Local LLM-Powered Voice Assistant on Raspberry Pi

The recent GPT-4o audio demo proved that an LLM-powered voice assistant done correctly could create an awe-inspiring experience. Unfortunately, GPT-4o's audio feature is not publicly available. Instead of busy waiting, we will show you how to build a voice assistant of the same caliber right now in less than 400 lines of Python using Picovoice's on-device voice AI and local LLM stacks.
Why use Picovoice's tech stack instead of OpenAI? Picovoice is on-device, meaning voice processing and LLM inference are performed locally without the user's data traveling to a third-party API. Products built with Picovoice are private by design, compliant (GDPR, HIPPA, ...), and real-time without unreliable network (API) latency.
Blog: picovoice.ai/b...
GitHub: github.com/Pic...

[@zopenzop2225]

What about raspberry pi 3, can it run on that? or is 4 needed?

[@picovoice]

picoLLM supports 4 and 5 at the moment.

[@IronSpidey02]

Can it run on a raspberry pi 4?

[@picovoice]

Yes.