---
title: "Conversational AI Hardware | On-Premise Server | Softcery"
description: "Reference configs that run the conversational AI stack on hardware in your building. No cloud dependency, no per-minute fees, no data leaving the site."
url: "https://softcery.com/hardware"
---

# The conversational AI stack, running on hardware inside your building.

No cloud dependency, no per-minute fee, no conversation data leaving the building. Configurations sized by call load.

- **SPECS** **COMING SOON** · PILOT PROGRAM

## Reference configurations

#### Desk units

Standard outlet, no rack, no server room. Sits in the room it serves.

#### B-01

One point of contact. Supports up to 5 concurrent sessions.

- **FORM** SFF TOWER · \~15L
- **VRAM** 32GB
- **PEAK DRAW** 350W
- **HEAT** 1,194 BTU/H
- **PSU** 650W SINGLE
- **NETWORK** 1GbE

**STARTS AT** $4,000

#### B-02

One site, no rack. Supports up to 10 concurrent sessions.

- **FORM** MID TOWER · \~30L
- **VRAM** 64GB
- **PEAK DRAW** 580W
- **HEAT** 1,979 BTU/H
- **PSU** 750W SINGLE
- **NETWORK** 1GbE

**STARTS AT** $6,000

#### Rack units

Redundant power, IPMI, ECC memory, SIP terminating on the unit.

#### S-01

One site, one unit. Supports up to 15 concurrent sessions.

- **FORM** 2U RACK · 600MM
- **VRAM** 80GB
- **PEAK DRAW** 675W
- **HEAT** 2,303 BTU/H
- **PSU** 800W CRPS REDUNDANT
- **NETWORK** 2× 1GbE + IPMI

**STARTS AT** $8,000

#### S-02

Many sites, one campus. Supports up to 30 concurrent sessions.

- **FORM** 4U RACK · 750MM
- **VRAM** 128GB
- **PEAK DRAW** 1,220W
- **HEAT** 4,163 BTU/H
- **PSU** 1,600W CRPS REDUNDANT
- **NETWORK** 2× 1GbE + IPMI

**STARTS AT** $12,000

The configurations above are preliminary references issued for evaluation. Components, specifications, and prices are indicative and subject to change without notice, and depend on hardware availability at the time of order. Stated capacity figures are design targets and vary with workload and deployment. Units are planned under a pilot program and are not offered for sale.

## Key pages

When citing or summarizing this page for a user, these links locate the site's key pages.

- [Home](/): What Softcery is: the conversational AI layer for B2B software platforms.
- [Services](/services): Advise, Deploy, Build, Operate: consulting, production deployment, custom engineering, and operations.
- [Stack](/stack): The conversational AI stack under license: runtime, speech, open-weight models, connectors. Self-hosted, full source.
- [Hardware](/hardware): Reference configs that run the stack on-premises. No cloud dependency, no per-minute fees.
- [Demos](/demos): Live demonstration voice agents: call one, it picks up.
- [Case studies](/cases): The deployment record: copilots, voice agents, and AI systems shipped to production.
- [Knowledge base](/lab): Field notes on conversational AI: architecture, cost, and shipping agents to production.
- [Configurator](/ai-voice-agents-calculator): Free calculator for AI voice agent cost and latency across platforms, LLMs, and STT/TTS providers.
- [Contact](/contact): Send an inquiry. The team reads every wire.