Create a Smart Voice Assistant using Open AI's ChatGPT, Whisper, Python & Gradio | Python Project

In this video, I'll show you how you can create your own Smart Virtual Assistant like Google Assistant using Open AI's ChatGPT, Whisper. The entire solution will be created using Python & Gradio. OpenAI's ChatGPT launched just 5 days ago and already crossed 1 million users. ChatGPT is a prototype artificial intelligence chatbot focused on usability and dialog. Developed by OpenAI, the chatbot uses a large language model trained using reinforcement learning and based on the GPT-3.5 architecture. OpenAI's ChatGPT is a large language model that was trained to generate human-like text based on the input it receives. It is based on the GPT-3 (Generative Pretrained Transformer 3) model, which is one of the most advanced language models available. ChatGPT can be used for a variety of natural language processing tasks, including generating human-like responses to questions and prompts, summarizing text, and translating between languages. Open AI's Whisper is an automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web. The use of such a large and diverse dataset leads to improved robustness to accents, background noise and technical language. Moreover, it enables transcription in multiple languages, as well as translation from those languages into English. OpenAI has open-sourced the models and inference code to serve as a foundation for building useful applications and for further research on robust speech processing.

OpenAI, the company best known for Dall-E - the AI-based text-to-image generator - introduced a new chatbot called ChatGPT. ChatGPT is a ‘conversational’ AI and will answer queries just like a human would– well, at least that’s the promise and premise. So one can ask ChatGPT for anything; The reason ChatGPT has gone viral is because of the kind of responses it gives, being seen as a replacement for much of the daily mundane writing, from an email to even college-style essays. OpenAI has created ChatGPT, a start-up focused on artificial intelligence and its potential use cases. According to OpenAI’s description, ChatGPT can answer “follow-up questions”, and can also “admit its mistakes, challenge incorrect premises, and reject inappropriate requests.” It is based on the company’s GPT 3.5 series of language learning models (LLM). GPT stands for Generative Pre-trained Transformer 3 and this is a kind of computer language model that relies on deep learning techniques. The model is trained to predict what will come next, and that’s why one can technically have a ‘conversation’ with ChatGPT. According to OpenAI’s blog post about ChatGPT, the chatbot was also trained using “Reinforcement Learning from Human Feedback (RLHF).” One can go to the OpenAI website and sign up to try out ChatGPT.

*I use affiliate links on the products that I recommend. These give me a small portion of the sales price at no cost to you. I appreciate the proceeds and they help me to improve my channel!

Equipments I use for recording the videos:

If you do have any questions with what we covered in this video then feel free to ask in the comment section below & I'll do my best to answer those.

If you enjoy these tutorials & would like to support them then the easiest way is to simply like the video & give it a thumbs up & also it's a huge help to share these videos with anyone who you think would find them useful.

Please consider clicking the SUBSCRIBE button to be notified for future videos & thank you all for watching.

You can find me on:

#chatgpt #gpt3 #openai

[bhattbhavesh]

All of you asked for it - Here is the voice assistant video with ChatGPT API and voice output :)

[RedBricksTraffic]

very nice demonstration. The untapped potential of chatgpt is truly mindblowing.

[JessieJussMessy]

This is the content I was looking for. DING!

[Klocksby]

Awsome, we are living straight in a SciFi-Movie

[alx]

You can do the same with local whisper and GPT-2 or GPT-Neo(X) - and everything will be running locally without a byte being sent to internet

[avidesmond]

Great video, keep doing what you're doing!

[emoutraspalavras-marloncou]

Thank you so much. Can you code the logo of ChatGPT to be showed on a screen with randomly moving sound waves and cutting across the middle of the logo as the voice sounds? I would love to have that in my spare screen connected to a Raspberry pi and some Esp32 through WiFi for some home automation.

[DhananJayShembekar]

This is brilliant, i am pretty sure you can take the output from chatgpt and use some other python library speak that out.
But this is enough to showcase.

[wordpressobsessed]

Would you be able to do a video that uses a Twilio voice and/or SMS to interact with GPT? So the idea would be to text a question to a phone number and ChatGPT would text you back with the response. Or, call the number and ask the question with your voice, and ChatGPT responds via a voice like Amazon Joanna. Possible?

[tudev]

dios eres un crack, aun nose de python pero esto es very very gooddd

[roshankazani]

Hi Bhavesh, Thank you for this amazing video. Can you please guide us on how to create a text to speech interface as a continuation of this project. Amazing video. Thanks again.

[the_podcaster]

Bhavesh, you did amazing with the explanation, could you also add the output text in voice?

[Naranek]

That's mind blowing. Can you port this to a Raspberry Pi as a standalone solution?

[divineigbinoba]

Please how did you perse the output from wisper to chatGPT?

[jalexander]

Inspiring, Mr. Bhatt, your work here is outstanding! I've added voice-output to your Gradio UI using gTTS. However, when I link to the google colab notebook, youtube removes my comment :(

[nat.serrano]

I like the video, what are the advantages of using text to speech (whisper from openai) over SFSpeechRecognizer in swift?

[gadwal]

How's it working with Hindi? both Whisper and ChatGPT. ChatGPT doesn't seem to work well with Telugu. So just curious.

[danielpollock]

how can I add this to google smart home now or alexa so I can speak from anywhere in the room by saying some trigger word to listen like and respond output like "hello google" for example?

[KolTregaskes]

This is amazing, thank you. I'm not a coder but I have a list of apps and Python code I'd like to create with ChatGPT. Hopefully I can get to them before they start charging for using ChatGPT. 😉

[bjr]

Hi Bhavesh, how can it recognise distinguished or distorted speech?
plz reply asap..tnq