How to build a real-time AI assistant (with voice and vision)

[@toddroloff93]

Incredible video. You're taking your content to the next level. Keep up the good work and thankyou for all you do.

[@ChefDomein]

Sir, your AI voice assistant demo's are one of the most valuable and appreciated youtube videos I have come across. Please keep them coming and also would be great to do a demo with Groq for solving latency issue. You are doing great work man and your students are really appriciating it! Thanks a lot brother!

[@ronsinolast]

Hi, this is great. I tried and its working. I tried to introduce my self, then I ask, "Do you know my name ?" the response is "I'm not able to remember past conversations." So, Can we make it remember the conversations, and also "remember" my face ?

[@scott701230]

That actually a good question. I saw a paper published about persistent memory: short term memory, medium long term memory and building an automated RAG system to automatically RAG information to long term memory, so we can create an assistant that’s goal orientated and proactively manages you and towards meeting your goals.

[@dheerajmadaan866]

This was a really cool stuff. Thanks for sharing such a quality stuff. I ran it on vscode and it worked. The main problem is the latency. It took like 10s for the conversation. Not sure if it is because of the free account or their websocket API has the issue.

[@riemannderakhshan1037]

You turned your videos to the next level which is pretty amazing. I would like you to ask if is possible, show us how to use open source models in those apps. Thank you in advance.

[@davieslacker]

Really cool stuff... I def plan to recreate some of these things along with you when I have a bit more time at my computer. Just a thought, adding screen capture in with this would be pretty cool too to get help with whatever applications you're in... I would imagine you could include both camera and screenshot images in the same context and it should be able to distinguish which you're asking about.. or build a different tool that it can function call for that. Can't wait until we get some slightly more expressive voices as an option like OpenAI teased us with.

[@ashishtandi4440]

Incredible!. I tried the same thing there is a noticeable delay. I am not sure if it is the TTS or STT or the LLM API itself. While yours and the default demo at Livekit is damn fast.

[@bimalnair]

Absolutely fabulous! Thanks for making this one! I loved it!!

[@moacirosa]

Amazing content with solid explanation. Thanks very much 👏

[@underfitted]

Glad you liked it!

[@iitjeephysics2789]

from livekit import agents, rtc ImportError: cannot import name 'agents' from 'livekit' (unknown location). I am getting this error.

[@codemonkey2k5]

Is there any way you could do a version of this that can use a locally run Ollama server? Even if it means that I lose the image feature.

[@johanransbygranberg2219]

My first thought too!!

[@SaddamBinSyed]

Hi ..thanks for the nice video.. Can we use local LLM (like ollama) instead of a paid one..?

[@solanobordim]

This could be very useful for blind people. Thank you

[@vincentzhong3920]

Sir，what is the latency？ same as gpt4o s demo or much longer？

[@huangphoenix]

Great video, keep going. Just wonder if you can add barge-in function?

[@mehershahzad-n5s]

Amazing 🙂

[@sumitdevraye9725]

Great video. Keep these coming.

[@7BlackJack8]

Can be used with google flash? Thanks for super content!❤

[@amazingvideos4824]

Man this is amazing Can we deploy it to cloud so it works from anywhere? I deployed it to heroku but its not accessing the webcam

[@ridhwanbakare3406]

This is really cool. As someone with python knowledge how would you suggest I get started? Any roadmaps or videos you published?

[@jameszhang2832]

Fantastic, thank you very much. How would you adapt your code if you have multiple participants?

[@user-yh2uz6fd7l]

Great info, thx! Is there a way to use local LLM (like ollama, local AI etc) on this platform instead of openai?

[@ainewsera]

I need this but with a face to talk to me in real time. Can you do this?

[@jimmywang6177]

very interesting! thank you!

[@mehmetbakideniz]

great video as always. Does this system keep chat history?

[@edgarl.mardal8256]

Hi, I am working on creating a closed lan-network, using per to per, and will input a live AI agent, locally stored, getting knowledge from LLM, and wonder if it is possible to have this kind of system then running without using internet?

[@ccouto2869]

oh my god, amazing, tanks

[@abdiasj3692]

would love to see how to to implement Deepgram TTS instead of OPenAI !

[@underfitted]

It’s actually very simple: simpler than what I had to do to get OpenAI working

[@abdiasj3692]

@@underfitted Hey thank for replying! This would be an awesome! Also using maybe openrouter as well! Wild ideas come to mind!

[@andriusem]

Hi, great video! How to change the source code that it captures my screen, desktop. Thanks.

[@sharplcdtv198]

your code generally doesn't run in VScode in windows... some things seem platform dependent unfortunately

[@underfitted]

I don’t think it’s a problem with my code… it’s a problem with Windows. Try WSL.

[@aaronwenniger7966]

now i keep running into troubles when using this code, I would love to be able to discuss this so i can get it fixed i want to implement some features to see if it can work for something else to.

[@AI_by_AI_007]

Yes the API keys do not pass -- what are you experiencing?

[@aaronwenniger7966]

@@AI_by_AI_007 Hi Yes, So i had to rework the code a little bit to get everything working again. And now its working great except that the voice of the AI is not working and i cannot give voice commands anymore.

[@Noahperaudon]

@@aaronwenniger7966How do you have do for the livekit api key ?

[@Noahperaudon]

How for the livekit api key ?

[@aaronwenniger7966]

@@Noahperaudon ?

[@reynoldoramas3138]

Hola Santiago saludos desde Cuba, acabo de ver en su perfil de Github que es un coterráneo. Su contenido es muy valioso, por aquí un ingeniero de IA tratando de salir adelante en este mundo. Me encantaría poder contactar con usted y ayudarle en algún proyecto.

[@insitegd7483]

Thank you, It is very interesting.

[@rithikkumar7683]

I hope we can we use gemini 1.5 pro? I will try to make this changes in old code

[@AmitMarx-ei8tt]

Got stuck with the API Keys, i'm not sure how to set them

[@twetemomedical9500]

Any one else not getting a response on the interface, it’s registering my commands by no response

[@user-yp8qr6kj2e]

I wish the code would process the timeline.

[@jock21341]

sir can you help me why my assistant isnt talking back or nothings happening but its recognising in chat what im saying

[@jeff_holmes]

Curious about the latency. I noticed that you cut the video after each question (after <a href="#" class="seekto" data-time="1195">19:55</a>), so I am assuming it was a few seconds?

[@underfitted]

It wasn’t bad, but GPT-4o is not as fast as it could be, so you definitely have to wait a second or so for an answer

[@vesalaasanen2158]

@@underfitted , would be nice to add at least one answer in real time so we would get more realistic picture of it.

[@theprocess-YT]

so i cannaot code can you make toturial for using ph3 which is free and have vision and also use visper ai to convert text to speech and other free tools so minimizing the cost to completely zero I am a student trying out these stuff and don't wanna pay or don't have money to pay for the API or other things so please make a toturial using all the free and open source tools

[@juanmanuelzwiener4447]

Santiago, the voices of assistant are only in english? or also in spanish? abrazo crack!

[@underfitted]

They speak Spanish too

[@dmitrypehovski]

Hi , i start test with all your steps and got stuck on the fact that text and audio from the openai api are not transferred to livekit, all requests pass in the terminal , tried many solutions...doesnt work

[@densonsmith2]

I think I may have a similar issue on Windows there is some problem with the ffmpeg library.

[@sr.modanez]

obrigado, fantástico o vídeo 👏👏👏👏👏👏👏👏👏

[@Brou15O]

could i get this on my smartphone?

[@underfitted]

As is, no. You’ll need to rewrite it in a phone-friendly language

[@rxWar]

Nice men thanks

[@boooosh2007]

Is this functionally any different than your previous video?

[@underfitted]

While they work the same for the demo, my previous code is very brittle. This one is much better because I’m using an entire existing infrastructure to support it.

[@danieladama8105]

This is great!

[@apdurden]

Yeah, this is cool but not helping. I can open the LiveKit interface but can't find a way to get the agent to connect. API keys all correct

[@apdurden]

I think the track management piece has changed since you made this. Running into no local_participant attribute for the Room object

[@nmstoker]

Shame that the hook with videos is start open source and then get people draw into handling supporting functions via a commercial platform (for $$$)

[@jsanti1000]

Dangggggggg!!!

[@aidanthompson5053]

<a href="#" class="seekto" data-time="158">2:38</a>

[@densonsmith2]

Has anyone gotten this to work on Windows?

[@LesBrickodeurs]

No I've got an error at line 12

[@LesBrickodeurs]

from livekit.agents.voice_assistant import AssistantContext, VoiceAssistant ImportError: cannot import name 'AssistantContext' from 'livekit.agents.voice_assistant' (D:\Github\livekit-assistant\.venv\Lib\site-packages\livekit\agents\voice_assistant\__init__.py)

[@davidkeane1820]

@@LesBrickodeurs yes the SDKs have changed and a lot of this no longer works off the bat ..im still playing around but it probably needs redoing

[@Noahperaudon]

Hey I have a issue with key api livekit its telling me error like its invalid

[@AI_by_AI_007]

Me as well -- YOU on windows or MAC as you try this?

[@Noahperaudon]

@@AI_by_AI_007 windows

[@Noahperaudon]

@@AI_by_AI_007Windows

[@rahahoseini1523]

@@AI_by_AI_007 How can I access to the API Keys? could you please tell me step by step.

[@bhaskerbobby]

Hi Im getting following error --> {"message": "draining worker", "level": "INFO", "id": "unregistered", "timeout": 60, "timestamp": "2024-08-16T<a href="#" class="seekto" data-time="146">02:26</a>:14.669243+<a href="#" class="seekto" data-time="0">00:00</a>"} {"message": "shutting down worker", "level": "INFO", "id": "unregistered", "timestamp": "2024-08-16T<a href="#" class="seekto" data-time="146">02:26</a>:14.670548+<a href="#" class="seekto" data-time="0">00:00</a>"}

[@YounessArjoune]

How did you get passed this error if you ever did?