> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cartesia.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Getting Started

> Prerequisites and initial setup for Cartesia self-hosted deployments

# Prerequisites

Before deploying Cartesia's self-hosted solution, you'll need:

## Enterprise Contract

Cartesia's self-hosted products generally require an enterprise contract. Please reach out to [support@cartesia.ai](mailto:support@cartesia.ai) to request a conversation with our Go-to-Market team.

## Infrastructure

### Hardware Requirements

Cartesia models require GPUs running NVidia devices from the Ampere family or newer, with at least 24GB GPU Memory. We'll provide more specifics
depending on how you run your GPU clusters.  See [Hardware Selection](/self-hosted/hardware-selection) for more details.

### Deployment Options

You can deploy a self-hosted Cartesia cluster in one of 3 ways that we provide today:

* Via Helm Charts on a Managed Kubernetes Cluster with the right hardware.
* Via Docker Compose / Docker Swarm on bare-metal or VM nodes (beta).
* Via managed endpoints on Sagemaker Jumpstart.

Since all of our code executes in containers, you can go with a much more customized deployment option as well.

# Setup Stages

<Note>We highly recommend trying out our cloud offering first, since you can test your application and integrate it without all the work required for self-hosting.</Note>

<Steps>
  <Step title="Create Cartesia Account">
    Sign up at [play.cartesia.ai](https://play.cartesia.ai) and create an API key.
    Navigate to [play.cartesia.ai/keys](https://play.cartesia.ai/keys) and select your organization.
  </Step>

  <Step title="Request Enterprise Access">
    Contact [support@cartesia.ai](mailto:support@cartesia.ai) for getting enterprise access.

    If you're deploying on [AWS Sagemaker](/self-hosted/cloud-service-provisioning), you can request directly on the cloud platform itself.
  </Step>

  <Step title="Choose Deployment Method">
    Select your preferred deployment approach based on your infrastructure:

    * [**Managed Kubernetes**](/self-hosted/managed-kubernetes)
    * [**Docker**](/self-hosted/docker-compose) (beta)
    * [**Cloud Service Provisioning**](/self-hosted/cloud-service-provisioning)

    Depending on how you're deploying, you'll also decide on the hardware at this stage.
  </Step>

  <Step title="Deploy">
    Once approved, you'll receive access to:

    * Google Cloud Storage bucket containing cartesia-kube and related artifacts (Docker images, voices, LoRA weights)
    * Private Docker registry credentials
    * Helm chart repositories
    * Terraform configuration examples
    * Deployment documentation and support
    * An offline license (required if you are doing an [air-gapped deployment](/self-hosted/air-gapped))

    See [Provisioned Resources](/self-hosted/provisioned-resources) for a full breakdown of what's included and how to access each resource, including downloading cartesia-kube.

    Download cartesia-kube from the GCS bucket and follow the guide for your chosen deployment method to get up and running. The provided configurations work out of the box, but can be customized to fit your infrastructure needs.
  </Step>

  <Step title="Post Deployment">
    Post deployment, we provide some resources to validate and benchmark your deployment on your own hardware. See [Smoke Tests and Benchmarking](/self-hosted/smoke-tests-and-benchmarking).
    If you're looking to setup monitoring on the deployment, checkout [Metrics](/self-hosted/metrics)
  </Step>
</Steps>

# Pre-deployment Checklist

After choosing your deployment method (Step 3 above), work through this detailed checklist before executing Step 4 (Deploy).

## Infrastructure readiness

* Hardware confirmed against the [Compatibility Matrix](/self-hosted/hardware-selection#compatibility-matrix) — Kubernetes version, GPU type and memory, GPU exposure mechanism.
* Network plan reviewed against the [port matrix and outbound egress requirements](/self-hosted/architecture#network-topology-and-ports). Firewall rules approved.
* TLS plan reviewed against the [Ingress and TLS](/self-hosted/managed-kubernetes#ingress-and-tls) guidance for your platform.
* DNS plan: hostname owners identified, A record reservations made.
* Cluster either provisioned (Helm-only path) or Terraform-ready (Terraform path) — see [Managed Kubernetes](/self-hosted/managed-kubernetes).

## Configuration

* `cartesia-kube` downloaded and verified — see [Deployment Configurations](/self-hosted/provisioned-resources#deployment-configurations).
* Config file populated for your deployment method — see [Configuration Files](/self-hosted/provisioned-resources#configuration-files).
* Image registry, release tag, ingress hostname, certificate, and namespace settings reviewed — see [Managed Kubernetes](/self-hosted/managed-kubernetes) for the full value set.
* Worker fleet sized — one worker per GPU, `capacity` set per the [Concurrency per GPU](/self-hosted/hardware-selection#concurrency-per-gpu) table.
* (Air-gapped only) License file downloaded and seed configured — see [Seeding the initial license](/self-hosted/air-gapped#at-install-time).
* Autoscaling thresholds set if KEDA or the cluster autoscaler will be used — see [Autoscaling](/self-hosted/auto-scaling).