Real-Time Conversational AI Avatar

Experimental deployment of a local conversational stack on an ARM VM.

AIOllamaDockerARM

OPENTALKING

Context

Explore a conversational avatar while reducing dependency on external APIs.

Hosted solutions can add recurring costs and external dependencies.

Containerized deployment of a conversational engine and local LLM on an ARM VM.

Compute constraints should be measured early when sizing a real-time demo.

Under the hood

Architecture, constraints, deliverables and real impact.

01 AI

02 Ollama

03 Docker

04 ARM

Compute constraints should be measured early when sizing a real-time demo.

Designed for real-world use

I start from the problem and business flow, then aim for an observable, testable and maintainable solution rather than a demo effect.