Skip to main content

​
On-prem Introduction

Not available today. This describes work we intend to do, not a feature you can buy or switch on. Where it concerns where your data is held, our Privacy Policy is the operative statement and it overrides anything on this page.
For organizations with the highest security, privacy, or latency requirements, Movoice AI offers On-Premise Deployments.

​
Why Choose On-Prem?

  1. Direct Data Control: Keep all call audio and transcriptions within your own secure VPC or physical servers.
  2. Zero External Dependencies: Run your own ASR, LLM (e.g., Llama 3), and TTS clusters for complete independence.
  3. Low Latency (LAN): If your internal systems are local, voice AI processing happens on the same network, eliminating internet travel time.

​
Deployment Architecture

We provide our entire stack as a set of Docker Containers orchestrated via Kubernetes (K8s).
  • Movoice Core: The orchestration engine.
  • Internal Database: Stores your agents and session data (PostgreSQL/Redis).
  • VAD/Voice Gateway: Handles the real-time audio processing.

​
Enterprise Requirements

On-Premise deployment is exclusively available for Enterprise customers. This requires a dedicated onboarding session with our solutions architects to map your infrastructure and compliance needs.

​
Contact Us

Interested in running Movoice AI on your own servers? Please reach out to enterprise@movoice.ai.