Join us in this exciting journey as we build a simple local AI Voice Assistant right from scratch! In this comprehensive video, we guide you through setting up an AI agent that operates entirely within your computer, executing tasks like creating, reading, editing, and deleting files, and managing tasks in a database—all by voice command (I'll do a second version of this soon integrating more capabilities like emails, calendar management etc...). Learn to install and configure key models like Whisper and Llama 3.2, harness the power of two-calling for enhanced functionality, and integrate everything into a seamless app using Gradio. Perfect for tech enthusiasts and budding developers eager to dive into AI development locally. That's it! If you like the video don't forget to like and subscribe! :)
📚 Chapters:
00:00 - Introduction to Building a Local AI Voice Assistant
00:18 - Requirements for the Voice Assistant
00:42 - Using Whisper for Voice Control
02:00 - Setting Up Virtual Environment and Dependencies
03:19 - Installing and Activating the Environment
05:10 - Testing the Setup with Code Imports
06:39 - Setting Up Whisper Model for Audio Transcription
07:23 - Adjusting the Transcription Pipeline
08:04 - Introduction to Llama 3.2 for Conversational AI
09:36 - Setting Up Interaction with Llama 3.2
12:03 - Function for Interacting with Llama Model
13:21 - Preparing Audio Input for Transcription
15:36 - Recording Audio with Python
17:14 - Transcribing Audio File
18:59 - Reconnecting Transcription with Llama
19:12 - Building Task Management Features
22:00 - Handling Task Data with Pandas
23:35 - Two Calling for Executing AI Commands
26:47 - Adding Create Task Functionality to AI
30:32 - Processing AI Tool Calls for Tasks
34:44 - Extending AI Capabilities to File Management
40:12 - Debugging Tool Setup
43:30 - Transitioning to Gradio App Interface
45:16 - Implementing Gradio Interface for AI
50:03 - Testing the Gradio Application
52:24 - Troubleshooting Audio Input in Gradio
57:59 - Conclusion and Wrap Up
🔗 Links:
Source code: https://github.com/EnkrateiaLucca/loc...
Subscribe!: / @automatalearninglab
Tiktok: https://www.tiktok.com/@enkrateialucc...
Twitter: / lucasenkrateia
LinkedIn: / lucas-soares-969044167
Check out my course on prompt engineering:
https://automatalearninglab.thinkific...
Support the Channel!
Buy me a cup of coffee: https://tr.ee/7tYsD-tUu2
Paypal: https://paypal.me/lucasenkrateia?coun...