Build A Talking AI with LLAMA 3 (Python tutorial)

Learn to build a talking AI! This tutorial covers real-time transcription with AssemblyAI, using LLAMA 3 as the language model with Ollama, and ElevenLabs for text-to-speech.

Timestamps:
00:00 - Demo
00:17 - How we will build a talking AI with LLAMA 3
00:34 - Streaming Speech-to-text with AssemblyAI
02:07 - Step 1: Installing python libraries
05:35 - Step 2: Streaming Speech-to-text with AssemblyAI
09:10 - Step 3: Generating an AI response with Ollama & LLAMA 3 and Text-to-speech using ElevenLabs

▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT ▬▬▬▬▬▬▬▬▬▬▬▬

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

#MachineLearning #DeepLearning

[Anonymatter]

Great video, got it working only to find it requires payment. Never mind, it is a great tutorial.

[cheybrown]

Amazing video 🎉.

Was portaudio the library used to listen and capture the audio?

[RaviTejaVanjarapu]

Can you not send converse in audio with Llama 3.2 directly instead of converting and conversing in text ? I heard Llama 3.2 is multimodal model.

[ankittripathi]

On Ubuntu facing issues related to Alsa during speech detection. Do you have any idea on this?

[marketfinds]

Sorry, newbie, what is the 'source' command you use at the start?
You also jumped from step 1 to 6.
ie when I run: The term 'ollama' is not recognized as the name of a cmdlet

Thanks

[gileneusz]

I'm not sure if talking to animals is a good idea....

[MrOktony]

Don’t forget you can also use text to speech, found in settings accessibility - it’s not real time, but at least it’s private. It would be awesome if you could get terminal speaking in real time, without using web based services..

[fiorellademedina]

hello, how you can know the version of llama 3 with ollama? Is it 8B or 70B.?

[AGSAnanya]

just want to know if this can be used a voice assistant that take orders in a drive in locations

[dippyzippy]

This is great video. I'm wondering if the voice can be changed? I've tried everything, but I'm unable to change the voice?

[godu]

real time transcription is blank can someone help me out

[internationalfriendsnetwork]

this is all wel and good, but something you have over looked, are the needs of those with blindness or visual impairments. Why have you not considdered a fully narrated/audio discribed accessible approach. How is someone with no eye site ment to follow along with you in your videos?

[鍾雨蓁智慧商務系]

I'd like to know if using AssemblyAI for real-time transcription requires a paid subscription
thanks

[tanb]

How can I integrate with a bot created using chainlit ?

[PrintingBTW]

Can this be ran locally without any internet connection once setup

[GurlalSingh-bc]

is it possible to attach file file and yalk to assistant on that document ?

[Stevenschulzhh]

Can live speech transcription be used in German or any other language than English ??

[rabidrabbitmeow]

Any idea how to deal with this?

OSError: [Errno -9996] Invalid input device (no default output device)

[Pixelatedcharts]

Can we use this api free for Life time ?

[Threecommaaclub]

When running the code i receive the following message in the terminal "`ALSA lib confmic.c.:160,

i think this may be a warning message but i want to surpress them, how would i go about doing that?