Coding My Own Virtual Voice Assistant | OpenAI Whisper & StreamLit

In this tutorial we will go through an end to end coding project , where we will build a virtual voice assistant built on OpenAI Whisper , Python and Steamlit in 25 minutes. This is a great starter project for someone who wants to build a voice enabled AI assistant.
#openai #gpt4 #python #streamlit

[@sierraryan3229]

Great tutorial! Could you share the code?

[@eugenmalatov5470]

this is a great tutorial.
+ i have been struggling with the autoplay. Thanks for explaining a solution
- your bot does not have memory
I am surprised that everything is so fast. Streamlit is very slow on my computer.

[@novadocnews]

OMG!! FINALLY! Thank you so much for your tutorial. I have spend weeks searching for one that actually works because most tutorials are outdated and only give back errors. I am not a programmer (Im trying to learn) and yours is the first AI Voice assitstant that actually worked to perfection. I would like to ask only if you could recommend a way to add a function for giving the ai memory so it can follow a conversation? In the past I used something called "conversationbuffermemory" function.
Thank you again and best wishes from Mexico!😊

[@SunilSamson]

if you are using streamlit then you would need to initialize a session_state to have a conversational bot

[@isa-bv481]

Hey, this is really great ... at least until I tried to run & test the part as of 17:38 in your video. I get essentially the error TypeError: 'str' object is not callable (see traceback below). However, I installed Pytorch, CUDA, ffmpeg, whisper and I tested it - in the command prompt my recorded audio is translated to text correctly. It drives me crazy. I'm about to reboot my PC and try again, but if you have any hint... it would be very welcome.
Traceback:
File "C:\Users\MarcDeValckenaere\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\streamlit
untime\scriptrunner\script_runner.py", line 535, in _run_script
exec(code, module.__dict__)
File "G:\My Drive\KENNIS\STARTUP\projects\AI Voice Assistant\app.py", line 60, in
main()
File "G:\My Drive\KENNIS\STARTUP\projects\AI Voice Assistant\app.py", line 49, in main
transcribed_text = transcribe_audio(client, audio_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\My Drive\KENNIS\STARTUP\projects\AI Voice Assistant\app.py", line 16, in transcribe_audio
return transcript.text()
^^^^^^^^^^^^^^^^^

[@mohanKrishna-zm3qj]

hi great u did this far same error i got,,,,did you found the solution ?

[@LiuGang]

Thanks for your sharing. It is a great one. Can you also help to share the code? Thanks.

[@Player-oz2nk]

Now we need groq integration!

[@robertgoldbornatyout]

Great tutorial! Could you share the code?😰😰😰😰😥😥😥😢😢😢😭😭😭

[@ArielYahni]

Nice!!!❤ did you share the code?

[@kevinoudelet]

Thank you for the code

[@vijayantkumar3705]

Can you share the code link?

[@_SUYASHPRAKASH]

@@vijayantkumar3705 did you got the code?

[@priyanka9672]

I do not get the microphone Icon

[@riddheshmore2315]

I was getting the same issue, after you run the file in your browser you could see 3 dot, under that click on Rerun and it was solved

[@_SUYASHPRAKASH]

@@riddheshmore2315 can you share the source code?

[@abderahimmazouz2088]

if you change the theme color from white to black it will appear

[@abderahimmazouz2088]

or set the appearnce to wide mode