for the wake command. This happens on both Windows and Linux(With Jack). Does anyone know how to solve this problem? I even tried using a client.py which listens for a wake and then opens the chatbot.py(while waiting till chatbot.py is finished with exit()). Did not resolve my problem. I thought the problem lied within using Jack on Linux but this problem also happens on Windows. I'm completely clueless. Any help is appreciated.
i met with a problem. when two speaak statements are usedly . one is excuting and another shows an "ERRNO 14 permission denied " example def speak(text):
I learned a lot from your project , But how could I make this assistance to response faster ,like other assistant "alexa,/Ok google," dosen't take to time fro response.
I have a bug that makes it unuseable, if I run the programm it immidiantly get into a loop of writing "Listening" and saying "What did you say?", how can i fix that (i copied like the whole text from his homepage (not that stuff where i have my own stuff entered). I have no clue how to fix this!
Hey man, I figured my mistake, in my case it was just a silly order based bug. I think you should compare your code to the code provided in the desc link. It'll get sorted
@@supamdeepbains5172 I dont know if you managed to solve it, but with my assistant i just had to change the speak output. It appears that the bot identified commands in it's own output. (command: Start browser, voice output "Starting browser" seemed to cause the repeated commands.)
Hey tim.when i run this voice assistance program,i got permission error.so i couldn't fix it.can you help me to fix it. Error is show that as Traceback(most recent call last) and error name is permissionsError:[Errno 13] permission denied:'voice.mp3'
Hey Guys, Does someone know how to fix this problem: Traceback (most recent call last): File "Controller.py", line 5, in awake = WAKE.Wake() File "/home/saiba/Dokumente/Bot/Wake.py", line 9, in Wake if said.count(Wake) > 0: TypeError: must be str, not function Thank you :)
@@arkaitzhedger294 Thanks for the help.... I have found a way around. > * WAKE_KEYWORD = ["hi tim", "hey tim", "okay tim", "ok tim"] for WAKE in WAKE_KEYWORD: if WAKE in query:
Thanks for this serie. Tim. How would you handle multiple users ? Say i speak to the assistant. It gives me my calendar. My wife speaks to it, it gives her plans back. Thanks by advance.
on tutorial 2 I got this error: Traceback (most recent call last): File "/Users/rowan/Desktop/Coding/Other/main.py", line 26, in get_audio() File "/Users/rowan/Desktop/Coding/Other/main.py", line 15, in get_audio with my_mic as source: File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/speech_recognition/__init__.py", line 138, in __enter__ self.audio.open( File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/pyaudio.py", line 750, in open stream = Stream(self, *args, **kwargs) File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/pyaudio.py", line 441, in __init__ self._stream = pa.open(**arguments) OSError: [Errno -9998] Invalid number of channels >>> how do I fix this
Gökhan Tekir Firstly, use “pip install pyttsx3” in command prompt to install pyttsx3 Then use the following code in your program: import pyttsx3 def speak(text): engine = pyttsx3.init() engine.say(text) engine.runAndWait() As you can see, this does not require any mp3 file to be saved, so you won’t have to face any issue regarding that. Hope this helps! :)
Sir, please use hotword detection in the program.... i Google many stuff. found two to three services works on python firstly 'snowboy hot word detection' the problem is that its not working on windows. secondly 'picovoice/porcupine hot word detection' which also work on windows but problem is that they made the script for console based and i am not a professional python program because of that i can't implement it on IDE but you can do it.. you have the skill to add it on IDE so please add that on your program. if you need any kind of help for that i will be there in any time... & love from India❤️
Hey Tim! When I tried it, it says: PermissionError: [Errno 13] Permission denied: 'voice.mp3' It would be great if anyone could help me with this. Thanks a Ton!
umm, I have been searching and searching. But I haven't found it yet. Away for your voice to be distinguished over someone else. The Correct term for this I believe is Speaker Identification.
Thanks for implementing my suggestion :D I feel honored.
You could create a separate audio file (e.g. hey_tim.mp3) which is played every time the wakeword is detected.
That would speed up the wakeword detection because the program wouldn't have to create a new file every time.
that was smart. good thinking 👍
Ufff :O that's a pretty smart thinking. Thanks for the Tip mate.
Sir no one could beat you. At this age you are such a successful programmer
I think you should continue further this series.🔥🔥🔥🔥
yesss please do
Hi Tim,
Are you going to continue to improve the Voice Assistant? You were talking about adding web scraping. The UI could be improved as well with an avatar for instance and what about integrating AI? The assistant could understand commands even if different words are used to start it and it could have AI chatting capabilities for prolonged times. You are doing a great job!
Hey! you literally explained exactly what i am tryin to make right now. Did you managed to do it and if so would you please like to help me out with the Ai part ?
@@saadmansuri4092 after 8 months do u still need help with this?
@@fares-ol8bz i do hahaha
@@fares-ol8bz I am just getting into my programming again and I could use some assistance as well if you are able to help
2:17, if it says 230 instead of 2:30 for you, just add a ", " in between
The whole of your content (this series and the previous) is state-of-the-art. I believe that you inspire thousands of enthusiast who follow you on TH-cam. The content is all the time up to date and clearly displayed. Beside your remarkable and outstanding work on TH-cam channel I hope that you will complete your study on time.
Analyzing the popularity of your videos , it seems that the most popular are projects and videos where you solve the problems. It is extremely interesting to use our brains more often and presents SW from this approach (as an amazing tool to solve the challenges).
Regarding this series it can be probably good idea to control HW by voice. You can deploy SW on Raspberry PI or the other microcontroller). The script can be pretty easy but very practical in order to build intelligent house.
Thanks you again and good luck!
You can add double while (true) loop ,one runs every time and other runs only when we say the wake word , we can also create another sleep word and trigger to break the inner while loop ...
Hey tim,
It would be cool to automate sending emails with attachments and having the ability to set events on the Google calendar api
Could you make it so that it can learn? Like if you tell it to learn a sound you make and to play it back whenever you want, or have it play a game of chess against you and learn as it plays so it can get better?
Hey Tim, it will really be the best if the voice assistant has a GUI and works like a .exe application rather than a python script.
I need help i can't figure this out or what to do. Every time I ask it about a day it says "you have one event this day" and then stops shows the event but doesn't do anything after except this.
start_time = str(start.split("T")[1].split("-")[0])
IndexError: list index out of range
How do i fix this and have return to listening after I hear the event?
@Tech With Tim is there any way to access the same script from smart phone or remotely access the program?
can be done using cloud facility connect your android app to google firebase and set a flag variable anytime any voice request(you have voice api for android) is made to application it goes to firebase sets flag and accordingly sends request to running py script or else make use of kivy library for python and make a basic android app.
Interesting video, I would love it if you continue this series! There are some nice suggestions already in the comments :)
Just one thing about the wake up command, I think it's not optimal, is it? I guess there should be a more efficient way than converting ever input to check it (maybe check the sound wave itself instead of sending all to the google speech to text). I guess it would use way too much battery if assistants like siri would do this constantly or do I assume this wrong?
Implement on UI design too
For faster Python try to use Cython.
Pretty handy stuff though
When the next features are coming????
Use Machine Learning to make the voice sound more realistic. You can program the assistant to watch a lot of movies and TV shows overtime using machine learning to learn the different pitches of certain words and stuff like that.
Hello, do you have any clue how to do this? It is interesting idea
Hi Tim, I really like your videos and specially this playlist but i have some issues running the program.
I don´t know if is the speech recognition or the pyttsx3 but the assistant is to slow answering questions and recognizing the audio.
What could fix this?, I hope that you can answer this, thanks you so much I really appreciate your work.
could you make a plugin system tutorial maybe connected through an api with django? just a thought, wanted to see you do it (couldn't do it myself)
appreciate your work thanks for the video keep up the good work
I noticed another very minor bug. Let's say you have an event scheduled from one day to another (like a movie from 11:30 PM on Monday to 12:30 AM on Tuesday). When you ask for events on Tuesday, it says you have an event named movie at 11:30 PM, even though that event is actually on the previous day at 11:30 AM.
Great! Can you update this system with new technologies like CHatGPT, Whisper.... etc ?
Hey @Tech With Tim,
I am currently having a problem withe the event function:
It gives me the right events but they are all two hours earlier displayed than they are.
I am thinking that it has something to do with the timezone...
But i don't know how to fix it.
(I live in Germany, Munich)
Can you make it so you can have it access all of your calendars on google, including the ones you import?
Hey, my program can't say anymore after saying one thing.
How do i fix this?
Does anyone know if it is possible to make voice assistant for andorid phone with python?
Is there a way to make it learn with machine learning (I think that is the right term for what I am wanting to say?. As in, it can learn about your habits and have more personalized suggestions for new calendar events, it can understand what you say so you don't have to say exact phrases, it can learn English so it can say things in different ways, etc. If so, that would be amazing! And if this doesn't make sense, please let me know and I can try to explain it better
no need to wait for confirmation after giving the wake up word. you can simple say the full command like "hey mike say hello" and then remove the hey mike.
Awesome...I like your videos, but can you also include the deployment to a phone, web service etc
This works great! Thank you. Now that I got it all running. When I try to run main.py from the CMD I get ModuleNotFoundError: No module named 'pyaudio'
Works with no errors in Pycharm but not from command prompt. Any ideas?
In pycharm it makes virtual environment of python which is completely different from the python in your computer. Try pip install pyaudio in CMD.
This is very useful!
Hi Tim, there is a way to change the voice? for example to drag voice from a .mp3 or .wav file? i had try it but i can't find something can you help? or make a video with that?
In the next video, we wanna see if the assistant captured the entire thing you said at the end. :P
Hi tim,
as you can see before you spell out wake word, all that you are saying in printing as it is so, is there any way to not to print all this and print only wake word
it shows me an error if i have more than one event on a day it shows first event but this error while printing out second event
Traceback (most recent call last):
File "C:/Users/yadav/PycharmProjects/voicerecognition/voice.py", line 176, in
get_events(date, SERVICE)
File "C:/Users/yadav/PycharmProjects/voicerecognition/voice.py", line 85, in get_events
print(start, event['summary'])
KeyError: 'summary'
couldn't find any solution
Can you do the same project but implement AI for maybe detect the wake word or interpreting some commands?
Please Make more videos
Thanks for your teaching. Our feedback can be a help to upload more important videos.
One small bug - The program continually loops through printing Exception/Listening statements because it's continuously trying to analyse what you say. If you don't say anything, that's an exception because it's trying to convert empty sound to text and then it returns to waiting for you to say your 'wake' phrase. Now, this can be changed simply by removing the print('listening') and replace print('exception') with pass lines but that only removes the display to the user of what's going on, doesn't stop the error from occurring... Any ideas?
I have the problem that after prolonged use after too many exceptions the bot just freezes and wont understand any incoming commands anymore. Do you have the same issue(caused by this bug you just described)?
Thank you for this one!
Could not find this repo on your github, is there a way i can clone this project?
Thanks in advanced.
mine doesnt reply to me. It picks up what im saying but its always stuck on listening
add limit to it
example of code:- audio = r.listen(source,phrase_time_limit=10) #it will limit time for 10 seconds so whatever you will speak for 10 sec it will listen it and respond you accordingly and you can also change the limit from 10 to 5 sec or anything you like :-)
@@fakeaccount7013 wait where do i have to put it
is there anyway to make the program say "unrecognized command" when it doesn't know what i am saying
Maybe slightly change how it accepts commands. above CALENDAR_STRS, try for phrase in text: if phrase in calenderstrings then.. elif phrase in notestrings then.. else: speak('not recognised)
/disclaimer: just learning, don't know that it would be the best way to work but a setup like that would check the whole text for any phrase in the phrase dictionaries (calenderstrings, notestrings), then execute the appropriate command and if no phrase recognised then return your desired 'unrecognized' result
I absolutely love this project. This project really started my interest in using voice technology.
Unfortunately i never really got it working just as i wanted. Somehow after prolonged use, after hearing too many non command requests or silences, the program just stops receiving new commands. Making it impossible to have the program constantly on waiting for the wake command. This happens on both Windows and Linux(With Jack). Does anyone know how to solve this problem?
I even tried using a client.py which listens for a wake and then opens the chatbot.py(while waiting till chatbot.py is finished with exit()). Did not resolve my problem. I thought the problem lied within using Jack on Linux but this problem also happens on Windows. I'm completely clueless.
Any help is appreciated.
i met with a problem.
when two speaak statements are usedly . one is excuting and another shows an "ERRNO 14 permission denied "
example
def speak(text):
tts = gTTS(text=text, lang='en')
fn = "voice.mp3"
tts.save(fn)
playsound.playsound(fn)
speak("what to say")
speak("you need to say")
@SnakeSkins i tried
It shows permission denied
I learned a lot from your project , But how could I make this assistance to response faster ,like other assistant "alexa,/Ok google," dosen't take to time fro response.
I have a bug that makes it unuseable, if I run the programm it immidiantly get into a loop of writing "Listening" and saying "What did you say?", how can i fix that (i copied like the whole text from his homepage (not that stuff where i have my own stuff entered). I have no clue how to fix this!
Hey man, I figured my mistake, in my case it was just a silly order based bug. I think you should compare your code to the code provided in the desc link. It'll get sorted
Google news api would be cool
can i get a heart?
Yes
@@TechWithTim Thanks for the heart
Hey Tim, you are awesome!! Just now saw your other videos on the VA tutorial. But I can't seem to install PyAudio. Can you please help me..
first download "pipwin" like this...
"pip install pipwin"
then write "pipwin install pyaudio"
do all this in the terminal
How tot turn this ai assistant to any app or software plzz reply soon
Hello, Tim, you have an error with the link for enrolling in The Fundamentals of Programming w/ Python,, at the last, you add /p so correct it.
thank you for amazing videos!
How about wakewords?
snowboy but for windows?
I tried it but was unsuccessful tbh
Hello there, can this app be opened on an android? or has anyone some toughs on how to do that ?
Thank you a lot it was really helpful
Nice....
How to save all reminder's for the day in a single file with saving time ?
if i add 2 reminder it would save each one in each different files
Is it applicable to raspberrypi?
Hi, strangely enough my assistant repeats some things twice. Does anyone know whats causing this?
same man idk happening with me too
@@supamdeepbains5172 I dont know if you managed to solve it, but with my assistant i just had to change the speak output. It appears that the bot identified commands in it's own output. (command: Start browser, voice output "Starting browser" seemed to cause the repeated commands.)
@Tech With Tim how do i go about creating a desktop or mobile application with this...if anyone know please let me know thank you
is there anyway to create a shutdown command which will stop the program listening/running
do the following if you want to create a shutdown command which will stop the program listening/running:
if "stop" in text:
speak("stopping")
exit()
@@soumya9895 thanks so much really helpful
I have Mic and it's just stucked on Listening. Tested on cmd and VSCode terminal
hey can you please tell me that how can i access chrome in the same way you accessed notepad
use the webbrowser module
@@viswamberprasad9418 thanks
Hey tim.when i run this voice assistance program,i got permission error.so i couldn't fix it.can you help me to fix it. Error is show that as Traceback(most recent call last) and error name is permissionsError:[Errno 13] permission denied:'voice.mp3'
If you can help me.send a mail to this email: wmpdhananjaya@gmail.com
@@pasindudhananjaya6107 add an "os.remove('voice.mp3')" to the end of the function "speak"
@@DL_GLCH thanks, that helped
@@utkarshthanvi4048 you're welcome :D
Hey Guys,
Does someone know how to fix this problem:
Traceback (most recent call last):
File "Controller.py", line 5, in
awake = WAKE.Wake()
File "/home/saiba/Dokumente/Bot/Wake.py", line 9, in Wake
if said.count(Wake) > 0:
TypeError: must be str, not function
Thank you :)
is there any way I can have a list of words like: *["hey tim", "hi tim", "ok tim"]*
Please tell if you know...
copy this and replace your WAKE list with it,
WAKE = "hey tim", "hi tim", "ok tim"
you can add any word you want using that.
@@arkaitzhedger294 Thanks for the help.... I have found a way around.
>
*
WAKE_KEYWORD = ["hi tim", "hey tim", "okay tim", "ok tim"]
for WAKE in WAKE_KEYWORD:
if WAKE in query:
if query.count(WAKE) > 0:
speak("I\'m listening")
print("I\'m listening")
query = takeCommand().lower()
*
Amazing ❤
for some reason it says 200 30pm minutes it does not say 2:30pm for me Tim pls give me an answer PLS PLS PLS PLS
Thanks for this serie. Tim. How would you handle multiple users ? Say i speak to the assistant. It gives me my calendar. My wife speaks to it, it gives her plans back. Thanks by advance.
would love to know too... some kind of voice recognition. By the way, thanks for your vids Tim. Great
you would need machine learning for that, to recognize yours and her voice
Anyone know how to make it answer multiple questions in a row and not turn off after only one question
Hi tim, everything works fine except every time i say something it takes approx 10-15 seconds and then proceeds to next command. Can you help me out?
Yeah same problem dude
Did you find any solutions ???
hi can u make it close the notepad automatically after written down the notes
important keyboard module and then press alt+f4.... it will close automatically notepad
Can we make jarvis with help of google assistant and with a.i
Why not join the digital assistant with the pizza ordering application?
If int(start_time.split(":")[0]) < 12:
^
SyntaxError: invalid syntax
Please Tim how can I solve this error.
The 'I' in if statement is small, you've used the Capital I. Hope it solves your issue :)
Amazing
I am the 1000th like your welcome
on tutorial 2 I got this error: Traceback (most recent call last):
File "/Users/rowan/Desktop/Coding/Other/main.py", line 26, in
get_audio()
File "/Users/rowan/Desktop/Coding/Other/main.py", line 15, in get_audio
with my_mic as source:
File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/speech_recognition/__init__.py", line 138, in __enter__
self.audio.open(
File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/pyaudio.py", line 750, in open
stream = Stream(self, *args, **kwargs)
File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/pyaudio.py", line 441, in __init__
self._stream = pa.open(**arguments)
OSError: [Errno -9998] Invalid number of channels
>>> how do I fix this
please show how can he set a timer or start a song or do math pleaseeee
when the program needs to play the voice.mp3 second time, it gives permission denied voice.mp3 error. can anyone help me pls
Gökhan Tekir This issue was resolved. You can find the updated code in the Tech with Tim website.
@@zenjacob9155 thank you
@@zenjacob9155 sorry i couldn't find it. Can you pls help me
Gökhan Tekir sure, just a min
Gökhan Tekir
Firstly, use “pip install pyttsx3” in command prompt to install pyttsx3
Then use the following code in your program:
import pyttsx3
def speak(text):
engine = pyttsx3.init()
engine.say(text)
engine.runAndWait()
As you can see, this does not require any mp3 file to be saved, so you won’t have to face any issue regarding that. Hope this helps! :)
Sir, please use hotword detection in the program.... i Google many stuff. found two to three services works on python firstly 'snowboy hot word detection' the problem is that its not working on windows. secondly 'picovoice/porcupine hot word detection' which also work on windows but problem is that they made the script for console based and i am not a professional python program because of that i can't implement it on IDE but you can do it.. you have the skill to add it on IDE so please add that on your program. if you need any kind of help for that i will be there in any time... & love from India❤️
thanks.
After 4 or 5 times it takes too long time, how can I fix this issue to enhance the performance, by the way Awsome video
I’m going to look into it and see if I can fix it!
@@TechWithTim Cool 😍👍
@@TechWithTim its been a year and u still have'nt fixed it. Comeon man it was one of the best series
Hey, Tim can I get whole source code??
Can you share tho code please?
how to change the language and put it in FRENCH
Hey Tim!
When I tried it, it says: PermissionError: [Errno 13] Permission denied: 'voice.mp3'
It would be great if anyone could help me with this. Thanks a Ton!
Can I get source code ?
Source code please..
umm, I have been searching and searching. But I haven't found it yet. Away for your voice to be distinguished over someone else. The Correct term for this I believe is Speaker Identification.
Im looking for something like this too did you found it ? i also want like noise cancellation so that it can understand the input
@@saadmansuri4092 No Unfortunately I have not.
The only thing I could think training a neutral network on your specific voice. With recorded voice recognition patterns.
@@1215cubs Oh i see... yep, makes sense.
bro please give the source code
It did not work bro
what is not working?
@@prashasthnair9198 The whole thing bro
@@prashasthnair9198 But I like Tech with Tim