I am just amazed by how quickly you make a video on the latest news/releases. If you can share which habit/practice/tools you follow to be consistent and always at the bleeding edge of technology. It will be super helpful.
Great information, thanks for supplying everything. I've been looking for something like this for a project. It's just a shame about the delay/lag before getting a response.
Very nice TTS demo video. My voice sample app finally run on MacOS after adding: virtualenv -p python3.9 env; pip install ipython; pip install ffmpeg-python
Hey, would it be possible to make it simmilar to an amazon alexa in google collab? The microphone is always on but only captures the input after you say an activation keyword and only ends when you say an ending keyword? I've tried to do so but keep failing....
Good demo. However it would be great if you can build the voice assistant as an App that takes input and replies to you after processing it , without clicking on submit . Basically an interactive bot with continuous inputs and continuous outputs , for example Alexa or Siri . The answers provided would be by GPT4 itself.
My code is not working and you directly jumped to google colabs with is totally new to me, I try but god knows what it was installing . Any suggestion how to succeed in this.?
disappointed.. wrote the complete code by myself first and it just showed "403. That’s an error. That’s all we know." after executing the gradio cell. Also, then I tried to run your file - I faced the same error. Gradio isn't working probably. Please help fix this.
@@1littlecoder yes, I basically want to set the create a help desk ticket using voice commands ,for this I need to send user said data to help desk api
Great work brother🫡. Is there any way to make it sound like me( voice clone my own audio) any great open source options for making my voice model apart from corentinJ which i tried already. If you could show a way around that would be really helpful brother.
How to make pyttsx3 work in colab? I stuck on "engine = pyttsx3.init()" . the error shows: "OSError: libespeak.so.1: cannot open shared object file: No such file or directory"
When trying this an error occurs ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. tts 0.11.1 requires numpy==1.21.6; python_version < "3.10", but you have numpy 1.21.0 which is incompatible It means TTS needs numpy 1.21.6 while my runtime has 1.21.0 so I wrote this !pip install numpy==1.21.6 you can also uninstall numpy first !pip install numpy and then again install !pip install numpy==1.21.6 you might need to restart you runtime
@@1littlecoder yeah, the answers GPT 3 provide are verbose. But I look forward to the near future where we can have a very life-like conversation with shorter form more appropriate responses; with interruptions and much quicker processing time. Exciting, unprecedented, powerful, scary, dangerous.
Thanks for the great video, it helped me a lot. Is it possible to create a personal voice assistant that uses pdf files with langchain? Thanks again :)
Hi bro.. My kind request is that you can test it again.. because from yesterday night itself there will be error showing that unexpected end of JSON input. Kindly help me sir. Before that the code is fine but from yesterday night and till now it make bugg and showing the error. Kindly help me sir
Thank you again for your amazing work but the line of code "from TTS.api import TTS" is not working 😐 , they say to me : ImportError Traceback (most recent call last) in 2 import gradio as gr 3 import openai ----> 4 from TTS.api import TTS 11 frames /usr/local/lib/python3.8/dist-packages/numba/__init__.py in _ensure_critical_deps() 138 raise ImportError("Numba needs NumPy 1.18 or greater") 139 elif numpy_version > (1, 21): --> 140 raise ImportError("Numba needs NumPy 1.21 or less") 141 142 try: ImportError: Numba needs NumPy 1.21 or les
Great work brother🫡. Is there any way to make it sound like me( voice clone my own audio) any great open source options for making my voice model apart from corentinJ which i tried already. If you could show a way around that would be really helpful brother.
Defiantly You are not a little coder, you are the best talented coder in youtube
Ah Thank you
Appreciate your amazing work !! Keep making and sharing
I recently started following you and I want to thank you for giving such clean explanation of these concepts… BTW, great Italian Air Force t-shirt!!
Great observation. Thank you !
Way to go! Thank you for keeping it beginner friendly :)
I am just amazed by how quickly you make a video on the latest news/releases. If you can share which habit/practice/tools you follow to be consistent and always at the bleeding edge of technology. It will be super helpful.
Thank you, I'll try to make a content on it!
@@1littlecoder Hi used your code but in the end it is showing error sting do not match with the pattern
I'm gonna learn everything from you❤️
neenga legend thaan
Very impressive and the output sounds great.
What was the text to speech model you used? ElevenLabs is probably the best one I've heard so far.
I was using Coqui
Some how I always learn something from you, thanks 🙏
Beat video yet! Great PoC.
Glad you liked it!
Great information, thanks for supplying everything. I've been looking for something like this for a project. It's just a shame about the delay/lag before getting a response.
This was very helpful, thank you so much. :)
You're very welcome!
Very helpful! Thanks.
Glad it was helpful! You are welcome
Very nice TTS demo video. My voice sample app finally run on MacOS after adding: virtualenv -p python3.9 env; pip install ipython; pip install ffmpeg-python
Amazing! Thanks a lot!!!
Hey, would it be possible to make it simmilar to an amazon alexa in google collab? The microphone is always on but only captures the input after you say an activation keyword and only ends when you say an ending keyword? I've tried to do so but keep failing....
Can I hire you to build a conversational ai for me?
Thanks very much
Wow this is amazing can this be accessed anywhere.
Is this your actual API key at 8:00 or a random string :)
It's an actual API key. I revoked it after the video :)
I've explained the same in my previous Python API video
It is showing error as gradio. Inputs is deprected ...
Need help
Well Done
can we add this in our resume as major project?
Absolutely
@@vanshikarathi2356 that would require lot of code changes
Very helpful. Thanks. How much would you charge to make this a mobile app on Android and iOS?
Flutter ;)
Good demo. However it would be great if you can build the voice assistant as an App that takes input and replies to you after processing it , without clicking on submit . Basically an interactive bot with continuous inputs and continuous outputs , for example Alexa or Siri . The answers provided would be by GPT4 itself.
I am getting an error unexpected end of json input after recording the audio. Please help me I have tried fixing it but no use.
My code is not working and you directly jumped to google colabs with is totally new to me, I try but god knows what it was installing . Any suggestion how to succeed in this.?
disappointed..
wrote the complete code by myself first and it just showed "403. That’s an error.
That’s all we know." after executing the gradio cell.
Also, then I tried to run your file - I faced the same error.
Gradio isn't working probably.
Please help fix this.
Do you have debug mode on ?
When you launch the gradio application add (debug = True) as an argument and let me know what error is there.
Also do you have ad blocker or brave browser?
Are you available for hire for a project?
Is it possible to integrate this bot to crm ?
Can we deploy this? I have tried in several ways but everywhere it is throwing errors, please let me know how to deploy it.
How do I change the voice sir?
Can I use the message context to make a call to an api …basically I want to configure the output based on question asked
Can you please elaborate the question?
@@1littlecoder yes, I basically want to set the create a help desk ticket using voice commands ,for this I need to send user said data to help desk api
How do I make this into a web application?
The gradio application I showed you was a web application.
Can I do this in Flutter flow?
Great work brother🫡. Is there any way to make it sound like me( voice clone my own audio) any great open source options for making my voice model apart from corentinJ which i tried already. If you could show a way around that would be really helpful brother.
How to make pyttsx3 work in colab? I stuck on "engine = pyttsx3.init()" . the error shows: "OSError: libespeak.so.1: cannot open shared object file: No such file or directory"
is it possible to run this locally to reduce the lag time?
if you have got GPU whisper and TTS would be faster.
can i use it in my flask app as file af python ?? please reply soon
Why would you want to use this in flask?
Great information, thanks for supplying everything. But I am getting "Unexpected end of JSON input" error. So how can I fix this?
Do you know if the recording happens properly?
@@1littlecoder ya i can hear the input recording properly
@@1littlecoder facing the same issue
@@1littlecoderI'm also getting the same error
Can you make a video on deploying one of these web apps?
What if I want to make this a Whatsapp bot?
My gradio application does not run 😶😶 Gives me 403 error
Did you try with share=True inside launch() ?
@@1littlecoder That Worked, Thank you
Hey how to use this api in javascript
When trying this an error occurs
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
tts 0.11.1 requires numpy==1.21.6; python_version < "3.10", but you have numpy 1.21.0 which is incompatible
It means TTS needs numpy 1.21.6 while my runtime has 1.21.0
so I wrote this !pip install numpy==1.21.6
you can also uninstall numpy first !pip install numpy
and then again install !pip install numpy==1.21.6
you might need to restart you runtime
You need to restart runtime of the colab notebook after you install the new numpy
Same problem but it doesn't work please help me
Please how to connect it all with whatsapp ????
If you found anything related to it, please tell me
see ya alexa 👋
Haha, this is is still far from that
@@1littlecoder yeah, the answers GPT 3 provide are verbose. But I look forward to the near future where we can have a very life-like conversation with shorter form more appropriate responses; with interruptions and much quicker processing time. Exciting, unprecedented, powerful, scary, dangerous.
Thanks for the great video, it helped me a lot. Is it possible to create a personal voice assistant that uses pdf files with langchain? Thanks again :)
How can I do this android
Sir iam getting the error please help me sir
Hi bro..
My kind request is that you can test it again.. because from yesterday night itself there will be error showing that unexpected end of JSON input. Kindly help me sir. Before that the code is fine but from yesterday night and till now it make bugg and showing the error. Kindly help me sir
Have the same error, did you find a solution ?
@@borisjuniorkoulevo yes bro
@@reelsgalataa3631 please let me know as well. facing the same issue
@@reelsgalataa3631please share the solution, facing the same issue
Can we make telegram bot with this code, and If yes then any video tutorial or anything can help, thanks in advance
LJ Speech voice!
Streamline the interface and add Cortana’s voice from Halo PLEEEEEASE
have you jailbroken your chatgpt yet?
do you have a telegram or discord group where i can join and ask questions
Thank you again for your amazing work but the line of code "from TTS.api import TTS" is not working 😐 , they say to me : ImportError Traceback (most recent call last)
in
2 import gradio as gr
3 import openai
----> 4 from TTS.api import TTS
11 frames
/usr/local/lib/python3.8/dist-packages/numba/__init__.py in _ensure_critical_deps()
138 raise ImportError("Numba needs NumPy 1.18 or greater")
139 elif numpy_version > (1, 21):
--> 140 raise ImportError("Numba needs NumPy 1.21 or less")
141
142 try:
ImportError: Numba needs NumPy 1.21 or les
exactly same error
You need to restart runtime of the Google Colab after the numpy installation
Thanks! great video!
Great work brother🫡. Is there any way to make it sound like me( voice clone my own audio) any great open source options for making my voice model apart from corentinJ which i tried already. If you could show a way around that would be really helpful brother.