- 11
- 27 803
Jesús Copado
Spain
Приєднався 9 жов 2024
Hi! I’m Jesús Copado, Lead Artificial Intelligence Engineer. On this channel, I explore the world of AI through hands-on projects that make complex tech accessible-think building your own Samantha from the movie Her. With a focus on AI, AI Art, and Python, I bring years of coding experience and a love for cinema to each video. Expect a mix of technical deep dives, movie references, and free resources to kickstart your AI journey.
For more information, questions or inquiries, visit my website: www.jesuscopado.com
For more information, questions or inquiries, visit my website: www.jesuscopado.com
This Voice AI Agent Runs SQL and Creates Charts Instantly | OpenAI Agent Realtime API Demo
📌 GitHub repo: github.com/jesuscopado/samantha-os1
The following is a demo of what I believe is the future of human-computer interaction: a conversation between me and a Voice AI Agent named Samantha. She acts as a data analyst, running SQL queries and creating charts instantly, all through natural, human-like conversation.
Watch as I challenge Samantha with increasingly complex requests-and she handles them with ease. This is transformative technology in action.
👉 What other features would you like to see in Samantha? Drop your ideas in the comments!
The following is a demo of what I believe is the future of human-computer interaction: a conversation between me and a Voice AI Agent named Samantha. She acts as a data analyst, running SQL queries and creating charts instantly, all through natural, human-like conversation.
Watch as I challenge Samantha with increasingly complex requests-and she handles them with ease. This is transformative technology in action.
👉 What other features would you like to see in Samantha? Drop your ideas in the comments!
Переглядів: 552
Відео
This AI Agent Could Replace Data Analysts: See it Run SQL Queries in Realtime
Переглядів 750День тому
👉 Text-To-SQL explanation: ua-cam.com/video/xdceFu78uOA/v-deo.html 📌 GitHub repo: github.com/jesuscopado/samantha-os1 In this video, I’ll show you how I built a Voice SQL AI Agent using OpenAI’s Realtime API. You’ll see a full demo of a mock bookstore database, featuring queries, charts, and even multi-tool scenarios like generating emails and automating workflows. Let me know in the comments i...
Build a Voice AI Agent That Runs SQL Queries Instantly | OpenAI Realtime API Tutorial
Переглядів 52714 днів тому
👉 Full Demo SQL AI Agent: ua-cam.com/video/QDxcjlIVdnA/v-deo.html 📌 GitHub repo: github.com/jesuscopado/samantha-os1 In this video, I’ll guide you through building a Voice SQL AI Agent using OpenAI’s Realtime. We’re taking Text-to-SQL to the next level by using voice commands for seamless database querying. Imagine running a SQL query with a simple voice command like “What are our busiest shopp...
Watch Me Build a Prompt + Image Generator App in Python | FLUX, Groq & Streamlit
Переглядів 6932 місяці тому
In this video, I’m coding a complete Prompt Image Generator App using Python, TogetherAI's FLUX API, Groq API, and Streamlit-step by step! I’ll show you how to merge various tools into one powerful app, from generating prompts to creating and saving AI-generated images seamlessly. Even if you’re just starting to learn Python, this video is perfect for you! With tools like ChatGPT by your side, ...
Ultra-Realistic AI Image Generation with FLUX 1.1 Pro | Ultimate Guide & Prompt Tips
Переглядів 3,4 тис.2 місяці тому
In this video, I’ll walk you through my complete process for generating ultra-realistic AI images using FLUX 1.1 Pro. We’ll cover why starting with a highly realistic image is essential for creating realistic AI videos and explore the best text-to-image tools, including Midjourney, Stable Diffusion, and my top pick-FLUX. I’ll show you how to use FLUX for stunningly realistic results and why it ...
Create Ultra Realistic AI Videos | My Full Pipeline & Hailou Minimax Tutorial (Free Trial)
Переглядів 7 тис.2 місяці тому
In this video, I’ll take you through my complete pipeline for creating ultra-realistic AI videos. We start by understanding why a realistic base image is key, move on to the full pipeline (trust me, text-to-video is not that simple!), and focus on how image-to-video tools like Hailou Minimax make a huge difference. I’ll show you how to use video generation tools like Runway Gen3 Alpha, Kling 1....
Guy with a Mustache Talks with Samantha | OpenAI Realtime API | Live Speech-to-Speech AI Demo
Переглядів 1,2 тис.3 місяці тому
📌 GitHub repo: github.com/jesuscopado/samantha-os1 In this video, you’ll see Samantha in action! Watch as I talk live with the AI assistant I built using OpenAI’s Realtime API. Get a glimpse of what a real-time, conversational AI experience feels like-just like talking to Samantha from Her! Chapters 00:00 Demo highlights 02:34 Outro
How to Build Samantha with OpenAI’s Realtime API for FREE! | Speech-to-speech AI Agent Explanation
Переглядів 4,8 тис.3 місяці тому
📌 GitHub repo: github.com/jesuscopado/samantha-os1 In this video, I’ll show you how to build your own real-time, speech-to-speech AI assistant, inspired by Samantha from the movie Her. We’ll dive into the Realtime API from OpenAI, exploring how it powers a seamless conversation flow, and I’ll walk you through every step to create your own AI assistant-all for free! Links to APIs/resources: - Az...
Watch Me Build Samantha: Full Demo & Code Breakdown | OpenAI Realtime API Conversational Agent AI
Переглядів 8 тис.3 місяці тому
📌 GitHub repo: github.com/jesuscopado/samantha-os1 This video includes a breakdown of the code and setup so you can follow along and build your own AI assistant using OpenAI's Realtime API Links to APIs/resources: - Azure Free Trial: azure.microsoft.com/en-gb/pricing/offers/ms-azr-0044p/ (200$ in Azure credits to spend) - TogetherAI's FLUX API: www.together.ai/blog/flux-api-is-now-available-on-...
How much you paid to use openAi API? As for me in start it said free credits ran out
a video dedicated to how to fine tune an LLM would be very interesting.! :D
Will work on that soon ;)
this is fucking awesome, as a quantitative analyst and financial markets trader I can't imagine how amazing it would be to have samantha with me, I want to marry her! y tu eres un pto genio amigo!
Brutal Jesus!
Gracias tío!
Excellent Jesus! keep 'em coming!
Thanks a lot! :)
Qué pasada de claridad y precisión de tablas y el rapport por voz cada vez es más limpio y orgánico. ¡Esto va muy rápido!
Gracias amor!
amazing work copado are you planning on making a longer video where you go deeper on how you built this amazing agent ?, if you are currently working on it then i can't wait for it this is pretty cool!
Yes! I explain everything about this in this other video: ua-cam.com/video/xdceFu78uOA/v-deo.html :)
do you have twitter?
Nou, but I do use LinkedIn. Why?
@jesuscopado-en somebody made a fake token of your project on solana and made a fake account there as well. maybe it would be a good idea to launch your own token i could help you with that (by the way your fake token reached 30M market cap, imagine what would happen with a real one)
advanced: finetuning LLM for sql agent ++
Cool you're interested! I'll work on that soon :D
You are doing a great job, which tool are you using to capture speech which the is coverted to text?
That's done via OpenAI Realtime API. It directly does speech-to-speech when it comes to developer user. Check out my first video on it if you wanna learn more about that: ua-cam.com/video/NJn1HDjLBns/v-deo.html
You are really amazing
Thanks a lot! :)
Thank you for making an illustrative demonstration. This is the first time I've seen a video from your channel. One thing I haven't quite figured out is why you use two LLMs; Grok and Llama. At first glance, one of them would have been enough. I'd appreciate it if you could explain why you used the two LLMs.
Glad you liked it! So I used only one model, Llama 3.3. And I used it on the Groq platform that provides very efficient LLM inference. They do have a veeery similar name to the LLM model called Grok from X hahaha. You can check this article to read about Llama 3.3 on Groq: groq.com/a-new-scaling-paradigm-metas-llama-3-3-70b-challenges-death-of-scaling-law/
Thanks (and happy birthday) Jesus!
Thank you!
This is genius. Love the stack and innovation here
Thans a lot! :)
Simple and really useful video!
Thanks a lot Giorgio! <3
So instead of a keyboard and a mouse we can talk to our computers? Would be great to have a swarm of drones to protect me and commendable by voice. THat I would buy.
I love love love this and thank you for sharing, how did you build your tools ?
Thanks a lot! Well, now I'm building them faster using Cursor. But usually just reading documentation, trying out things and having open discussions with ChatGPT :D
Great now my AI is going to get all emotional on me when I get upset from its hallucinations
Gorgeous lady 😍
espectacular
brutal
Que copado!
jajajaja muchas gracias! :D
i dont want Anything to do with openai ! they can keep their keys n apis n chatcrap to themselves. i like actual open ai like ollama n llama based models. one day ppl will say openai who ?
I'm also a big fan of open-source, if I can I'll use that instead of OpenAI/Claude, but it's undeniable they have the edge when it comes to these innovations like Realtime API
I have seen your UA-cam it's amazing. I have a question can you combine your all videos and make an AI Sementa live video when you asked her she responded that instead of audio make her a video with the expiration from the previous girl that you make emotion picture to video
I'm glad you like my channel :) That'd be complicated, cause the avatar video models and lip sync models are still very slow, but soon in for future for sure this will be possible!
brilliant! keep up the good work.
Thanks a lot! Will do for sure :)
Very Nice, All The Best
Appreciate it :)
Thank you; your explanation of the process and implementation nails it. All the Best
Thanks a lot :)
i need to use lora there
i hop you soon show us how to develop sono or Audio like ai
I'll work on that for sure soon!
Nice explanation 👌 looking forward to more from you.
Thanks a lot :)
Great vid!!! in what program and how do you make your subtitles with that style?
Video increible!!' Muchas gracias por la ayuda!!!
Jesus, what is the video you are referring to here? 7. Demo my app: prompt generator with Groq API + TogetherAPI FLUX API • API access means we can build applications on top of it • Refer to video where I build this live in less than 15 mins using ChatGPT Canvas and Copilot (100% Python)
Jesus, excellent! Yes, please, a video about prompt engineering to prompt more details. Thank you very much!!
Thanks Daniel! And I'll work on that one for sure soon :)
nice one! you can also add extra sauce codes using claude! but remember, this is their daily play at openai, they can rly make this in seconds or the real Samantha at this point, but they don't wanna freak the society! not yet! I'm pretty sure sama is using Skies voice exclusively on his phone, I'm talking about the real Samantha, but no one sees him using ChatGPT!
Buenas, muy bien este vídeo también. Sí, sería estupendo profundizar en ingeniería de prompts, a mí me interesa perfiles femeninos con enfoque fashion, pero no solo retrato, también half y full body. Gracias…
Genial que te haya gustado el vídeo! Pues dentro de poquito haré vídeo sobre ello, gracias por el feedback :)
Good job mate.
Thanks! :)
You should have more subscribes mate.
@@jesuscopado-en Im using your AI for my work right now
any high quality open source image-to-video options?
Yep, just recently Mochi1 was released. Check their repo: github.com/genmoai/models And playground: www.genmo.ai/play
I like your work. This is awesome. How can I build this for myself usisng the tools you provided? I watched the other video but still can't figure out the process. Where to start from?
Glad you like it :) Hhmm I'd honestly recommend to ChatGPT your way into understanding. If you're new to Python or programming, ask for the basics, then take screenshots or copy paste errors and ask for clarification, that would both help you learn and progress in the projects.
Great content. You got a follow, good sir ❤
Appreciate that 🫶
Nice. Do you have a tutorial for creating different angles of a character similar to this realness so that it can be later used for model training?
Will create one in the next days/weeks for sure! A LoRA tutorial for the best character consistency
Hi brother, I really appreciate the content of both videos. The question is, I have a model created with artificial intelligence and I want to make it more realistic and with better quality, then make a video with that image. How could it be done that way? Thanks!
Glad you liked the videos :) You mean you already fine-tuned a stable diffusion or flux model but you don't get realistic images? I'd say maybe work more on those images for your LoRA. I'll be posting a video just about that in the next days/weeks
Hi, getting stuck at Connected to OpenAI realtime: - the mic turns on and nothing else happens, no error codes even. API Keys set.
btw Together now only offers $1 of free credits.
Ah dang... Dunno what to tell you. Annoying to not have the error trace yeah. Maybe the endpoint is not correctly set... I'll soon update the repo with the latest Chainlit version (not the alpha) and maybe that helps.
@@jesuscopado-en Cheers! :D
Looks like gpt-4o-realtime-preview, 2024-10-01 is available only in eastus2 and swedencentral
Great video Jesus! Thanks for sharing. 🙏 Subscribed!
Glad you liked the video! :)
Nice explanation! What tool are you using for the subtitles ? It looks nice.
Glad you liked the explanation! :) I'm using screen.studio, a MacOS app. But that app uses internally the Whisper speech-to-text model from OpenAI to create those subs. And I'm sure many other tools implement Whisper as well
@ I use screen studio for videos yes! But I liked the captions here. You mean screen studio auto generated the captions for you ? Seems I need to double check my features list haha ha
@@soamjena hahaha, yep, directly in screen studio
Woah I’m in shock!!! 😮😮
Great video !
Thanks a lot! :)
can you create project like this without using azure ?
Yess, also directly using OpenAI API :) Just need to configure those env variables
@@jesuscopado-en can i use this project without using azure ?
The interuptability looks really good, 'she' shuts up quickly when you start talking
Yess, that's crazy good, and contributes a lot to the feeling of having a human-like conversation :D
Excellent synthesis of the sites from which to work with images and video using AI. There isn’t much content on UA-cam yet that explains so clearly how to understand and apply iterations with AI at this level. With so much progress in just a few months, it’s difficult to keep up with everything! The moustache plays a key and differential role here tho