Skip to main content

Overview

Before deploying Smallest Self-Host, you’ll need credentials from Smallest.ai and infrastructure with GPU support.

Credentials from Smallest.ai

Contact [email protected] to obtain the following:
Your unique license key for validation. This is required for all deployments.You’ll add this to your configuration:
global:
  licenseKey: "your-license-key-here"
Or as an environment variable:
LICENSE_KEY=your-license-key-here
Credentials to pull Docker images from quay.io:
  • Username
  • Password
  • Email
Login to the registry:
docker login quay.io
For Kubernetes, you’ll add these to your values.yaml:
global:
  imageCredentials:
    create: true
    registry: quay.io
    username: "your-username"
    password: "your-password"
    email: "[email protected]"
Download URLs for the AI models (STT and/or TTS).For Docker deployments, add to your .env:
MODEL_URL=your-model-url-here
For Kubernetes, add to values.yaml:
models:
  asrModelUrl: "your-asr-model-url"
  ttsModelUrl: "your-tts-model-url"

Infrastructure Requirements

GPU Requirements

  • NVIDIA GPU with 16+ GB VRAM
  • Recommended: A10, L4, L40s, T4, or A100
  • NVIDIA Driver 525+ (for A10, A100, L4)
  • NVIDIA Driver 470+ (for T4, V100)

Container Runtime

  • Docker 20.10+ or Podman 4.0+
  • NVIDIA Container Toolkit
  • For Kubernetes: GPU Operator or Device Plugin

Minimum Resources

ComponentCPUMemoryGPUStorage
Lightning ASR4-8 cores12-16 GB1x NVIDIA (16+ GB VRAM)50+ GB
Lightning TTS4-8 cores12-16 GB1x NVIDIA (16+ GB VRAM)20+ GB
API Server0.5-2 cores512 MB - 2 GBNone1 GB
License Proxy0.25-1 core256-512 MBNone100 MB
Redis0.5-1 core512 MB - 2 GBNone1 GB

Network Requirements

The License Proxy requires outbound HTTPS access to validate licenses:
EndpointPortPurpose
console-api.smallest.ai443License validation and usage reporting
Ensure your firewall and network policies allow outbound HTTPS traffic to console-api.smallest.ai.

Next Steps

Choose your deployment method and follow the specific prerequisites: