ฝัง
- เผยแพร่เมื่อ 23 ก.พ. 2023
- In this tutorial, we will guide you through the process of creating your very own GPT-3 powered voice assistant with Python. Say goodbye to asking Siri questions she can't answer and hello to a smarter personal assistant.
We'll take you through the process step by step, explaining each line of code, so you can follow along even if you're new to Python and AI. This project is a great opportunity for anyone interested in learning more about ChatGPT, Python, Saas and Artificial Intelligence.
Don't miss out on this opportunity to expand your AI skills and create your very own personal assistant. Watch the tutorial now and start building your AI-powered personal assistant!
No code ChatGPT Voice Assistant: voigpt.com
Official Ai Austin Discord: / discord
Help me make more videos:
www.buymeacoffee.com/aiaustin
#ChatGPT #gpt3 #python - วิทยาศาสตร์และเทคโนโลยี
Build Your Own GPT-4o Voice Assistant in Python with Groq, Llama3, OpenAI-TTS & Faster-Whisper
th-cam.com/video/pi6gr_YHSuc/w-d-xo.html
idk if i commented before but i really enjoy this. its simple to understand and easy to follow especially youre clean code and the use of comments makes it verry easy to code allong and to customize stuff as needed.
I have just tried to do something like this for my program, but you are the first one, thank you very much, great job. Now I will use it for my program. Thank you.
Can you make a video showing how you doing this avatar talk. Cheers
+1
I would love to know how....
It's actually easy you first generate a face of your choice on midjourney or dall-e and you import that picture in an app like facedance, ifunface, speakpick, etc..
Unreal Engine Metahumans can do it but it is intense, Metahumans looks more realistic also
Cheers
Great video! I found it really informative and helpful. Thanks for sharing your knowledge and expertise with us. Looking forward to more videos like this in the future!
The avatar is so well made, every one i saw blinks so much but this one does it at a reasonable phase.
Thanks laddie! I've been scratching my head with assemblyAI for days to make this to work, this went seemingly!
i know right assembly ai is so much money
Try the updated tutorial with GPT 3.5 Turbo, OpenAI Whisper and an open sourced Bing AI API:
th-cam.com/video/aokn48vB0kc/w-d-xo.html
Bro Can You Please make a Tutorial video of making The Avatar Video Like You ❣️
INSANE.....already an update.... hahaa this is nuts man.
J
that ending had me cracked up, thank you for that
Can you make it for Android?
Very cool, make it and I'll use it, especially would love it if we could upload a Mid-journey etc talking avatar of our choice (or photo that could be adapted).
Thanks Mate! Through this i was able to completly copy famous Chatbots like Siri or Alexa and thanks to the python statement "in", i was able to create a bot, who can filter my commands from whole and variable sentences. My Bot almost feels like a human teacher i can ask any question 😁 ... well ... almost ... davinci seems not to be able to tell the correct date and time since both is created from learning and not from actual live data (i asked GPT directly, Davinci refused to give me a usefull answer 😂)
I had some problems with the speak and talk part, so it ended up like a chatbot that works with "hotkeys"/command triggers for input to make specific things. Like, command trigger "music" opens a youtube playlist and things like that. I'm happy with the results :)
edit: now It can "talk"... I generated some phrases on viocevox, downloaded the audio files and made it play along with the texts in the code at some key points
can you please share your code with me? im interested in the music part. thank you :D
you prolly doing it in windwos. the say function doesnt work in windows its the same case as mine.
Bro, can you please share your code? I kind of need it for a school project.
I'll make it worth your time I swear!
If you are looking for a topic for your next video, I would love to see you take this to a web interface using flask. I have been trying so many different ways from other videos but always end up in a dark rabbit how with a chatbot, unable to find something that works. It keeps recommending code that breaks in so many ways and loses the original function that was working.
this is a great tutorial!. I really love it if you upgrade it. What i mean by upgrade is that, import the python programme in to any type of device such as arduino or raspberry pi ( If possible). Make it wireless.
Great example, well explained and acutally works. I have tried multiple youtube examples and forever end up in a rabbit hole spiral with chatgpt providing corrections to then only create further errors. I really liked how you explained each function and process. I was a great tutorial in provide clear and precise instructions that were very informative. Thank you.
Very glad that helped, Thanks for the feedback Marc! More python tutorials coming!
@@Ai_Austin Hi, i just wanted to ask about an error I am getting! I have done pip3 to install everything, and when I run it I get an error saying pyaudio wants installed. I go and do everything "pip3 install pyaudio" "pip install pyaudio" etc. Nothing is working, it does like half of it then says that "Could not build wheels for pyaudio" blah blah blah. Then it says that there's an error with "#include 'portaudio.h' ". Do you know how to fix this?????
@@PhoenixVids123 in windows it will show for me like that, so i am using raspberry pi the pip install pyaudio worked on the pi
You can make a iPhone shortcut with the api. It’s one response though, but works really well. Using your api key. No programming needed.
This is a really good video compared to most on here. Cheers
This is really helpful stuff, this level of quality get an insta like from me
I watched your video and really enjoyed it. Please make another project like this where it will be a mobile application and whenever I call genius it will respond like Siri or google assistant. And if you make a video let me know with a little reply.
In the end, I will say one thing, you are a wonderful teacher
I actually learned some things completely unrelated to the video. Thanks dude.
amazing! congrats
Amazing man....
this is good bro, thank you
lol the end :D nice one
Great video. As someone else mentioned, the code is a little small. In future videos would you be able to make it larger so it's easier to read.
that is the best animated avatar ive ever seen
Awesome!
Great! Good coding,
Thanks brother 👍👍
I made a similar code, it s very easy, but you can improve yours by saving in a txt file all the questions and answers so it can memorize what you said before.
You just have to give all the content of the file for each request
Simply, GENIIUS🤣
SOOOOO sick dude!! can you teach us how to implement an avatar to integrate it with the gpt responses? such as yours in the video
Great tutorial, Austin. Simple, to the point. Would it make sense to upgrade this to the Turbo model now? Also, could you do a tutorial about fine-tuning {prompt: x, response: y} to clone your friends using chat history data?
Absolutely. If you just change the engine variable in the open ai function of the code, you can just specify “gpt-3.5-turbo”. Then it will send your prompts to the new version of the API.
Fine tuning is absolutely in the video pipeline. Have a few others ahead of it but will be creating a fine tuning tutorial here soon.
@@Ai_Austin looks like fine tuning is not yet available for Turbo. I've tried with DaVinci without much success
@@Ai_Austin Hmm I'm getting " Engine does not exist" error... What am I overlooking?
@@sebaccimaster it s not working like that you have all another syntax for the completion. Look in internet you will find your answers
thanks buddy!
I understood nothing, but damn IT stuff and programing is fascinating, it would probably take me 1000 years to learn it, that is why all I can do is admire people like you.
I bet you could learn it. Its not reserved for some super high iq humans. Checkout the free online book “automate the boring stuff with python”. Give yourself a month. Study it 1-2 hour 3 times a week, this program will look like fluent english!
@@Ai_Austin thx buddy, I'll give it a try :)
"That sounds like NLE CHOPPA" ahahah you got me there m8 love the video
Nice i try next
Looks cool bro
Great！
This can be very beneficial for those who may have a disability. Very cool
WOW you are an incredible tutor
i have been an instructor/teacher for 30 years now and i NEVER seen code writing and concepts explained so clearly and understandable like you just did here
explaining and teaching code is not so trivial as many would thing and there are plenty examples for that on the net
GREAT video (and note that im not even talking about the specific content itself) keep up the good work,
SUBSCIBED
c'mon bro really? you've never in you're 30 whole years of teaching never seen it explained better amongst professional teachers? I mean sure the video is informative but c'mon.
Genius
Bro this is so cool
Hello, loved the video works wonders.
Would you be able to make a video series on how to add other features? such as opening apps, opening websites, setting alarms, adding a todo list & having it speak at cirten times of the day, say you want an alarm at 7am the bot would say good morning (name) today is (Date) with the weather being (weather info) & so forth I think it would be really cool
Thank you for your advice! It worked for me! It's great! And I received some help from GPT-Chat too!
Hi, please do you know how to run the script in windows using VS code? I'm a junior developer trying to run this code and dont work :( I have already python installed in my pc. Copy and paste the code, paste my OpenAI apy key in place, run the python3 app.py in a VS terminal but did't work
@@carlosmontes7088Hi, Carlos. Did you solved your problem? Bc i have the same...
@@marekkupis3086 Hi, No, I can't solve yet :( if you can solve anytime please let me know. I'm almost sure it is about a configuration that we don't know. Maybe install a dev dependency or something
@@carlosmontes7088 Hey Carlos I was using VS Code today to run the script and it worked perfectly. Just had to rewrite it a bit. Moved the generate response function above transcribe audio to text in order for it to work.
This is all cool, but what if you wanted to do it with ChatGPT-4? Or are the libraries for it not available to the public yet?
can you make this with GPT4all? would love to see a video on how to get this running on a offline system since you dont want to be depending on their model, if it gets out of hand we need backup models
Thanks Austin and increase the font size in the editor next time
Great video austin but my program cannot access the voice of the microphone. Do I need to save my voice as a file for this program to recognize
Can some explain were we are headed with but me its gonna be wild 😂 loved the Dis-song😅🎉
Beultiful pipeline this channel.
Had to get rid of the underscore in speech_recognition to get that to work. And I had to run pip install pyaudio to get it to work, but it works. Does this thing have contextual memory? Will it remember by conversations with it? I don't see any logging or context, so I don't think it does.
Very interesting. Thanks. What software do you use to create teh talking head? Thanks.
awesome, I love this. how you do the animated face?
the video was good and i followed it but al last what files Did you download while you were running the programm can you tell and if i want to convert the voice to jarvis's voice how can i do it
insane !
Not sure if anyone asked you this... How did you create your AI visual in place of your face?
I'm totally intrigued!
Man it's been a year! wow! what a year!
You can also use a shortcut and use your api key to it use it there you do have to say what you named the shortcut tho but that’s about it
will it run the same on python or do I need to change something? because I'm trying to run it on Python and it does not run like VSC.
Thanks for the great video :)
One nit-pick, the text is so small it's a struggle to read, I'm constantly leaning into the screen just to know what I'm looking at. There's heaps of dead space around your avatar, maybe consider zooming in a bit on your next vid.
This is amazing 💯, it would be cool if you could also create a video on how to control other applications, using this module, btw is it possible ?
Yes, absolutely possible.
Which AI tool you use avtar and voice-over
Thanks for video
How did you make the avatar to talk? (The guy talking). Do you have a guide for yhat?
with sr.Microphone() as source:
recognizer sr.Recognizer()
audio = recognizer.listen(source)
its highlightin "sr" as an error and when i run it it says invalid syntax, and when i try to pip install the library it says that its already installed
This is a good video it could be even better though with a release of GPT 3.5 turbo if you would take and show this again using GPT 3.5 turbo and whisper I think he would have a lot better response and a lot of people will really jump on wanting to do this. Thanks.
I have been researching Whisper. Its barrier to entry is a lot higher. Meaning if you want to run Whisper without having to pay for every question to transcribe, it needs to be done locally. Which puts you in the position of either needing a PC with 10+ GB of video ram.
I also have not seen any evidence that the whisper api performs better in transcription than google speech recognition. OpenAI is the hype but I don’t want to make people feel obligated to shell out money for something that is currently possible for free.
If one needed offline transcribing and has a beast of a pc to power the python program, Whisper would be a great choice.
I think today’s computers are probably powerful enough to handle text to speech I am a blind individual and I use several apps on my phone on my computer that dude just this kind of conversion and they’re not high power apps or high power computer. Some of them sent off to the Internet for processing but one of the things that could be done. If CPU horsepower is a real concern is push it off to the GPU most computers have Decent graphics processing units that would process much faster than a CPU ever could and it doesn’t take a lot of code to do that.
I do think there’s a little more involved in writing code but I don’t think it’s any strong barrier. I think it’s just something Hass to be learn how to do. I’m in the process of trying to learn some of these things myself and I don’t see it as difficult as what you think it might be Again being blind it’s a little hard for me to quickly ramp up to the stuff but I’m getting there
how did you create the host animation..please explain
This is great, and I'd love to try it, but the text is so small and kind of blurred that it's a challenge to make out the code. Will you add it to the description or pinned comment? That'd be really helpful.
I would love to combine this, with the Elevenlabz AI voice I make, to create a Juiz AI for me and my friend lol.
Is there anyway to attach this kind of virtual assistant code to a virtual avatar that can respond like the one in this video?
How did you create your avatar and his speech? It sounds much better than the pyttsx's generated voice?
It's 11labs probably
Bro you're just awesome,
Can U please make an app like this...
Coming very soon! 🫣
@@Ai_Austin thanks broooo
will figure this out.
22hrs later , i got it to ask me
"Say 'name' to start recording your question..."
but this pops up.
"Audio file content:
b''
im assuming its something to do with the speech recognizer not picking up audio. ( the input.wav was created byt 0 bytes . ) not sure what to do next. if anyone else had this problem let me know the corrective steps please ^_^
11 hrs later , i got it to work! the first time i ever used python or any coding program tbh.
Currently working on integrating some Amazon API's to make the a much more usable experience. Including no wake word. I have 0 technical background but in the last 6 hours with the help of chatgpt I have a working model
My goal exactly with these tutorials is you add your own preferences and upgrade upon these. Super cool to hear you’re doing it with no coding background man!
This video is deeply unsettling to me. I love it
Wonderful
Thank you! Cheers!
Can u help me? The code is all correct but there is a huge error saying that google is not an attribute in the module recognizer
please show us how to make a vatar like yours that's really cool
Awesome :), will this work on a raspberry pi?
Do we already have an app on Google or apple Play Store that works as a gpt voice assistant and speaks using out of choice Avatar of choice?
Sure, here's an improved version of your statement:
"I used ChatGPT to analyze the script of this video and engaged in a conversation where ChatGPT3 generated a micro-detailed strategy to guide you through every last detail that you might need to know. In summary, during our conversation, you asked about creating a GPT-3 powered voice assistant with Python. I provided you with a step-by-step guide that covers everything from importing necessary libraries and setting up the OpenAI API key to defining functions for transcribing audio to text, generating responses, and speaking responses. We also discussed the importance of error handling and adding additional features to improve the accuracy and usefulness of the voice assistant."
Opa
help please it says An error occured: You exceeded your current quota, please check your plan and billing details.
Is it functional like google? I wanna use it to command a moving equipment or device. Does it support different languages?
What program are you using ?
LOL, I built this app thinking "oh I'll to the old one becuase it will be less complicated" I finally got this thing to work and my AI is dumb as a brick, good exercise but now I will build the newer version.
😂
Yeah it's crazy how fast these things are advancing. My newest Gemini tutorial would be my recommendation. It's going to be the smartest, fastest and I put a lot more work into that video to make it as thorough as possible.
It being longer doesn't make it harder. It just is a a more thorough tutorial!
What do you use to generate your animated AI avatar and voice for that avatar (narrating the video)?
yeah! how did you code the talking avatar
This looks super nice, beautiful tutorial !!
Is the code attached here some where ? or in git ?
Damn I was thinking about it this morning, but it appears that someone already did it 1 month ago before me.
so i'm having a slight problem when i say genius after starting the bot it comes back with: An error occurred: local variable 'filename' referenced before assignment. is there a fix for this?
Awesome Video
Thank you 🙏
Great video !. what if you add the talking avatar feature to the ai assistant like the one in the video?
Thank you 🙏 That is the future but for now the tools to do it would make an extremely expensive and slow assistant
Opa quero ver
Can you do a video of this for gpt-4?
Hey, nice tutorial, but can you let me know if there is a way to change the voice of the model? If yes, how?
Thanks!
Yes we can modify parameters of the tts. Ask chatgpt how you can modify the parameters of the tts and you will have a little code snippet. just copy and paste the three lines after the initialization, you can modify the values for testing different voices and speech rates
i got it to say "say "Genius" to start recording" but it still wont work due to gTTS not working, it says on line 66, col 35 that theres a problem and it cannot be defined
Hi, how do we change the voice to sound a bit like normal voice. And how do we make this work like google AI. For it to come up on our phones when we say 'Hey Genius' Or just call her name.
Hi ! I love this video, but once I have the code, how I can launch the program ? (run the program don't work) 🥺
Is it possible to retain a session-like memory of previously asked questions with the API like we can do on the ChatGPT web interface?
For instance if I ask "Where is the oldest tree located"? and follow it by "How tall is it?", can we make API responses retain the context?
Using 3.5-turbo it is possible to have contextual memory. It would definitely add some complexity and would potentially want to create a command to refresh memory if you did so.
it s very easy, you just have to save your questions and the answers in a .txt file , then you give for each new request the content of the file !
Great video 👍🏻 do you have the code on Git or available anywhere?
*Le: dot
could you redo this for the new GTP 3.5 turbo API?
How did you create that animated narrator on the screen?
Better that a picture if IT --ar 3:2 Residents of TH-cam
cannot access local variable 'audio' where it is not associated with a value (error) How do I fix